{"id":11666445,"url":"https://github.com/AgentOps-AI/tokencost","last_synced_at":"2025-10-06T11:32:24.554Z","repository":{"id":212178608,"uuid":"726692169","full_name":"AgentOps-AI/tokencost","owner":"AgentOps-AI","description":"Easy token price estimates for LLMs","archived":false,"fork":false,"pushed_at":"2024-04-23T07:03:49.000Z","size":1626,"stargazers_count":190,"open_issues_count":4,"forks_count":9,"subscribers_count":7,"default_branch":"main","last_synced_at":"2024-04-23T11:15:21.671Z","etag":null,"topics":["analytics","claude","large-language-models","llm","observability","openai","price","price-tracker","token","tokenization"],"latest_commit_sha":null,"homepage":"https://agentops.ai","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AgentOps-AI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2023-12-03T04:56:44.000Z","updated_at":"2024-06-16T00:00:12.578Z","dependencies_parsed_at":"2024-01-26T03:28:47.739Z","dependency_job_id":"60a60076-9837-476f-b02a-21f9352fb183","html_url":"https://github.com/AgentOps-AI/tokencost","commit_stats":null,"previous_names":["agentops-ai/tokencost"],"tags_count":16,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AgentOps-AI%2Ftokencost","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AgentOps-AI%2Ftokencost/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AgentOps-AI%2Ftokencost/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AgentOps-AI%2Ftokencost/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AgentOps-AI","download_url":"https://codeload.github.com/AgentOps-AI/tokencost/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":219877270,"owners_count":16554853,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["analytics","claude","large-language-models","llm","observability","openai","price","price-tracker","token","tokenization"],"created_at":"2024-06-25T13:06:32.596Z","updated_at":"2025-10-06T11:32:24.543Z","avatar_url":"https://github.com/AgentOps-AI.png","language":"Python","readme":"\u003cp align=\"center\"\u003e\n \u003cimg src=\"https://raw.githubusercontent.com/AgentOps-AI/tokencost/main/tokencost.png\" height=\"300\" alt=\"Tokencost\" /\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n \u003cem\u003eClientside token counting + price estimation for LLM apps and AI agents.\u003c/em\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n \u003ca href=\"https://pypi.org/project/tokencost/\" target=\"_blank\"\u003e\n \u003cimg alt=\"Python\" src=\"https://img.shields.io/badge/python-3670A0?style=for-the-badge\u0026logo=python\u0026logoColor=ffdd54\" /\u003e\n \u003cimg alt=\"Version\" src=\"https://img.shields.io/pypi/v/tokencost?style=for-the-badge\u0026color=3670A0\"\u003e\n \u003c/a\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n\u003ca href=\"https://twitter.com/agentopsai/\"\u003e🐦 Twitter\u003c/a\u003e\n\u003cspan\u003e\u0026nbsp;\u0026nbsp;•\u0026nbsp;\u0026nbsp;\u003c/span\u003e\n\u003ca href=\"https://discord.com/invite/FagdcwwXRR\"\u003e📢 Discord\u003c/a\u003e\n\u003cspan\u003e\u0026nbsp;\u0026nbsp;•\u0026nbsp;\u0026nbsp;\u003c/span\u003e\n\u003ca href=\"https://agentops.ai/?tokencost\"\u003e🖇️ AgentOps\u003c/a\u003e\n\u003c/p\u003e\n\n\n# TokenCost\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) ![PyPI - Version](https://img.shields.io/pypi/v/tokencost)\n[![X (formerly Twitter) Follow](https://img.shields.io/twitter/follow/AgentOpsAI)](https://x.com/agentopsai)\n\nTokencost helps calculate the USD cost of using major Large Language Model (LLMs) APIs by calculating the estimated cost of prompts and completions.\n\nBuilding AI agents? Check out [AgentOps](https://agentops.ai/?tokencost)\n\n\n### Features\n* **LLM Price Tracking** Major LLM providers frequently add new models and update pricing. This repo helps track the latest price changes\n* **Token counting** Accurately count prompt tokens before sending OpenAI requests\n* **Easy integration** Get the cost of a prompt or completion with a single function\n\n### Example usage:\n\n```python\nfrom tokencost import calculate_prompt_cost, calculate_completion_cost\n\nmodel = \"gpt-3.5-turbo\"\nprompt = [{ \"role\": \"user\", \"content\": \"Hello world\"}]\ncompletion = \"How may I assist you today?\"\n\nprompt_cost = calculate_prompt_cost(prompt, model)\ncompletion_cost = calculate_completion_cost(completion, model)\n\nprint(f\"{prompt_cost} + {completion_cost} = {prompt_cost + completion_cost}\")\n# 0.0000135 + 0.000014 = 0.0000275\n```\n\n## Installation\n\n#### Recommended: [PyPI](https://pypi.org/project/tokencost/):\n\n```bash\npip install tokencost\n```\n\n## Usage\n\n### Cost estimates\nCalculating the cost of prompts and completions from OpenAI requests\n```python\nfrom openai import OpenAI\n\nclient = OpenAI()\nmodel = \"gpt-3.5-turbo\"\nprompt = [{ \"role\": \"user\", \"content\": \"Say this is a test\"}]\n\nchat_completion = client.chat.completions.create(\n messages=prompt, model=model\n)\n\ncompletion = chat_completion.choices[0].message.content\n# \"This is a test.\"\n\nprompt_cost = calculate_prompt_cost(prompt, model)\ncompletion_cost = calculate_completion_cost(completion, model)\nprint(f\"{prompt_cost} + {completion_cost} = {prompt_cost + completion_cost}\")\n# 0.0000180 + 0.000010 = 0.0000280\n```\n\n**Calculating cost using string prompts instead of messages:**\n```python\nfrom tokencost import calculate_prompt_cost\n\nprompt_string = \"Hello world\" \nresponse = \"How may I assist you today?\"\nmodel= \"gpt-3.5-turbo\"\n\nprompt_cost = calculate_prompt_cost(prompt_string, model)\nprint(f\"Cost: ${prompt_cost}\")\n# Cost: $3e-06\n```\n\n**Counting tokens**\n\n```python\nfrom tokencost import count_message_tokens, count_string_tokens\n\nmessage_prompt = [{ \"role\": \"user\", \"content\": \"Hello world\"}]\n# Counting tokens in prompts formatted as message lists\nprint(count_message_tokens(message_prompt, model=\"gpt-3.5-turbo\"))\n# 9\n\n# Alternatively, counting tokens in string prompts\nprint(count_string_tokens(prompt=\"Hello world\", model=\"gpt-3.5-turbo\"))\n# 2\n\n```\n\n## How tokens are counted\n\nUnder the hood, strings and ChatML messages are tokenized using [Tiktoken](https://github.com/openai/tiktoken), OpenAI's official tokenizer. Tiktoken splits text into tokens (which can be parts of words or individual characters) and handles both raw strings and message formats with additional tokens for message formatting and roles.\n\nFor Anthropic models above version 3 (i.e. Sonnet 3.5, Haiku 3.5, and Opus 3), we use the [Anthropic beta token counting API](https://docs.anthropic.com/claude/docs/beta-api-for-counting-tokens) to ensure accurate token counts. For older Claude models, we approximate using Tiktoken with the cl100k_base encoding.\n\n\n## Cost table\nUnits denominated in USD. All prices can be located [here](pricing_table.md).\n\n\u003c!-- PRICING_TABLE_START --\u003e\n\n| Model Name | Prompt Cost (USD) per 1M tokens | Completion Cost (USD) per 1M tokens | Max Prompt Tokens | Max Output Tokens |\n|:----------------------------------------------------------------------|:----------------------------------|:--------------------------------------|:--------------------|--------------------:|\n| gpt-4 | $30 | $60 | 8192 | 4096 |\n| gpt-4o | $2.5 | $10 | 128,000 | 16384 |\n| gpt-4o-audio-preview | $2.5 | $10 | 128,000 | 16384 |\n| gpt-4o-audio-preview-2024-10-01 | $2.5 | $10 | 128,000 | 16384 |\n| gpt-4o-mini | $0.15 | $0.6 | 128,000 | 16384 |\n| gpt-4o-mini-2024-07-18 | $0.15 | $0.6 | 128,000 | 16384 |\n| o1-mini | $1.1 | $4.4 | 128,000 | 65536 |\n| o1-mini-2024-09-12 | $3 | $12 | 128,000 | 65536 |\n| o1-preview | $15 | $60 | 128,000 | 32768 |\n| o1-preview-2024-09-12 | $15 | $60 | 128,000 | 32768 |\n| chatgpt-4o-latest | $5 | $15 | 128,000 | 4096 |\n| gpt-4o-2024-05-13 | $5 | $15 | 128,000 | 4096 |\n| gpt-4o-2024-08-06 | $2.5 | $10 | 128,000 | 16384 |\n| gpt-4-turbo-preview | $10 | $30 | 128,000 | 4096 |\n| gpt-4-0314 | $30 | $60 | 8,192 | 4096 |\n| gpt-4-0613 | $30 | $60 | 8,192 | 4096 |\n| gpt-4-32k | $60 | $120 | 32,768 | 4096 |\n| gpt-4-32k-0314 | $60 | $120 | 32,768 | 4096 |\n| gpt-4-32k-0613 | $60 | $120 | 32,768 | 4096 |\n| gpt-4-turbo | $10 | $30 | 128,000 | 4096 |\n| gpt-4-turbo-2024-04-09 | $10 | $30 | 128,000 | 4096 |\n| gpt-4-1106-preview | $10 | $30 | 128,000 | 4096 |\n| gpt-4-0125-preview | $10 | $30 | 128,000 | 4096 |\n| gpt-4-vision-preview | $10 | $30 | 128,000 | 4096 |\n| gpt-4-1106-vision-preview | $10 | $30 | 128,000 | 4096 |\n| gpt-3.5-turbo | $1.5 | $2 | 16,385 | 4096 |\n| gpt-3.5-turbo-0301 | $1.5 | $2 | 4,097 | 4096 |\n| gpt-3.5-turbo-0613 | $1.5 | $2 | 4,097 | 4096 |\n| gpt-3.5-turbo-1106 | $1 | $2 | 16,385 | 4096 |\n| gpt-3.5-turbo-0125 | $0.5 | $1.5 | 16,385 | 4096 |\n| gpt-3.5-turbo-16k | $3 | $4 | 16,385 | 4096 |\n| gpt-3.5-turbo-16k-0613 | $3 | $4 | 16,385 | 4096 |\n| ft:gpt-3.5-turbo | $3 | $6 | 16,385 | 4096 |\n| ft:gpt-3.5-turbo-0125 | $3 | $6 | 16,385 | 4096 |\n| ft:gpt-3.5-turbo-1106 | $3 | $6 | 16,385 | 4096 |\n| ft:gpt-3.5-turbo-0613 | $3 | $6 | 4,096 | 4096 |\n| ft:gpt-4-0613 | $30 | $60 | 8,192 | 4096 |\n| ft:gpt-4o-2024-08-06 | $3.75 | $15 | 128,000 | 16384 |\n| ft:gpt-4o-mini-2024-07-18 | $0.3 | $1.2 | 128,000 | 16384 |\n| ft:davinci-002 | $2 | $2 | 16,384 | 4096 |\n| ft:babbage-002 | $0.4 | $0.4 | 16,384 | 4096 |\n| text-embedding-3-large | $0.13 | $0 | 8,191 | nan |\n| text-embedding-3-small | $0.02 | $0 | 8,191 | nan |\n| text-embedding-ada-002 | $0.1 | $0 | 8,191 | nan |\n| text-embedding-ada-002-v2 | $0.1 | $0 | 8,191 | nan |\n| text-moderation-stable | $0 | $0 | 32,768 | 0 |\n| text-moderation-007 | $0 | $0 | 32,768 | 0 |\n| text-moderation-latest | $0 | $0 | 32,768 | 0 |\n| 256-x-256/dall-e-2 | -- | -- | nan | nan |\n| 512-x-512/dall-e-2 | -- | -- | nan | nan |\n| 1024-x-1024/dall-e-2 | -- | -- | nan | nan |\n| hd/1024-x-1792/dall-e-3 | -- | -- | nan | nan |\n| hd/1792-x-1024/dall-e-3 | -- | -- | nan | nan |\n| hd/1024-x-1024/dall-e-3 | -- | -- | nan | nan |\n| standard/1024-x-1792/dall-e-3 | -- | -- | nan | nan |\n| standard/1792-x-1024/dall-e-3 | -- | -- | nan | nan |\n| standard/1024-x-1024/dall-e-3 | -- | -- | nan | nan |\n| whisper-1 | -- | -- | nan | nan |\n| tts-1 | -- | -- | nan | nan |\n| tts-1-hd | -- | -- | nan | nan |\n| azure/tts-1 | -- | -- | nan | nan |\n| azure/tts-1-hd | -- | -- | nan | nan |\n| azure/whisper-1 | -- | -- | nan | nan |\n| azure/o1-mini | $1.21 | $4.84 | 128,000 | 65536 |\n| azure/o1-mini-2024-09-12 | $1.1 | $4.4 | 128,000 | 65536 |\n| azure/o1-preview | $15 | $60 | 128,000 | 32768 |\n| azure/o1-preview-2024-09-12 | $15 | $60 | 128,000 | 32768 |\n| azure/gpt-4o | $2.5 | $10 | 128,000 | 16384 |\n| azure/gpt-4o-2024-08-06 | $2.5 | $10 | 128,000 | 16384 |\n| azure/gpt-4o-2024-05-13 | $5 | $15 | 128,000 | 4096 |\n| azure/global-standard/gpt-4o-2024-08-06 | $2.5 | $10 | 128,000 | 16384 |\n| azure/global-standard/gpt-4o-mini | $0.15 | $0.6 | 128,000 | 16384 |\n| azure/gpt-4o-mini | $0.16 | $0.66 | 128,000 | 16384 |\n| azure/gpt-4-turbo-2024-04-09 | $10 | $30 | 128,000 | 4096 |\n| azure/gpt-4-0125-preview | $10 | $30 | 128,000 | 4096 |\n| azure/gpt-4-1106-preview | $10 | $30 | 128,000 | 4096 |\n| azure/gpt-4-0613 | $30 | $60 | 8,192 | 4096 |\n| azure/gpt-4-32k-0613 | $60 | $120 | 32,768 | 4096 |\n| azure/gpt-4-32k | $60 | $120 | 32,768 | 4096 |\n| azure/gpt-4 | $30 | $60 | 8,192 | 4096 |\n| azure/gpt-4-turbo | $10 | $30 | 128,000 | 4096 |\n| azure/gpt-4-turbo-vision-preview | $10 | $30 | 128,000 | 4096 |\n| azure/gpt-35-turbo-16k-0613 | $3 | $4 | 16,385 | 4096 |\n| azure/gpt-35-turbo-1106 | $1 | $2 | 16,384 | 4096 |\n| azure/gpt-35-turbo-0613 | $1.5 | $2 | 4,097 | 4096 |\n| azure/gpt-35-turbo-0301 | $0.2 | $2 | 4,097 | 4096 |\n| azure/gpt-35-turbo-0125 | $0.5 | $1.5 | 16,384 | 4096 |\n| azure/gpt-35-turbo-16k | $3 | $4 | 16,385 | 4096 |\n| azure/gpt-35-turbo | $0.5 | $1.5 | 4,097 | 4096 |\n| azure/gpt-3.5-turbo-instruct-0914 | $1.5 | $2 | 4,097 | nan |\n| azure/gpt-35-turbo-instruct | $1.5 | $2 | 4,097 | nan |\n| azure/gpt-35-turbo-instruct-0914 | $1.5 | $2 | 4,097 | nan |\n| azure/mistral-large-latest | $8 | $24 | 32,000 | nan |\n| azure/mistral-large-2402 | $8 | $24 | 32,000 | nan |\n| azure/command-r-plus | $3 | $15 | 128,000 | 4096 |\n| azure/ada | $0.1 | $0 | 8,191 | nan |\n| azure/text-embedding-ada-002 | $0.1 | $0 | 8,191 | nan |\n| azure/text-embedding-3-large | $0.13 | $0 | 8,191 | nan |\n| azure/text-embedding-3-small | $0.02 | $0 | 8,191 | nan |\n| azure/standard/1024-x-1024/dall-e-3 | -- | $0 | nan | nan |\n| azure/hd/1024-x-1024/dall-e-3 | -- | $0 | nan | nan |\n| azure/standard/1024-x-1792/dall-e-3 | -- | $0 | nan | nan |\n| azure/standard/1792-x-1024/dall-e-3 | -- | $0 | nan | nan |\n| azure/hd/1024-x-1792/dall-e-3 | -- | $0 | nan | nan |\n| azure/hd/1792-x-1024/dall-e-3 | -- | $0 | nan | nan |\n| azure/standard/1024-x-1024/dall-e-2 | -- | $0 | nan | nan |\n| azure_ai/jamba-instruct | $0.5 | $0.7 | 70,000 | 4096 |\n| azure_ai/mistral-large | $4 | $12 | 32,000 | 8191 |\n| azure_ai/mistral-small | $1 | $3 | 32,000 | 8191 |\n| azure_ai/Meta-Llama-3-70B-Instruct | $1.1 | $0.37 | 8,192 | 2048 |\n| azure_ai/Meta-Llama-3.1-8B-Instruct | $0.3 | $0.61 | 128,000 | 2048 |\n| azure_ai/Meta-Llama-3.1-70B-Instruct | $2.68 | $3.54 | 128,000 | 2048 |\n| azure_ai/Meta-Llama-3.1-405B-Instruct | $5.33 | $16 | 128,000 | 2048 |\n| azure_ai/cohere-rerank-v3-multilingual | $0 | $0 | 4,096 | 4096 |\n| azure_ai/cohere-rerank-v3-english | $0 | $0 | 4,096 | 4096 |\n| azure_ai/Cohere-embed-v3-english | $0.1 | $0 | 512 | nan |\n| azure_ai/Cohere-embed-v3-multilingual | $0.1 | $0 | 512 | nan |\n| babbage-002 | $0.4 | $0.4 | 16,384 | 4096 |\n| davinci-002 | $2 | $2 | 16,384 | 4096 |\n| gpt-3.5-turbo-instruct | $1.5 | $2 | 8,192 | 4096 |\n| gpt-3.5-turbo-instruct-0914 | $1.5 | $2 | 8,192 | 4097 |\n| claude-instant-1 | $1.63 | $5.51 | 100,000 | 8191 |\n| mistral/mistral-tiny | $0.25 | $0.25 | 32,000 | 8191 |\n| mistral/mistral-small | $0.1 | $0.3 | 32,000 | 8191 |\n| mistral/mistral-small-latest | $0.1 | $0.3 | 32,000 | 8191 |\n| mistral/mistral-medium | $2.7 | $8.1 | 32,000 | 8191 |\n| mistral/mistral-medium-latest | $0.4 | $2 | 131,072 | 8191 |\n| mistral/mistral-medium-2312 | $2.7 | $8.1 | 32,000 | 8191 |\n| mistral/mistral-large-latest | $2 | $6 | 128,000 | 128000 |\n| mistral/mistral-large-2402 | $4 | $12 | 32,000 | 8191 |\n| mistral/mistral-large-2407 | $3 | $9 | 128,000 | 128000 |\n| mistral/pixtral-12b-2409 | $0.15 | $0.15 | 128,000 | 128000 |\n| mistral/open-mistral-7b | $0.25 | $0.25 | 32,000 | 8191 |\n| mistral/open-mixtral-8x7b | $0.7 | $0.7 | 32,000 | 8191 |\n| mistral/open-mixtral-8x22b | $2 | $6 | 65,336 | 8191 |\n| mistral/codestral-latest | $1 | $3 | 32,000 | 8191 |\n| mistral/codestral-2405 | $1 | $3 | 32,000 | 8191 |\n| mistral/open-mistral-nemo | $0.3 | $0.3 | 128,000 | 128000 |\n| mistral/open-mistral-nemo-2407 | $0.3 | $0.3 | 128,000 | 128000 |\n| mistral/open-codestral-mamba | $0.25 | $0.25 | 256,000 | 256000 |\n| mistral/codestral-mamba-latest | $0.25 | $0.25 | 256,000 | 256000 |\n| mistral/mistral-embed | $0.1 | -- | 8,192 | nan |\n| deepseek-chat | $0.14 | $0.28 | 128,000 | 4096 |\n| codestral/codestral-latest | $0 | $0 | 32,000 | 8191 |\n| codestral/codestral-2405 | $0 | $0 | 32,000 | 8191 |\n| text-completion-codestral/codestral-latest | $0 | $0 | 32,000 | 8191 |\n| text-completion-codestral/codestral-2405 | $0 | $0 | 32,000 | 8191 |\n| deepseek-coder | $0.14 | $0.28 | 128,000 | 4096 |\n| groq/llama2-70b-4096 | $0.7 | $0.8 | 4,096 | 4096 |\n| groq/llama3-8b-8192 | $0.05 | $0.08 | 8,192 | 8192 |\n| groq/llama3-70b-8192 | $0.59 | $0.79 | 8,192 | 8192 |\n| groq/llama-3.1-8b-instant | $0.05 | $0.08 | 128,000 | 8192 |\n| groq/llama-3.1-70b-versatile | $0.59 | $0.79 | 8,192 | 8192 |\n| groq/llama-3.1-405b-reasoning | $0.59 | $0.79 | 8,192 | 8192 |\n| groq/mixtral-8x7b-32768 | $0.24 | $0.24 | 32,768 | 32768 |\n| groq/gemma-7b-it | $0.07 | $0.07 | 8,192 | 8192 |\n| groq/gemma2-9b-it | $0.2 | $0.2 | 8,192 | 8192 |\n| groq/llama3-groq-70b-8192-tool-use-preview | $0.89 | $0.89 | 8,192 | 8192 |\n| groq/llama3-groq-8b-8192-tool-use-preview | $0.19 | $0.19 | 8,192 | 8192 |\n| cerebras/llama3.1-8b | $0.1 | $0.1 | 128,000 | 128000 |\n| cerebras/llama3.1-70b | $0.6 | $0.6 | 128,000 | 128000 |\n| friendliai/mixtral-8x7b-instruct-v0-1 | $0.4 | $0.4 | 32,768 | 32768 |\n| friendliai/meta-llama-3-8b-instruct | $0.1 | $0.1 | 8,192 | 8192 |\n| friendliai/meta-llama-3-70b-instruct | $0.8 | $0.8 | 8,192 | 8192 |\n| claude-instant-1.2 | $0.16 | $0.55 | 100,000 | 8191 |\n| claude-2 | $8 | $24 | 100,000 | 8191 |\n| claude-2.1 | $8 | $24 | 200,000 | 8191 |\n| claude-3-haiku-20240307 | $0.25 | $1.25 | 200,000 | 4096 |\n| claude-3-haiku-latest | $0.25 | $1.25 | 200,000 | 4096 |\n| claude-3-opus-20240229 | $15 | $75 | 200,000 | 4096 |\n| claude-3-opus-latest | $15 | $75 | 200,000 | 4096 |\n| claude-3-sonnet-20240229 | $3 | $15 | 200,000 | 4096 |\n| claude-3-5-sonnet-20240620 | $3 | $15 | 200,000 | 8192 |\n| claude-3-5-sonnet-20241022 | $3 | $15 | 200,000 | 8192 |\n| claude-3-5-sonnet-latest | $3 | $15 | 200,000 | 8192 |\n| text-bison | -- | -- | 8,192 | 2048 |\n| text-bison@001 | -- | -- | 8,192 | 1024 |\n| text-bison@002 | -- | -- | 8,192 | 1024 |\n| text-bison32k | $0.12 | $0.12 | 8,192 | 1024 |\n| text-bison32k@002 | $0.12 | $0.12 | 8,192 | 1024 |\n| text-unicorn | $10 | $28 | 8,192 | 1024 |\n| text-unicorn@001 | $10 | $28 | 8,192 | 1024 |\n| chat-bison | $0.12 | $0.12 | 8,192 | 4096 |\n| chat-bison@001 | $0.12 | $0.12 | 8,192 | 4096 |\n| chat-bison@002 | $0.12 | $0.12 | 8,192 | 4096 |\n| chat-bison-32k | $0.12 | $0.12 | 32,000 | 8192 |\n| chat-bison-32k@002 | $0.12 | $0.12 | 32,000 | 8192 |\n| code-bison | $0.12 | $0.12 | 6,144 | 1024 |\n| code-bison@001 | $0.12 | $0.12 | 6,144 | 1024 |\n| code-bison@002 | $0.12 | $0.12 | 6,144 | 1024 |\n| code-bison32k | $0.12 | $0.12 | 6,144 | 1024 |\n| code-bison-32k@002 | $0.12 | $0.12 | 6,144 | 1024 |\n| code-gecko@001 | $0.12 | $0.12 | 2,048 | 64 |\n| code-gecko@002 | $0.12 | $0.12 | 2,048 | 64 |\n| code-gecko | $0.12 | $0.12 | 2,048 | 64 |\n| code-gecko-latest | $0.12 | $0.12 | 2,048 | 64 |\n| codechat-bison@latest | $0.12 | $0.12 | 6,144 | 1024 |\n| codechat-bison | $0.12 | $0.12 | 6,144 | 1024 |\n| codechat-bison@001 | $0.12 | $0.12 | 6,144 | 1024 |\n| codechat-bison@002 | $0.12 | $0.12 | 6,144 | 1024 |\n| codechat-bison-32k | $0.12 | $0.12 | 32,000 | 8192 |\n| codechat-bison-32k@002 | $0.12 | $0.12 | 32,000 | 8192 |\n| gemini-pro | $0.5 | $1.5 | 32,760 | 8192 |\n| gemini-1.0-pro | $0.5 | $1.5 | 32,760 | 8192 |\n| gemini-1.0-pro-001 | $0.5 | $1.5 | 32,760 | 8192 |\n| gemini-1.0-ultra | $0.5 | $1.5 | 8,192 | 2048 |\n| gemini-1.0-ultra-001 | $0.5 | $1.5 | 8,192 | 2048 |\n| gemini-1.0-pro-002 | $0.5 | $1.5 | 32,760 | 8192 |\n| gemini-1.5-pro | $1.25 | $5 | 2,097,152 | 8192 |\n| gemini-1.5-pro-002 | $1.25 | $5 | 2,097,152 | 8192 |\n| gemini-1.5-pro-001 | $1.25 | $5 | 1,000,000 | 8192 |\n| gemini-1.5-pro-preview-0514 | $0.08 | $0.31 | 1,000,000 | 8192 |\n| gemini-1.5-pro-preview-0215 | $0.08 | $0.31 | 1,000,000 | 8192 |\n| gemini-1.5-pro-preview-0409 | $0.08 | $0.31 | 1,000,000 | 8192 |\n| gemini-1.5-flash | $0.08 | $0.3 | 1,000,000 | 8192 |\n| gemini-1.5-flash-exp-0827 | $0 | $0 | 1,000,000 | 8192 |\n| gemini-1.5-flash-002 | $0.08 | $0.3 | 1,048,576 | 8192 |\n| gemini-1.5-flash-001 | $0.08 | $0.3 | 1,000,000 | 8192 |\n| gemini-1.5-flash-preview-0514 | $0.08 | $0 | 1,000,000 | 8192 |\n| gemini-pro-experimental | $0 | $0 | 1,000,000 | 8192 |\n| gemini-flash-experimental | $0 | $0 | 1,000,000 | 8192 |\n| gemini-pro-vision | $0.5 | $1.5 | 16,384 | 2048 |\n| gemini-1.0-pro-vision | $0.5 | $1.5 | 16,384 | 2048 |\n| gemini-1.0-pro-vision-001 | $0.5 | $1.5 | 16,384 | 2048 |\n| medlm-medium | -- | -- | 32,768 | 8192 |\n| medlm-large | -- | -- | 8,192 | 1024 |\n| vertex_ai/claude-3-sonnet@20240229 | $3 | $15 | 200,000 | 4096 |\n| vertex_ai/claude-3-5-sonnet@20240620 | $3 | $15 | 200,000 | 8192 |\n| vertex_ai/claude-3-5-sonnet-v2@20241022 | $3 | $15 | 200,000 | 8192 |\n| vertex_ai/claude-3-haiku@20240307 | $0.25 | $1.25 | 200,000 | 4096 |\n| vertex_ai/claude-3-opus@20240229 | $15 | $75 | 200,000 | 4096 |\n| vertex_ai/meta/llama3-405b-instruct-maas | $0 | $0 | 32,000 | 32000 |\n| vertex_ai/meta/llama3-70b-instruct-maas | $0 | $0 | 32,000 | 32000 |\n| vertex_ai/meta/llama3-8b-instruct-maas | $0 | $0 | 32,000 | 32000 |\n| vertex_ai/meta/llama-3.2-90b-vision-instruct-maas | $0 | $0 | 128,000 | 2048 |\n| vertex_ai/mistral-large@latest | $2 | $6 | 128,000 | 8191 |\n| vertex_ai/mistral-large@2407 | $2 | $6 | 128,000 | 8191 |\n| vertex_ai/mistral-nemo@latest | $0.15 | $0.15 | 128,000 | 128000 |\n| vertex_ai/jamba-1.5-mini@001 | $0.2 | $0.4 | 256,000 | 256000 |\n| vertex_ai/jamba-1.5-large@001 | $2 | $8 | 256,000 | 256000 |\n| vertex_ai/jamba-1.5 | $0.2 | $0.4 | 256,000 | 256000 |\n| vertex_ai/jamba-1.5-mini | $0.2 | $0.4 | 256,000 | 256000 |\n| vertex_ai/jamba-1.5-large | $2 | $8 | 256,000 | 256000 |\n| vertex_ai/mistral-nemo@2407 | $3 | $3 | 128,000 | 128000 |\n| vertex_ai/codestral@latest | $0.2 | $0.6 | 128,000 | 128000 |\n| vertex_ai/codestral@2405 | $0.2 | $0.6 | 128,000 | 128000 |\n| vertex_ai/imagegeneration@006 | -- | -- | nan | nan |\n| vertex_ai/imagen-3.0-generate-001 | -- | -- | nan | nan |\n| vertex_ai/imagen-3.0-fast-generate-001 | -- | -- | nan | nan |\n| text-embedding-004 | $0.1 | $0 | 2,048 | nan |\n| text-multilingual-embedding-002 | $0.1 | $0 | 2,048 | nan |\n| textembedding-gecko | $0.1 | $0 | 3,072 | nan |\n| textembedding-gecko-multilingual | $0.1 | $0 | 3,072 | nan |\n| textembedding-gecko-multilingual@001 | $0.1 | $0 | 3,072 | nan |\n| textembedding-gecko@001 | $0.1 | $0 | 3,072 | nan |\n| textembedding-gecko@003 | $0.1 | $0 | 3,072 | nan |\n| text-embedding-preview-0409 | $0.01 | $0 | 3,072 | nan |\n| text-multilingual-embedding-preview-0409 | $0.01 | $0 | 3,072 | nan |\n| palm/chat-bison | $0.12 | $0.12 | 8,192 | 4096 |\n| palm/chat-bison-001 | $0.12 | $0.12 | 8,192 | 4096 |\n| palm/text-bison | $0.12 | $0.12 | 8,192 | 1024 |\n| palm/text-bison-001 | $0.12 | $0.12 | 8,192 | 1024 |\n| palm/text-bison-safety-off | $0.12 | $0.12 | 8,192 | 1024 |\n| palm/text-bison-safety-recitation-off | $0.12 | $0.12 | 8,192 | 1024 |\n| gemini/gemini-1.5-flash-002 | $0.08 | $0.3 | 1,048,576 | 8192 |\n| gemini/gemini-1.5-flash-001 | $0.08 | $0.3 | 1,048,576 | 8192 |\n| gemini/gemini-1.5-flash | $0.08 | $0.3 | 1,048,576 | 8192 |\n| gemini/gemini-1.5-flash-latest | $0.08 | $0.3 | 1,048,576 | 8192 |\n| gemini/gemini-1.5-flash-8b-exp-0924 | $0 | $0 | 1,048,576 | 8192 |\n| gemini/gemini-1.5-flash-exp-0827 | $0 | $0 | 1,048,576 | 8192 |\n| gemini/gemini-1.5-flash-8b-exp-0827 | $0 | $0 | 1,000,000 | 8192 |\n| gemini/gemini-pro | $0.35 | $1.05 | 32,760 | 8192 |\n| gemini/gemini-1.5-pro | $3.5 | $10.5 | 2,097,152 | 8192 |\n| gemini/gemini-1.5-pro-002 | $3.5 | $10.5 | 2,097,152 | 8192 |\n| gemini/gemini-1.5-pro-001 | $3.5 | $10.5 | 2,097,152 | 8192 |\n| gemini/gemini-1.5-pro-exp-0801 | $3.5 | $10.5 | 2,097,152 | 8192 |\n| gemini/gemini-1.5-pro-exp-0827 | $0 | $0 | 2,097,152 | 8192 |\n| gemini/gemini-1.5-pro-latest | $3.5 | $1.05 | 1,048,576 | 8192 |\n| gemini/gemini-pro-vision | $0.35 | $1.05 | 30,720 | 2048 |\n| gemini/gemini-gemma-2-27b-it | $0.35 | $1.05 | nan | 8192 |\n| gemini/gemini-gemma-2-9b-it | $0.35 | $1.05 | nan | 8192 |\n| command-r | $0.15 | $0.6 | 128,000 | 4096 |\n| command-r-08-2024 | $0.15 | $0.6 | 128,000 | 4096 |\n| command-light | $0.3 | $0.6 | 4,096 | 4096 |\n| command-r-plus | $2.5 | $10 | 128,000 | 4096 |\n| command-r-plus-08-2024 | $2.5 | $10 | 128,000 | 4096 |\n| command-nightly | $1 | $2 | 4,096 | 4096 |\n| command | $1 | $2 | 4,096 | 4096 |\n| rerank-english-v3.0 | $0 | $0 | 4,096 | 4096 |\n| rerank-multilingual-v3.0 | $0 | $0 | 4,096 | 4096 |\n| rerank-english-v2.0 | $0 | $0 | 4,096 | 4096 |\n| rerank-multilingual-v2.0 | $0 | $0 | 4,096 | 4096 |\n| embed-english-v3.0 | $0.1 | $0 | 1,024 | nan |\n| embed-english-light-v3.0 | $0.1 | $0 | 1,024 | nan |\n| embed-multilingual-v3.0 | $0.1 | $0 | 1,024 | nan |\n| embed-english-v2.0 | $0.1 | $0 | 4,096 | nan |\n| embed-english-light-v2.0 | $0.1 | $0 | 1,024 | nan |\n| embed-multilingual-v2.0 | $0.1 | $0 | 768 | nan |\n| replicate/meta/llama-2-13b | $0.1 | $0.5 | 4,096 | 4096 |\n| replicate/meta/llama-2-13b-chat | $0.1 | $0.5 | 4,096 | 4096 |\n| replicate/meta/llama-2-70b | $0.65 | $2.75 | 4,096 | 4096 |\n| replicate/meta/llama-2-70b-chat | $0.65 | $2.75 | 4,096 | 4096 |\n| replicate/meta/llama-2-7b | $0.05 | $0.25 | 4,096 | 4096 |\n| replicate/meta/llama-2-7b-chat | $0.05 | $0.25 | 4,096 | 4096 |\n| replicate/meta/llama-3-70b | $0.65 | $2.75 | 8,192 | 8192 |\n| replicate/meta/llama-3-70b-instruct | $0.65 | $2.75 | 8,192 | 8192 |\n| replicate/meta/llama-3-8b | $0.05 | $0.25 | 8,086 | 8086 |\n| replicate/meta/llama-3-8b-instruct | $0.05 | $0.25 | 8,086 | 8086 |\n| replicate/mistralai/mistral-7b-v0.1 | $0.05 | $0.25 | 4,096 | 4096 |\n| replicate/mistralai/mistral-7b-instruct-v0.2 | $0.05 | $0.25 | 4,096 | 4096 |\n| replicate/mistralai/mixtral-8x7b-instruct-v0.1 | $0.3 | $1 | 4,096 | 4096 |\n| openrouter/deepseek/deepseek-coder | $0.14 | $0.28 | 66,000 | 4096 |\n| openrouter/microsoft/wizardlm-2-8x22b:nitro | $1 | $1 | nan | nan |\n| openrouter/google/gemini-pro-1.5 | $2.5 | $7.5 | 1,000,000 | 8192 |\n| openrouter/mistralai/mixtral-8x22b-instruct | $0.65 | $0.65 | nan | nan |\n| openrouter/cohere/command-r-plus | $3 | $15 | nan | nan |\n| openrouter/databricks/dbrx-instruct | $0.6 | $0.6 | nan | nan |\n| openrouter/anthropic/claude-3-haiku | $0.25 | $1.25 | nan | nan |\n| openrouter/anthropic/claude-3-haiku-20240307 | $0.25 | $1.25 | 200,000 | 4096 |\n| anthropic/claude-3-5-sonnet-20241022 | $3 | $15 | 200,000 | 8192 |\n| anthropic/claude-3-5-sonnet-latest | $3 | $15 | 200,000 | 8192 |\n| openrouter/anthropic/claude-3.5-sonnet | $3 | $15 | 200,000 | 8192 |\n| openrouter/anthropic/claude-3.5-sonnet:beta | $3 | $15 | 200,000 | 8192 |\n| openrouter/anthropic/claude-3-sonnet | $3 | $15 | nan | nan |\n| openrouter/mistralai/mistral-large | $8 | $24 | nan | nan |\n| openrouter/cognitivecomputations/dolphin-mixtral-8x7b | $0.5 | $0.5 | nan | nan |\n| openrouter/google/gemini-pro-vision | $0.12 | $0.38 | nan | nan |\n| openrouter/fireworks/firellava-13b | $0.2 | $0.2 | nan | nan |\n| openrouter/meta-llama/llama-3-8b-instruct:free | $0 | $0 | nan | nan |\n| openrouter/meta-llama/llama-3-8b-instruct:extended | $0.22 | $2.25 | nan | nan |\n| openrouter/meta-llama/llama-3-70b-instruct:nitro | $0.9 | $0.9 | nan | nan |\n| openrouter/meta-llama/llama-3-70b-instruct | $0.59 | $0.79 | nan | nan |\n| openrouter/openai/o1-mini | $3 | $12 | 128,000 | 65536 |\n| openrouter/openai/o1-mini-2024-09-12 | $3 | $12 | 128,000 | 65536 |\n| openrouter/openai/o1-preview | $15 | $60 | 128,000 | 32768 |\n| openrouter/openai/o1-preview-2024-09-12 | $15 | $60 | 128,000 | 32768 |\n| openrouter/openai/gpt-4o | $2.5 | $10 | 128,000 | 4096 |\n| openrouter/openai/gpt-4o-2024-05-13 | $5 | $15 | 128,000 | 4096 |\n| openrouter/openai/gpt-4-vision-preview | $10 | $30 | nan | nan |\n| openrouter/openai/gpt-3.5-turbo | $1.5 | $2 | nan | nan |\n| openrouter/openai/gpt-3.5-turbo-16k | $3 | $4 | nan | nan |\n| openrouter/openai/gpt-4 | $30 | $60 | nan | nan |\n| openrouter/anthropic/claude-instant-v1 | $1.63 | $5.51 | nan | 8191 |\n| openrouter/anthropic/claude-2 | $11.02 | $32.68 | nan | 8191 |\n| openrouter/anthropic/claude-3-opus | $15 | $75 | 200,000 | 4096 |\n| openrouter/google/palm-2-chat-bison | $0.5 | $0.5 | nan | nan |\n| openrouter/google/palm-2-codechat-bison | $0.5 | $0.5 | nan | nan |\n| openrouter/meta-llama/llama-2-13b-chat | $0.2 | $0.2 | nan | nan |\n| openrouter/meta-llama/llama-2-70b-chat | $1.5 | $1.5 | nan | nan |\n| openrouter/meta-llama/codellama-34b-instruct | $0.5 | $0.5 | nan | nan |\n| openrouter/nousresearch/nous-hermes-llama2-13b | $0.2 | $0.2 | nan | nan |\n| openrouter/mancer/weaver | $5.62 | $5.62 | nan | nan |\n| openrouter/gryphe/mythomax-l2-13b | $1.88 | $1.88 | nan | nan |\n| openrouter/jondurbin/airoboros-l2-70b-2.1 | $13.88 | $13.88 | nan | nan |\n| openrouter/undi95/remm-slerp-l2-13b | $1.88 | $1.88 | nan | nan |\n| openrouter/pygmalionai/mythalion-13b | $1.88 | $1.88 | nan | nan |\n| openrouter/mistralai/mistral-7b-instruct | $0.13 | $0.13 | nan | nan |\n| openrouter/mistralai/mistral-7b-instruct:free | $0 | $0 | nan | nan |\n| j2-ultra | $15 | $15 | 8,192 | 8192 |\n| jamba-1.5-mini@001 | $0.2 | $0.4 | 256,000 | 256000 |\n| jamba-1.5-large@001 | $2 | $8 | 256,000 | 256000 |\n| jamba-1.5 | $0.2 | $0.4 | 256,000 | 256000 |\n| jamba-1.5-mini | $0.2 | $0.4 | 256,000 | 256000 |\n| jamba-1.5-large | $2 | $8 | 256,000 | 256000 |\n| j2-mid | $10 | $10 | 8,192 | 8192 |\n| j2-light | $3 | $3 | 8,192 | 8192 |\n| dolphin | $0.5 | $0.5 | 16,384 | 16384 |\n| chatdolphin | $0.5 | $0.5 | 16,384 | 16384 |\n| luminous-base | $30 | $33 | nan | nan |\n| luminous-base-control | $37.5 | $41.25 | nan | nan |\n| luminous-extended | $45 | $49.5 | nan | nan |\n| luminous-extended-control | $56.25 | $61.88 | nan | nan |\n| luminous-supreme | $175 | $192.5 | nan | nan |\n| luminous-supreme-control | $218.75 | $240.62 | nan | nan |\n| ai21.j2-mid-v1 | $12.5 | $12.5 | 8,191 | 8191 |\n| ai21.j2-ultra-v1 | $18.8 | $18.8 | 8,191 | 8191 |\n| ai21.jamba-instruct-v1:0 | $0.5 | $0.7 | 70,000 | 4096 |\n| amazon.titan-text-lite-v1 | $0.3 | $0.4 | 42,000 | 4000 |\n| amazon.titan-text-express-v1 | $1.3 | $1.7 | 42,000 | 8000 |\n| amazon.titan-text-premier-v1:0 | $0.5 | $1.5 | 42,000 | 32000 |\n| amazon.titan-embed-text-v1 | $0.1 | $0 | 8,192 | nan |\n| amazon.titan-embed-text-v2:0 | $0.2 | $0 | 8,192 | nan |\n| mistral.mistral-7b-instruct-v0:2 | $0.15 | $0.2 | 32,000 | 8191 |\n| mistral.mixtral-8x7b-instruct-v0:1 | $0.45 | $0.7 | 32,000 | 8191 |\n| mistral.mistral-large-2402-v1:0 | $8 | $24 | 32,000 | 8191 |\n| mistral.mistral-large-2407-v1:0 | $3 | $9 | 128,000 | 8191 |\n| mistral.mistral-small-2402-v1:0 | $1 | $3 | 32,000 | 8191 |\n| bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1 | $0.45 | $0.7 | 32,000 | 8191 |\n| bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1 | $0.45 | $0.7 | 32,000 | 8191 |\n| bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1 | $0.59 | $0.91 | 32,000 | 8191 |\n| bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2 | $0.15 | $0.2 | 32,000 | 8191 |\n| bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2 | $0.15 | $0.2 | 32,000 | 8191 |\n| bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2 | $0.2 | $0.26 | 32,000 | 8191 |\n| bedrock/us-east-1/mistral.mistral-large-2402-v1:0 | $8 | $24 | 32,000 | 8191 |\n| bedrock/us-west-2/mistral.mistral-large-2402-v1:0 | $8 | $24 | 32,000 | 8191 |\n| bedrock/eu-west-3/mistral.mistral-large-2402-v1:0 | $10.4 | $31.2 | 32,000 | 8191 |\n| anthropic.claude-3-sonnet-20240229-v1:0 | $3 | $15 | 200,000 | 4096 |\n| anthropic.claude-3-5-sonnet-20240620-v1:0 | $3 | $15 | 200,000 | 4096 |\n| anthropic.claude-3-5-sonnet-20241022-v2:0 | $3 | $15 | 200,000 | 8192 |\n| anthropic.claude-3-5-sonnet-latest-v2:0 | $3 | $15 | 200,000 | 4096 |\n| anthropic.claude-3-haiku-20240307-v1:0 | $0.25 | $1.25 | 200,000 | 4096 |\n| anthropic.claude-3-opus-20240229-v1:0 | $15 | $75 | 200,000 | 4096 |\n| us.anthropic.claude-3-sonnet-20240229-v1:0 | $3 | $15 | 200,000 | 4096 |\n| us.anthropic.claude-3-5-sonnet-20240620-v1:0 | $3 | $15 | 200,000 | 4096 |\n| us.anthropic.claude-3-5-sonnet-20241022-v2:0 | $3 | $15 | 200,000 | 8192 |\n| us.anthropic.claude-3-haiku-20240307-v1:0 | $0.25 | $1.25 | 200,000 | 4096 |\n| us.anthropic.claude-3-opus-20240229-v1:0 | $15 | $75 | 200,000 | 4096 |\n| eu.anthropic.claude-3-sonnet-20240229-v1:0 | $3 | $15 | 200,000 | 4096 |\n| eu.anthropic.claude-3-5-sonnet-20240620-v1:0 | $3 | $15 | 200,000 | 4096 |\n| eu.anthropic.claude-3-5-sonnet-20241022-v2:0 | $3 | $15 | 200,000 | 8192 |\n| eu.anthropic.claude-3-haiku-20240307-v1:0 | $0.25 | $1.25 | 200,000 | 4096 |\n| eu.anthropic.claude-3-opus-20240229-v1:0 | $15 | $75 | 200,000 | 4096 |\n| anthropic.claude-v1 | $8 | $24 | 100,000 | 8191 |\n| bedrock/us-east-1/anthropic.claude-v1 | $8 | $24 | 100,000 | 8191 |\n| bedrock/us-west-2/anthropic.claude-v1 | $8 | $24 | 100,000 | 8191 |\n| bedrock/ap-northeast-1/anthropic.claude-v1 | $8 | $24 | 100,000 | 8191 |\n| bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 |\n| bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 |\n| bedrock/eu-central-1/anthropic.claude-v1 | $8 | $24 | 100,000 | 8191 |\n| bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 |\n| bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 |\n| bedrock/us-east-1/1-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 |\n| bedrock/us-east-1/6-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 |\n| bedrock/us-west-2/1-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 |\n| bedrock/us-west-2/6-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 |\n| anthropic.claude-v2 | $8 | $24 | 100,000 | 8191 |\n| bedrock/us-east-1/anthropic.claude-v2 | $8 | $24 | 100,000 | 8191 |\n| bedrock/us-west-2/anthropic.claude-v2 | $8 | $24 | 100,000 | 8191 |\n| bedrock/ap-northeast-1/anthropic.claude-v2 | $8 | $24 | 100,000 | 8191 |\n| bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 |\n| bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 |\n| bedrock/eu-central-1/anthropic.claude-v2 | $8 | $24 | 100,000 | 8191 |\n| bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 |\n| bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 |\n| bedrock/us-east-1/1-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 |\n| bedrock/us-east-1/6-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 |\n| bedrock/us-west-2/1-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 |\n| bedrock/us-west-2/6-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 |\n| anthropic.claude-v2:1 | $8 | $24 | 100,000 | 8191 |\n| bedrock/us-east-1/anthropic.claude-v2:1 | $8 | $24 | 100,000 | 8191 |\n| bedrock/us-west-2/anthropic.claude-v2:1 | $8 | $24 | 100,000 | 8191 |\n| bedrock/ap-northeast-1/anthropic.claude-v2:1 | $8 | $24 | 100,000 | 8191 |\n| bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 |\n| bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 |\n| bedrock/eu-central-1/anthropic.claude-v2:1 | $8 | $24 | 100,000 | 8191 |\n| bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 |\n| bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 |\n| bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 |\n| bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 |\n| bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 |\n| bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 |\n| anthropic.claude-instant-v1 | $0.8 | $2.4 | 100,000 | 8191 |\n| bedrock/us-east-1/anthropic.claude-instant-v1 | $0.8 | $2.4 | 100,000 | 8191 |\n| bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 |\n| bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 |\n| bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 |\n| bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 |\n| bedrock/us-west-2/anthropic.claude-instant-v1 | $0.8 | $2.4 | 100,000 | 8191 |\n| bedrock/ap-northeast-1/anthropic.claude-instant-v1 | $2.23 | $7.55 | 100,000 | 8191 |\n| bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 |\n| bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 |\n| bedrock/eu-central-1/anthropic.claude-instant-v1 | $2.48 | $8.38 | 100,000 | 8191 |\n| bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 |\n| bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 |\n| cohere.command-text-v14 | $1.5 | $2 | 4,096 | 4096 |\n| bedrock/*/1-month-commitment/cohere.command-text-v14 | -- | -- | 4,096 | 4096 |\n| bedrock/*/6-month-commitment/cohere.command-text-v14 | -- | -- | 4,096 | 4096 |\n| cohere.command-light-text-v14 | $0.3 | $0.6 | 4,096 | 4096 |\n| bedrock/*/1-month-commitment/cohere.command-light-text-v14 | -- | -- | 4,096 | 4096 |\n| bedrock/*/6-month-commitment/cohere.command-light-text-v14 | -- | -- | 4,096 | 4096 |\n| cohere.command-r-plus-v1:0 | $3 | $15 | 128,000 | 4096 |\n| cohere.command-r-v1:0 | $0.5 | $1.5 | 128,000 | 4096 |\n| cohere.embed-english-v3 | $0.1 | $0 | 512 | nan |\n| cohere.embed-multilingual-v3 | $0.1 | $0 | 512 | nan |\n| meta.llama2-13b-chat-v1 | $0.75 | $1 | 4,096 | 4096 |\n| meta.llama2-70b-chat-v1 | $1.95 | $2.56 | 4,096 | 4096 |\n| meta.llama3-8b-instruct-v1:0 | $0.3 | $0.6 | 8,192 | 8192 |\n| bedrock/us-east-1/meta.llama3-8b-instruct-v1:0 | $0.3 | $0.6 | 8,192 | 8192 |\n| bedrock/us-west-1/meta.llama3-8b-instruct-v1:0 | $0.3 | $0.6 | 8,192 | 8192 |\n| bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0 | $0.36 | $0.72 | 8,192 | 8192 |\n| bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0 | $0.35 | $0.69 | 8,192 | 8192 |\n| bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0 | $0.32 | $0.65 | 8,192 | 8192 |\n| bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0 | $0.39 | $0.78 | 8,192 | 8192 |\n| bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0 | $0.5 | $1.01 | 8,192 | 8192 |\n| meta.llama3-70b-instruct-v1:0 | $2.65 | $3.5 | 8,192 | 8192 |\n| bedrock/us-east-1/meta.llama3-70b-instruct-v1:0 | $2.65 | $3.5 | 8,192 | 8192 |\n| bedrock/us-west-1/meta.llama3-70b-instruct-v1:0 | $2.65 | $3.5 | 8,192 | 8192 |\n| bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0 | $3.18 | $4.2 | 8,192 | 8192 |\n| bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0 | $3.05 | $4.03 | 8,192 | 8192 |\n| bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0 | $2.86 | $3.78 | 8,192 | 8192 |\n| bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0 | $3.45 | $4.55 | 8,192 | 8192 |\n| bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0 | $4.45 | $5.88 | 8,192 | 8192 |\n| meta.llama3-1-8b-instruct-v1:0 | $0.22 | $0.22 | 128,000 | 2048 |\n| meta.llama3-1-70b-instruct-v1:0 | $0.99 | $0.99 | 128,000 | 2048 |\n| meta.llama3-1-405b-instruct-v1:0 | $5.32 | $16 | 128,000 | 4096 |\n| meta.llama3-2-1b-instruct-v1:0 | $0.1 | $0.1 | 128,000 | 4096 |\n| us.meta.llama3-2-1b-instruct-v1:0 | $0.1 | $0.1 | 128,000 | 4096 |\n| eu.meta.llama3-2-1b-instruct-v1:0 | $0.13 | $0.13 | 128,000 | 4096 |\n| meta.llama3-2-3b-instruct-v1:0 | $0.15 | $0.15 | 128,000 | 4096 |\n| us.meta.llama3-2-3b-instruct-v1:0 | $0.15 | $0.15 | 128,000 | 4096 |\n| eu.meta.llama3-2-3b-instruct-v1:0 | $0.19 | $0.19 | 128,000 | 4096 |\n| meta.llama3-2-11b-instruct-v1:0 | $0.35 | $0.35 | 128,000 | 4096 |\n| us.meta.llama3-2-11b-instruct-v1:0 | $0.35 | $0.35 | 128,000 | 4096 |\n| meta.llama3-2-90b-instruct-v1:0 | $2 | $2 | 128,000 | 4096 |\n| us.meta.llama3-2-90b-instruct-v1:0 | $2 | $2 | 128,000 | 4096 |\n| 512-x-512/50-steps/stability.stable-diffusion-xl-v0 | -- | -- | 77 | nan |\n| 512-x-512/max-steps/stability.stable-diffusion-xl-v0 | -- | -- | 77 | nan |\n| max-x-max/50-steps/stability.stable-diffusion-xl-v0 | -- | -- | 77 | nan |\n| max-x-max/max-steps/stability.stable-diffusion-xl-v0 | -- | -- | 77 | nan |\n| 1024-x-1024/50-steps/stability.stable-diffusion-xl-v1 | -- | -- | 77 | nan |\n| 1024-x-1024/max-steps/stability.stable-diffusion-xl-v1 | -- | -- | 77 | nan |\n| sagemaker/meta-textgeneration-llama-2-7b | $0 | $0 | 4,096 | 4096 |\n| sagemaker/meta-textgeneration-llama-2-7b-f | $0 | $0 | 4,096 | 4096 |\n| sagemaker/meta-textgeneration-llama-2-13b | $0 | $0 | 4,096 | 4096 |\n| sagemaker/meta-textgeneration-llama-2-13b-f | $0 | $0 | 4,096 | 4096 |\n| sagemaker/meta-textgeneration-llama-2-70b | $0 | $0 | 4,096 | 4096 |\n| sagemaker/meta-textgeneration-llama-2-70b-b-f | $0 | $0 | 4,096 | 4096 |\n| together-ai-up-to-4b | $0.1 | $0.1 | nan | nan |\n| together-ai-4.1b-8b | $0.2 | $0.2 | nan | nan |\n| together-ai-8.1b-21b | $0.3 | $0.3 | nan | nan |\n| together-ai-21.1b-41b | $0.8 | $0.8 | nan | nan |\n| together-ai-41.1b-80b | $0.9 | $0.9 | nan | nan |\n| together-ai-81.1b-110b | $1.8 | $1.8 | nan | nan |\n| together-ai-embedding-up-to-150m | $0.01 | $0 | nan | nan |\n| together-ai-embedding-151m-to-350m | $0.02 | $0 | nan | nan |\n| together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1 | $0.6 | $0.6 | nan | nan |\n| together_ai/mistralai/Mistral-7B-Instruct-v0.1 | -- | -- | nan | nan |\n| together_ai/togethercomputer/CodeLlama-34b-Instruct | -- | -- | nan | nan |\n| ollama/codegemma | $0 | $0 | 8,192 | 8192 |\n| ollama/codegeex4 | $0 | $0 | 32,768 | 8192 |\n| ollama/deepseek-coder-v2-instruct | $0 | $0 | 32,768 | 8192 |\n| ollama/deepseek-coder-v2-base | $0 | $0 | 8,192 | 8192 |\n| ollama/deepseek-coder-v2-lite-instruct | $0 | $0 | 32,768 | 8192 |\n| ollama/deepseek-coder-v2-lite-base | $0 | $0 | 8,192 | 8192 |\n| ollama/internlm2_5-20b-chat | $0 | $0 | 32,768 | 8192 |\n| ollama/llama2 | $0 | $0 | 4,096 | 4096 |\n| ollama/llama2:7b | $0 | $0 | 4,096 | 4096 |\n| ollama/llama2:13b | $0 | $0 | 4,096 | 4096 |\n| ollama/llama2:70b | $0 | $0 | 4,096 | 4096 |\n| ollama/llama2-uncensored | $0 | $0 | 4,096 | 4096 |\n| ollama/llama3 | $0 | $0 | 8,192 | 8192 |\n| ollama/llama3:8b | $0 | $0 | 8,192 | 8192 |\n| ollama/llama3:70b | $0 | $0 | 8,192 | 8192 |\n| ollama/llama3.1 | $0 | $0 | 8,192 | 8192 |\n| ollama/mistral-large-instruct-2407 | $0 | $0 | 65,536 | 8192 |\n| ollama/mistral | $0 | $0 | 8,192 | 8192 |\n| ollama/mistral-7B-Instruct-v0.1 | $0 | $0 | 8,192 | 8192 |\n| ollama/mistral-7B-Instruct-v0.2 | $0 | $0 | 32,768 | 32768 |\n| ollama/mixtral-8x7B-Instruct-v0.1 | $0 | $0 | 32,768 | 32768 |\n| ollama/mixtral-8x22B-Instruct-v0.1 | $0 | $0 | 65,536 | 65536 |\n| ollama/codellama | $0 | $0 | 4,096 | 4096 |\n| ollama/orca-mini | $0 | $0 | 4,096 | 4096 |\n| ollama/vicuna | $0 | $0 | 2,048 | 2048 |\n| deepinfra/lizpreciatior/lzlv_70b_fp16_hf | $0.35 | $0.4 | 4,096 | 4096 |\n| deepinfra/Gryphe/MythoMax-L2-13b | $0.07 | $0.07 | 4,096 | 4096 |\n| deepinfra/mistralai/Mistral-7B-Instruct-v0.1 | $0.06 | $0.06 | 32,768 | 32768 |\n| deepinfra/meta-llama/Llama-2-70b-chat-hf | $0.64 | $0.8 | 4,096 | 4096 |\n| deepinfra/cognitivecomputations/dolphin-2.6-mixtral-8x7b | $0.24 | $0.24 | 32,768 | 32768 |\n| deepinfra/codellama/CodeLlama-34b-Instruct-hf | $0.6 | $0.6 | 4,096 | 4096 |\n| deepinfra/deepinfra/mixtral | $0.27 | $0.27 | 32,000 | 4096 |\n| deepinfra/Phind/Phind-CodeLlama-34B-v2 | $0.6 | $0.6 | 4,096 | 4096 |\n| deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1 | $0.08 | $0.24 | 32,768 | 32768 |\n| deepinfra/deepinfra/airoboros-70b | $0.7 | $0.9 | 4,096 | 4096 |\n| deepinfra/01-ai/Yi-34B-Chat | $0.6 | $0.6 | 4,096 | 4096 |\n| deepinfra/01-ai/Yi-6B-200K | $0.13 | $0.13 | 200,000 | 4096 |\n| deepinfra/jondurbin/airoboros-l2-70b-gpt4-1.4.1 | $0.7 | $0.9 | 4,096 | 4096 |\n| deepinfra/meta-llama/Llama-2-13b-chat-hf | $0.13 | $0.13 | 4,096 | 4096 |\n| deepinfra/amazon/MistralLite | $0.2 | $0.2 | 32,768 | 8191 |\n| deepinfra/meta-llama/Llama-2-7b-chat-hf | $0.13 | $0.13 | 4,096 | 4096 |\n| deepinfra/meta-llama/Meta-Llama-3-8B-Instruct | $0.03 | $0.06 | 8,192 | 8192 |\n| deepinfra/meta-llama/Meta-Llama-3-70B-Instruct | $0.3 | $0.4 | 8,192 | 8192 |\n| deepinfra/01-ai/Yi-34B-200K | $0.6 | $0.6 | 200,000 | 4096 |\n| deepinfra/openchat/openchat_3.5 | $0.06 | $0.06 | 8,192 | 8192 |\n| perplexity/codellama-34b-instruct | $0.35 | $1.4 | 16,384 | 16384 |\n| perplexity/codellama-70b-instruct | $0.7 | $2.8 | 16,384 | 16384 |\n| perplexity/llama-3.1-70b-instruct | $1 | $1 | 131,072 | 131072 |\n| perplexity/llama-3.1-8b-instruct | $0.2 | $0.2 | 131,072 | 131072 |\n| perplexity/llama-3.1-sonar-huge-128k-online | $5 | $5 | 127,072 | 127072 |\n| perplexity/llama-3.1-sonar-large-128k-online | $1 | $1 | 127,072 | 127072 |\n| perplexity/llama-3.1-sonar-large-128k-chat | $1 | $1 | 131,072 | 131072 |\n| perplexity/llama-3.1-sonar-small-128k-chat | $0.2 | $0.2 | 131,072 | 131072 |\n| perplexity/llama-3.1-sonar-small-128k-online | $0.2 | $0.2 | 127,072 | 127072 |\n| perplexity/pplx-7b-chat | $0.07 | $0.28 | 8,192 | 8192 |\n| perplexity/pplx-70b-chat | $0.7 | $2.8 | 4,096 | 4096 |\n| perplexity/pplx-7b-online | $0 | $0.28 | 4,096 | 4096 |\n| perplexity/pplx-70b-online | $0 | $2.8 | 4,096 | 4096 |\n| perplexity/llama-2-70b-chat | $0.7 | $2.8 | 4,096 | 4096 |\n| perplexity/mistral-7b-instruct | $0.07 | $0.28 | 4,096 | 4096 |\n| perplexity/mixtral-8x7b-instruct | $0.07 | $0.28 | 4,096 | 4096 |\n| perplexity/sonar-small-chat | $0.07 | $0.28 | 16,384 | 16384 |\n| perplexity/sonar-small-online | $0 | $0.28 | 12,000 | 12000 |\n| perplexity/sonar-medium-chat | $0.6 | $1.8 | 16,384 | 16384 |\n| perplexity/sonar-medium-online | $0 | $1.8 | 12,000 | 12000 |\n| fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct | $0.1 | $0.1 | 16,384 | 16384 |\n| fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct | $0.1 | $0.1 | 16,384 | 16384 |\n| fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct | $0.2 | $0.2 | 16,384 | 16384 |\n| accounts/fireworks/models/llama-v3p2-90b-vision-instruct | $0.9 | $0.9 | 16,384 | 16384 |\n| fireworks_ai/accounts/fireworks/models/firefunction-v2 | $0.9 | $0.9 | 8,192 | 8192 |\n| fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf | $1.2 | $1.2 | 65,536 | 65536 |\n| fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct | $0.9 | $0.9 | 32,768 | 32768 |\n| fireworks_ai/accounts/fireworks/models/yi-large | $3 | $3 | 32,768 | 32768 |\n| fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct | $1.2 | $1.2 | 65,536 | 65536 |\n| fireworks_ai/nomic-ai/nomic-embed-text-v1.5 | $0.01 | $0 | 8,192 | nan |\n| fireworks_ai/nomic-ai/nomic-embed-text-v1 | $0.01 | $0 | 8,192 | nan |\n| fireworks_ai/WhereIsAI/UAE-Large-V1 | $0.02 | $0 | 512 | nan |\n| fireworks_ai/thenlper/gte-large | $0.02 | $0 | 512 | nan |\n| fireworks_ai/thenlper/gte-base | $0.01 | $0 | 512 | nan |\n| fireworks-ai-up-to-16b | $0.2 | $0.2 | nan | nan |\n| fireworks-ai-16.1b-to-80b | $0.9 | $0.9 | nan | nan |\n| fireworks-ai-moe-up-to-56b | $0.5 | $0.5 | nan | nan |\n| fireworks-ai-56b-to-176b | $1.2 | $1.2 | nan | nan |\n| fireworks-ai-default | $0 | $0 | nan | nan |\n| fireworks-ai-embedding-up-to-150m | $0.01 | $0 | nan | nan |\n| fireworks-ai-embedding-150m-to-350m | $0.02 | $0 | nan | nan |\n| anyscale/mistralai/Mistral-7B-Instruct-v0.1 | $0.15 | $0.15 | 16,384 | 16384 |\n| anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1 | $0.15 | $0.15 | 16,384 | 16384 |\n| anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1 | $0.9 | $0.9 | 65,536 | 65536 |\n| anyscale/HuggingFaceH4/zephyr-7b-beta | $0.15 | $0.15 | 16,384 | 16384 |\n| anyscale/google/gemma-7b-it | $0.15 | $0.15 | 8,192 | 8192 |\n| anyscale/meta-llama/Llama-2-7b-chat-hf | $0.15 | $0.15 | 4,096 | 4096 |\n| anyscale/meta-llama/Llama-2-13b-chat-hf | $0.25 | $0.25 | 4,096 | 4096 |\n| anyscale/meta-llama/Llama-2-70b-chat-hf | $1 | $1 | 4,096 | 4096 |\n| anyscale/codellama/CodeLlama-34b-Instruct-hf | $1 | $1 | 4,096 | 4096 |\n| anyscale/codellama/CodeLlama-70b-Instruct-hf | $1 | $1 | 4,096 | 4096 |\n| anyscale/meta-llama/Meta-Llama-3-8B-Instruct | $0.15 | $0.15 | 8,192 | 8192 |\n| anyscale/meta-llama/Meta-Llama-3-70B-Instruct | $1 | $1 | 8,192 | 8192 |\n| cloudflare/@cf/meta/llama-2-7b-chat-fp16 | $1.92 | $1.92 | 3,072 | 3072 |\n| cloudflare/@cf/meta/llama-2-7b-chat-int8 | $1.92 | $1.92 | 2,048 | 2048 |\n| cloudflare/@cf/mistral/mistral-7b-instruct-v0.1 | $1.92 | $1.92 | 8,192 | 8192 |\n| cloudflare/@hf/thebloke/codellama-7b-instruct-awq | $1.92 | $1.92 | 4,096 | 4096 |\n| voyage/voyage-01 | $0.1 | $0 | 4,096 | nan |\n| voyage/voyage-lite-01 | $0.1 | $0 | 4,096 | nan |\n| voyage/voyage-large-2 | $0.12 | $0 | 16,000 | nan |\n| voyage/voyage-law-2 | $0.12 | $0 | 16,000 | nan |\n| voyage/voyage-code-2 | $0.12 | $0 | 16,000 | nan |\n| voyage/voyage-2 | $0.1 | $0 | 4,000 | nan |\n| voyage/voyage-lite-02-instruct | $0.1 | $0 | 4,000 | nan |\n| voyage/voyage-finance-2 | $0.12 | $0 | 32,000 | nan |\n| databricks/databricks-meta-llama-3-1-405b-instruct | $5 | $15 | 128,000 | 128000 |\n| databricks/databricks-meta-llama-3-1-70b-instruct | $1 | $3 | 128,000 | 128000 |\n| databricks/databricks-dbrx-instruct | $0.75 | $2.25 | 32,768 | 32768 |\n| databricks/databricks-meta-llama-3-70b-instruct | $1 | $3 | 128,000 | 128000 |\n| databricks/databricks-llama-2-70b-chat | $0.5 | $1.5 | 4,096 | 4096 |\n| databricks/databricks-mixtral-8x7b-instruct | $0.5 | $1 | 4,096 | 4096 |\n| databricks/databricks-mpt-30b-instruct | $1 | $1 | 8,192 | 8192 |\n| databricks/databricks-mpt-7b-instruct | $0.5 | $0 | 8,192 | 8192 |\n| databricks/databricks-bge-large-en | $0.1 | $0 | 512 | nan |\n| databricks/databricks-gte-large-en | $0.13 | $0 | 8,192 | nan |\n| azure/gpt-4o-mini-2024-07-18 | $0.16 | $0.66 | 128,000 | 16384 |\n| amazon.titan-embed-image-v1 | $0.8 | $0 | 128 | nan |\n| azure_ai/mistral-large-2407 | $2 | $6 | 128,000 | 4096 |\n| azure_ai/ministral-3b | $0.04 | $0.04 | 128,000 | 4096 |\n| azure_ai/Llama-3.2-11B-Vision-Instruct | $0.37 | $0.37 | 128,000 | 2048 |\n| azure_ai/Llama-3.2-90B-Vision-Instruct | $2.04 | $2.04 | 128,000 | 2048 |\n| azure_ai/Phi-3.5-mini-instruct | $0.13 | $0.52 | 128,000 | 4096 |\n| azure_ai/Phi-3.5-vision-instruct | $0.13 | $0.52 | 128,000 | 4096 |\n| azure_ai/Phi-3.5-MoE-instruct | $0.16 | $0.64 | 128,000 | 4096 |\n| azure_ai/Phi-3-mini-4k-instruct | $0.13 | $0.52 | 4,096 | 4096 |\n| azure_ai/Phi-3-mini-128k-instruct | $0.13 | $0.52 | 128,000 | 4096 |\n| azure_ai/Phi-3-small-8k-instruct | $0.15 | $0.6 | 8,192 | 4096 |\n| azure_ai/Phi-3-small-128k-instruct | $0.15 | $0.6 | 128,000 | 4096 |\n| azure_ai/Phi-3-medium-4k-instruct | $0.17 | $0.68 | 4,096 | 4096 |\n| azure_ai/Phi-3-medium-128k-instruct | $0.17 | $0.68 | 128,000 | 4096 |\n| xai/grok-beta | $5 | $15 | 131,072 | 131072 |\n| claude-3-5-haiku-20241022 | $0.8 | $4 | 200,000 | 8192 |\n| vertex_ai/claude-3-5-haiku@20241022 | $1 | $5 | 200,000 | 8192 |\n| openrouter/anthropic/claude-3-5-haiku | $1 | $5 | nan | nan |\n| openrouter/anthropic/claude-3-5-haiku-20241022 | $1 | $5 | 200,000 | 8192 |\n| anthropic.claude-3-5-haiku-20241022-v1:0 | $0.8 | $4 | 200,000 | 8192 |\n| us.anthropic.claude-3-5-haiku-20241022-v1:0 | $0.8 | $4 | 200,000 | 8192 |\n| eu.anthropic.claude-3-5-haiku-20241022-v1:0 | $0.25 | $1.25 | 200,000 | 8192 |\n| stability.sd3-large-v1:0 | -- | -- | 77 | nan |\n| gpt-4o-2024-11-20 | $2.5 | $10 | 128,000 | 16384 |\n| ft:gpt-4o-2024-11-20 | $3.75 | $15 | 128,000 | 16384 |\n| azure/gpt-4o-2024-11-20 | $2.75 | $11 | 128,000 | 16384 |\n| azure/global-standard/gpt-4o-2024-11-20 | $2.5 | $10 | 128,000 | 16384 |\n| groq/llama-3.2-1b-preview | $0.04 | $0.04 | 8,192 | 8192 |\n| groq/llama-3.2-3b-preview | $0.06 | $0.06 | 8,192 | 8192 |\n| groq/llama-3.2-11b-text-preview | $0.18 | $0.18 | 8,192 | 8192 |\n| groq/llama-3.2-11b-vision-preview | $0.18 | $0.18 | 8,192 | 8192 |\n| groq/llama-3.2-90b-text-preview | $0.9 | $0.9 | 8,192 | 8192 |\n| groq/llama-3.2-90b-vision-preview | $0.9 | $0.9 | 8,192 | 8192 |\n| vertex_ai/claude-3-sonnet | $3 | $15 | 200,000 | 4096 |\n| vertex_ai/claude-3-5-sonnet | $3 | $15 | 200,000 | 8192 |\n| vertex_ai/claude-3-5-sonnet-v2 | $3 | $15 | 200,000 | 8192 |\n| vertex_ai/claude-3-haiku | $0.25 | $1.25 | 200,000 | 4096 |\n| vertex_ai/claude-3-5-haiku | $1 | $5 | 200,000 | 8192 |\n| vertex_ai/claude-3-opus | $15 | $75 | 200,000 | 4096 |\n| gemini/gemini-exp-1114 | $0 | $0 | 1,048,576 | 8192 |\n| openrouter/qwen/qwen-2.5-coder-32b-instruct | $0.18 | $0.18 | 33,792 | 33792 |\n| us.meta.llama3-1-8b-instruct-v1:0 | $0.22 | $0.22 | 128,000 | 2048 |\n| us.meta.llama3-1-70b-instruct-v1:0 | $0.99 | $0.99 | 128,000 | 2048 |\n| us.meta.llama3-1-405b-instruct-v1:0 | $5.32 | $16 | 128,000 | 4096 |\n| stability.stable-image-ultra-v1:0 | -- | -- | 77 | nan |\n| fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct | $0.9 | $0.9 | 4,096 | 4096 |\n| omni-moderation-latest | $0 | $0 | 32,768 | 0 |\n| omni-moderation-latest-intents | $0 | $0 | 32,768 | 0 |\n| omni-moderation-2024-09-26 | $0 | $0 | 32,768 | 0 |\n| gpt-4o-audio-preview-2024-12-17 | $2.5 | $10 | 128,000 | 16384 |\n| gpt-4o-mini-audio-preview-2024-12-17 | $0.15 | $0.6 | 128,000 | 16384 |\n| o1 | $15 | $60 | 200,000 | 100000 |\n| o1-2024-12-17 | $15 | $60 | 200,000 | 100000 |\n| gpt-4o-realtime-preview-2024-10-01 | $5 | $20 | 128,000 | 4096 |\n| gpt-4o-realtime-preview | $5 | $20 | 128,000 | 4096 |\n| gpt-4o-realtime-preview-2024-12-17 | $5 | $20 | 128,000 | 4096 |\n| gpt-4o-mini-realtime-preview | $0.6 | $2.4 | 128,000 | 4096 |\n| gpt-4o-mini-realtime-preview-2024-12-17 | $0.6 | $2.4 | 128,000 | 4096 |\n| azure/o1 | $15 | $60 | 200,000 | 100000 |\n| azure_ai/Llama-3.3-70B-Instruct | $0.71 | $0.71 | 128,000 | 2048 |\n| mistral/mistral-large-2411 | $2 | $6 | 128,000 | 128000 |\n| mistral/pixtral-large-latest | $2 | $6 | 128,000 | 128000 |\n| mistral/pixtral-large-2411 | $2 | $6 | 128,000 | 128000 |\n| deepseek/deepseek-chat | $0.27 | $1.1 | 65,536 | 8192 |\n| deepseek/deepseek-coder | $0.14 | $0.28 | 128,000 | 4096 |\n| groq/llama-3.3-70b-versatile | $0.59 | $0.79 | 128,000 | 32768 |\n| groq/llama-3.3-70b-specdec | $0.59 | $0.99 | 8,192 | 8192 |\n| friendliai/meta-llama-3.1-8b-instruct | $0.1 | $0.1 | 8,192 | 8192 |\n| friendliai/meta-llama-3.1-70b-instruct | $0.6 | $0.6 | 8,192 | 8192 |\n| gemini-2.0-flash-exp | $0.15 | $0.6 | 1,048,576 | 8192 |\n| gemini/gemini-2.0-flash-exp | $0 | $0 | 1,048,576 | 8192 |\n| vertex_ai/mistral-large@2411-001 | $2 | $6 | 128,000 | 8191 |\n| vertex_ai/mistral-large-2411 | $2 | $6 | 128,000 | 8191 |\n| text-embedding-005 | $0.1 | $0 | 2,048 | nan |\n| gemini/gemini-1.5-flash-8b | $0 | $0 | 1,048,576 | 8192 |\n| gemini/gemini-exp-1206 | $0 | $0 | 2,097,152 | 8192 |\n| command-r7b-12-2024 | $0.15 | $0.04 | 128,000 | 4096 |\n| rerank-v3.5 | $0 | $0 | 4,096 | 4096 |\n| openrouter/deepseek/deepseek-chat | $0.14 | $0.28 | 65,536 | 8192 |\n| openrouter/openai/o1 | $15 | $60 | 200,000 | 100000 |\n| amazon.nova-micro-v1:0 | $0.04 | $0.14 | 128,000 | 10000 |\n| amazon.nova-lite-v1:0 | $0.06 | $0.24 | 300,000 | 10000 |\n| amazon.nova-pro-v1:0 | $0.8 | $3.2 | 300,000 | 10000 |\n| meta.llama3-3-70b-instruct-v1:0 | $0.72 | $0.72 | 128,000 | 4096 |\n| together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | $0.18 | $0.18 | nan | nan |\n| together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | $0.88 | $0.88 | nan | nan |\n| together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | $3.5 | $3.5 | nan | nan |\n| deepinfra/meta-llama/Meta-Llama-3.1-405B-Instruct | $0.8 | $0.8 | 32,768 | 32768 |\n| fireworks_ai/accounts/fireworks/models/deepseek-v3 | $0.9 | $0.9 | 128,000 | 8192 |\n| voyage/voyage-3-large | $0.18 | $0 | 32,000 | nan |\n| voyage/voyage-3 | $0.06 | $0 | 32,000 | nan |\n| voyage/voyage-3-lite | $0.02 | $0 | 32,000 | nan |\n| voyage/voyage-code-3 | $0.18 | $0 | 32,000 | nan |\n| voyage/voyage-multimodal-3 | $0.12 | $0 | 32,000 | nan |\n| voyage/rerank-2 | $0.05 | $0 | 16,000 | 16000 |\n| voyage/rerank-2-lite | $0.02 | $0 | 8,000 | 8000 |\n| databricks/meta-llama-3.3-70b-instruct | $1 | $3 | 128,000 | 128000 |\n| sambanova/Meta-Llama-3.1-8B-Instruct | $0.1 | $0.2 | 16,384 | 16384 |\n| sambanova/Meta-Llama-3.1-70B-Instruct | $0.6 | $1.2 | 128,000 | 128000 |\n| sambanova/Meta-Llama-3.1-405B-Instruct | $5 | $10 | 16,384 | 16384 |\n| sambanova/Meta-Llama-3.2-1B-Instruct | $0.04 | $0.08 | 16,384 | 16384 |\n| sambanova/Meta-Llama-3.2-3B-Instruct | $0.08 | $0.16 | 4,096 | 4096 |\n| sambanova/Meta-Llama-3.3-70B-Instruct | $0.6 | $1.2 | 131,072 | 131072 |\n| sambanova/Qwen2.5-Coder-32B-Instruct | $1.5 | $3 | 8,000 | 8000 |\n| sambanova/Qwen2.5-72B-Instruct | $2 | $4 | 8,000 | 8000 |\n| o3-mini | $1.1 | $4.4 | 200,000 | 100000 |\n| o3-mini-2025-01-31 | $1.1 | $4.4 | 200,000 | 100000 |\n| azure/o3-mini-2025-01-31 | $1.1 | $4.4 | 200,000 | 100000 |\n| azure/o3-mini | $1.1 | $4.4 | 200,000 | 100000 |\n| azure/o1-2024-12-17 | $15 | $60 | 200,000 | 100000 |\n| azure_ai/deepseek-r1 | $1.35 | $5.4 | 128,000 | 8192 |\n| deepseek/deepseek-reasoner | $0.55 | $2.19 | 65,536 | 8192 |\n| xai/grok-2-vision-1212 | $2 | $10 | 32,768 | 32768 |\n| xai/grok-2-vision-latest | $2 | $10 | 32,768 | 32768 |\n| xai/grok-2-vision | $2 | $10 | 32,768 | 32768 |\n| xai/grok-vision-beta | $5 | $15 | 8,192 | 8192 |\n| xai/grok-2-1212 | $2 | $10 | 131,072 | 131072 |\n| xai/grok-2 | $2 | $10 | 131,072 | 131072 |\n| xai/grok-2-latest | $2 | $10 | 131,072 | 131072 |\n| groq/deepseek-r1-distill-llama-70b | $0.75 | $0.99 | 128,000 | 128000 |\n| gemini/gemini-2.0-flash | $0.1 | $0.4 | 1,048,576 | 8192 |\n| gemini-2.0-flash-001 | $0.15 | $0.6 | 1,048,576 | 8192 |\n| gemini-2.0-flash-thinking-exp | $0 | $0 | 1,048,576 | 8192 |\n| gemini-2.0-flash-thinking-exp-01-21 | $0 | $0 | 1,048,576 | 65536 |\n| gemini/gemini-2.0-flash-001 | $0.1 | $0.4 | 1,048,576 | 8192 |\n| gemini/gemini-2.0-flash-lite-preview-02-05 | $0.08 | $0.3 | 1,048,576 | 8192 |\n| gemini/gemini-2.0-flash-thinking-exp | $0 | $0 | 1,048,576 | 65536 |\n| vertex_ai/codestral-2501 | $0.2 | $0.6 | 128,000 | 128000 |\n| openrouter/deepseek/deepseek-r1 | $0.55 | $2.19 | 65,336 | 8192 |\n| ai21.jamba-1-5-large-v1:0 | $2 | $8 | 256,000 | 256000 |\n| ai21.jamba-1-5-mini-v1:0 | $0.2 | $0.4 | 256,000 | 256000 |\n| us.amazon.nova-micro-v1:0 | $0.04 | $0.14 | 128,000 | 10000 |\n| us.amazon.nova-lite-v1:0 | $0.06 | $0.24 | 300,000 | 10000 |\n| us.amazon.nova-pro-v1:0 | $0.8 | $3.2 | 300,000 | 10000 |\n| stability.sd3-5-large-v1:0 | -- | -- | 77 | nan |\n| stability.stable-image-core-v1:0 | -- | -- | 77 | nan |\n| stability.stable-image-core-v1:1 | -- | -- | 77 | nan |\n| stability.stable-image-ultra-v1:1 | -- | -- | 77 | nan |\n| together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo | $0.88 | $0.88 | nan | nan |\n| together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free | $0 | $0 | nan | nan |\n| fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct | $0.1 | $0.1 | 16,384 | 16384 |\n| assemblyai/nano | -- | -- | nan | nan |\n| assemblyai/best | -- | -- | nan | nan |\n| azure/gpt-3.5-turbo-0125 | $0.5 | $1.5 | 16,384 | 4096 |\n| azure/gpt-3.5-turbo | $0.5 | $1.5 | 4,097 | 4096 |\n| gemini-2.0-pro-exp-02-05 | $1.25 | $10 | 2,097,152 | 8192 |\n| us.meta.llama3-3-70b-instruct-v1:0 | $0.72 | $0.72 | 128,000 | 4096 |\n| perplexity/sonar | $1 | $1 | 128,000 | nan |\n| perplexity/sonar-pro | $3 | $15 | 200,000 | 8000 |\n| openrouter/google/gemini-2.0-flash-001 | $0.1 | $0.4 | 1,048,576 | 8192 |\n| gpt-4.5-preview | $75 | $150 | 128,000 | 16384 |\n| gpt-4.5-preview-2025-02-27 | $75 | $150 | 128,000 | 16384 |\n| azure_ai/Phi-4 | $0.12 | $0.5 | 16,384 | 16384 |\n| cerebras/llama3.3-70b | $0.85 | $1.2 | 128,000 | 128000 |\n| claude-3-5-haiku-latest | $1 | $5 | 200,000 | 8192 |\n| claude-3-7-sonnet-latest | $3 | $15 | 200,000 | 128000 |\n| claude-3-7-sonnet-20250219 | $3 | $15 | 200,000 | 128000 |\n| vertex_ai/claude-3-7-sonnet@20250219 | $3 | $15 | 200,000 | 8192 |\n| openrouter/anthropic/claude-3.7-sonnet | $3 | $15 | 200,000 | 128000 |\n| openrouter/anthropic/claude-3.7-sonnet:beta | $3 | $15 | 200,000 | 128000 |\n| amazon.rerank-v1:0 | $0 | $0 | 32,000 | 32000 |\n| anthropic.claude-3-7-sonnet-20250219-v1:0 | $3 | $15 | 200,000 | 8192 |\n| us.anthropic.claude-3-7-sonnet-20250219-v1:0 | $3 | $15 | 200,000 | 8192 |\n| cohere.rerank-v3-5:0 | $0 | $0 | 32,000 | 32000 |\n| jina-reranker-v2-base-multilingual | $0.02 | $0.02 | 1,024 | 1024 |\n| bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0 | $3 | $15 | 200,000 | 4096 |\n| azure/gpt-4o-mini-realtime-preview-2024-12-17 | $0.6 | $2.4 | 128,000 | 4096 |\n| azure/eu/gpt-4o-mini-realtime-preview-2024-12-17 | $0.66 | $2.64 | 128,000 | 4096 |\n| azure/us/gpt-4o-mini-realtime-preview-2024-12-17 | $0.66 | $2.64 | 128,000 | 4096 |\n| azure/gpt-4o-realtime-preview-2024-10-01 | $5 | $20 | 128,000 | 4096 |\n| azure/us/gpt-4o-realtime-preview-2024-10-01 | $5.5 | $22 | 128,000 | 4096 |\n| azure/eu/gpt-4o-realtime-preview-2024-10-01 | $5.5 | $22 | 128,000 | 4096 |\n| azure/us/o3-mini-2025-01-31 | $1.21 | $4.84 | 200,000 | 100000 |\n| azure/eu/o3-mini-2025-01-31 | $1.21 | $4.84 | 200,000 | 100000 |\n| azure/us/o1-mini-2024-09-12 | $1.21 | $4.84 | 128,000 | 65536 |\n| azure/eu/o1-mini-2024-09-12 | $1.21 | $4.84 | 128,000 | 65536 |\n| azure/us/o1-2024-12-17 | $16.5 | $66 | 200,000 | 100000 |\n| azure/eu/o1-2024-12-17 | $16.5 | $66 | 200,000 | 100000 |\n| azure/us/o1-preview-2024-09-12 | $16.5 | $66 | 128,000 | 32768 |\n| azure/eu/o1-preview-2024-09-12 | $16.5 | $66 | 128,000 | 32768 |\n| azure/us/gpt-4o-2024-11-20 | $2.75 | $11 | 128,000 | 16384 |\n| azure/eu/gpt-4o-2024-11-20 | $2.75 | $11 | 128,000 | 16384 |\n| azure/us/gpt-4o-2024-08-06 | $2.75 | $11 | 128,000 | 16384 |\n| azure/eu/gpt-4o-2024-08-06 | $2.75 | $11 | 128,000 | 16384 |\n| azure/us/gpt-4o-mini-2024-07-18 | $0.16 | $0.66 | 128,000 | 16384 |\n| azure/eu/gpt-4o-mini-2024-07-18 | $0.16 | $0.66 | 128,000 | 16384 |\n| azure_ai/deepseek-v3 | $1.14 | $4.56 | 128,000 | 8192 |\n| azure_ai/mistral-nemo | $0.15 | $0.15 | 131,072 | 4096 |\n| azure_ai/Phi-4-mini-instruct | $0.08 | $0.3 | 131,072 | 4096 |\n| azure_ai/Phi-4-multimodal-instruct | $0.08 | $0.32 | 131,072 | 4096 |\n| gemini/gemini-2.0-pro-exp-02-05 | $0 | $0 | 2,097,152 | 8192 |\n| gemini/gemini-2.0-flash-thinking-exp-01-21 | $0 | $0 | 1,048,576 | 65536 |\n| gemini/gemma-3-27b-it | $0 | $0 | 131,072 | 8192 |\n| gemini/learnlm-1.5-pro-experimental | $0 | $0 | 32,767 | 8192 |\n| vertex_ai/imagen-3.0-generate-002 | -- | -- | nan | nan |\n| jamba-large-1.6 | $2 | $8 | 256,000 | 256000 |\n| jamba-mini-1.6 | $0.2 | $0.4 | 256,000 | 256000 |\n| eu.amazon.nova-micro-v1:0 | $0.05 | $0.18 | 128,000 | 10000 |\n| eu.amazon.nova-lite-v1:0 | $0.08 | $0.31 | 300,000 | 10000 |\n| 1024-x-1024/50-steps/bedrock/amazon.nova-canvas-v1:0 | -- | -- | 2,600 | nan |\n| eu.amazon.nova-pro-v1:0 | $1.05 | $4.2 | 300,000 | 10000 |\n| us.deepseek.r1-v1:0 | $1.35 | $5.4 | 128,000 | 4096 |\n| snowflake/deepseek-r1 | -- | -- | 32,768 | 8192 |\n| snowflake/snowflake-arctic | -- | -- | 4,096 | 8192 |\n| snowflake/claude-3-5-sonnet | -- | -- | 18,000 | 8192 |\n| snowflake/mistral-large | -- | -- | 32,000 | 8192 |\n| snowflake/mistral-large2 | -- | -- | 128,000 | 8192 |\n| snowflake/reka-flash | -- | -- | 100,000 | 8192 |\n| snowflake/reka-core | -- | -- | 32,000 | 8192 |\n| snowflake/jamba-instruct | -- | -- | 256,000 | 8192 |\n| snowflake/jamba-1.5-mini | -- | -- | 256,000 | 8192 |\n| snowflake/jamba-1.5-large | -- | -- | 256,000 | 8192 |\n| snowflake/mixtral-8x7b | -- | -- | 32,000 | 8192 |\n| snowflake/llama2-70b-chat | -- | -- | 4,096 | 8192 |\n| snowflake/llama3-8b | -- | -- | 8,000 | 8192 |\n| snowflake/llama3-70b | -- | -- | 8,000 | 8192 |\n| snowflake/llama3.1-8b | -- | -- | 128,000 | 8192 |\n| snowflake/llama3.1-70b | -- | -- | 128,000 | 8192 |\n| snowflake/llama3.3-70b | -- | -- | 128,000 | 8192 |\n| snowflake/snowflake-llama-3.3-70b | -- | -- | 8,000 | 8192 |\n| snowflake/llama3.1-405b | -- | -- | 128,000 | 8192 |\n| snowflake/snowflake-llama-3.1-405b | -- | -- | 8,000 | 8192 |\n| snowflake/llama3.2-1b | -- | -- | 128,000 | 8192 |\n| snowflake/llama3.2-3b | -- | -- | 128,000 | 8192 |\n| snowflake/mistral-7b | -- | -- | 32,000 | 8192 |\n| snowflake/gemma-7b | -- | -- | 8,000 | 8192 |\n| azure/global/gpt-4o-2024-11-20 | $2.5 | $10 | 128,000 | 16384 |\n| azure/global/gpt-4o-2024-08-06 | $2.5 | $10 | 128,000 | 16384 |\n| o1-pro | $150 | $600 | 200,000 | 100000 |\n| o1-pro-2025-03-19 | $150 | $600 | 200,000 | 100000 |\n| gpt-4o-search-preview-2025-03-11 | $2.5 | $10 | 128,000 | 16384 |\n| gpt-4o-search-preview | $2.5 | $10 | 128,000 | 16384 |\n| gpt-4o-mini-search-preview-2025-03-11 | $0.15 | $0.6 | 128,000 | 16384 |\n| gpt-4o-mini-search-preview | $0.15 | $0.6 | 128,000 | 16384 |\n| azure/gpt-4.5-preview | $75 | $150 | 128,000 | 16384 |\n| azure_ai/mistral-small-2503 | $1 | $3 | 128,000 | 128000 |\n| text-embedding-large-exp-03-07 | $0.1 | $0 | 8,192 | nan |\n| gpt-4.1 | $2 | $8 | 1,047,576 | 32768 |\n| gpt-4.1-2025-04-14 | $2 | $8 | 1,047,576 | 32768 |\n| gpt-4.1-mini | $0.4 | $1.6 | 1,047,576 | 32768 |\n| gpt-4.1-mini-2025-04-14 | $0.4 | $1.6 | 1,047,576 | 32768 |\n| gpt-4.1-nano | $0.1 | $0.4 | 1,047,576 | 32768 |\n| gpt-4.1-nano-2025-04-14 | $0.1 | $0.4 | 1,047,576 | 32768 |\n| watsonx/ibm/granite-3-8b-instruct | $200 | $200 | 8,192 | 1024 |\n| computer-use-preview | $3 | $12 | 8,192 | 1024 |\n| o3 | $2 | $8 | 200,000 | 100000 |\n| o3-2025-04-16 | $2 | $8 | 200,000 | 100000 |\n| o4-mini | $1.1 | $4.4 | 200,000 | 100000 |\n| o4-mini-2025-04-16 | $1.1 | $4.4 | 200,000 | 100000 |\n| gpt-image-1 | -- | -- | nan | nan |\n| low/1024-x-1024/gpt-image-1 | -- | -- | nan | nan |\n| medium/1024-x-1024/gpt-image-1 | -- | -- | nan | nan |\n| high/1024-x-1024/gpt-image-1 | -- | -- | nan | nan |\n| low/1024-x-1536/gpt-image-1 | -- | -- | nan | nan |\n| medium/1024-x-1536/gpt-image-1 | -- | -- | nan | nan |\n| high/1024-x-1536/gpt-image-1 | -- | -- | nan | nan |\n| low/1536-x-1024/gpt-image-1 | -- | -- | nan | nan |\n| medium/1536-x-1024/gpt-image-1 | -- | -- | nan | nan |\n| high/1536-x-1024/gpt-image-1 | -- | -- | nan | nan |\n| gpt-4o-transcribe | $2.5 | $10 | 16,000 | 2000 |\n| gpt-4o-mini-transcribe | $1.25 | $5 | 16,000 | 2000 |\n| gpt-4o-mini-tts | $2.5 | $10 | nan | nan |\n| azure/computer-use-preview | $3 | $12 | 8,192 | 1024 |\n| azure/gpt-4o-audio-preview-2024-12-17 | $2.5 | $10 | 128,000 | 16384 |\n| azure/gpt-4o-mini-audio-preview-2024-12-17 | $2.5 | $10 | 128,000 | 16384 |\n| azure/gpt-4.1 | $2 | $8 | 1,047,576 | 32768 |\n| azure/gpt-4.1-2025-04-14 | $2 | $8 | 1,047,576 | 32768 |\n| azure/gpt-4.1-mini | $0.4 | $1.6 | 1,047,576 | 32768 |\n| azure/gpt-4.1-mini-2025-04-14 | $0.4 | $1.6 | 1,047,576 | 32768 |\n| azure/gpt-4.1-nano | $0.1 | $0.4 | 1,047,576 | 32768 |\n| azure/gpt-4.1-nano-2025-04-14 | $0.1 | $0.4 | 1,047,576 | 32768 |\n| azure/o3 | $2 | $8 | 200,000 | 100000 |\n| azure/o3-2025-04-16 | $10 | $40 | 200,000 | 100000 |\n| azure/o4-mini | $1.1 | $4.4 | 200,000 | 100000 |\n| azure/gpt-4o-realtime-preview-2024-12-17 | $5 | $20 | 128,000 | 4096 |\n| azure/us/gpt-4o-realtime-preview-2024-12-17 | $5.5 | $22 | 128,000 | 4096 |\n| azure/eu/gpt-4o-realtime-preview-2024-12-17 | $5.5 | $22 | 128,000 | 4096 |\n| azure/o4-mini-2025-04-16 | $1.1 | $4.4 | 200,000 | 100000 |\n| azure/gpt-image-1 | -- | -- | nan | nan |\n| azure/low/1024-x-1024/gpt-image-1 | -- | -- | nan | nan |\n| azure/medium/1024-x-1024/gpt-image-1 | -- | -- | nan | nan |\n| azure/high/1024-x-1024/gpt-image-1 | -- | -- | nan | nan |\n| azure/low/1024-x-1536/gpt-image-1 | -- | -- | nan | nan |\n| azure/medium/1024-x-1536/gpt-image-1 | -- | -- | nan | nan |\n| azure/high/1024-x-1536/gpt-image-1 | -- | -- | nan | nan |\n| azure/low/1536-x-1024/gpt-image-1 | -- | -- | nan | nan |\n| azure/medium/1536-x-1024/gpt-image-1 | -- | -- | nan | nan |\n| azure/high/1536-x-1024/gpt-image-1 | -- | -- | nan | nan |\n| azure_ai/mistral-large-latest | $2 | $6 | 128,000 | 4096 |\n| xai/grok-3-beta | $3 | $15 | 131,072 | 131072 |\n| xai/grok-3-fast-beta | $5 | $25 | 131,072 | 131072 |\n| xai/grok-3-fast-latest | $5 | $25 | 131,072 | 131072 |\n| xai/grok-3-mini-beta | $0.3 | $0.5 | 131,072 | 131072 |\n| xai/grok-3-mini-fast-beta | $0.6 | $4 | 131,072 | 131072 |\n| xai/grok-3-mini-fast-latest | $0.6 | $4 | 131,072 | 131072 |\n| groq/whisper-large-v3 | -- | -- | nan | nan |\n| groq/whisper-large-v3-turbo | -- | -- | nan | nan |\n| groq/distil-whisper-large-v3-en | -- | -- | nan | nan |\n| meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8 | -- | -- | 10,000,000 | 4028 |\n| meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | -- | -- | 1,000,000 | 4028 |\n| meta_llama/Llama-3.3-70B-Instruct | -- | -- | 128,000 | 4028 |\n| meta_llama/Llama-3.3-8B-Instruct | -- | -- | 128,000 | 4028 |\n| gemini-2.5-pro-exp-03-25 | $1.25 | $10 | 1,048,576 | 65535 |\n| gemini/gemini-2.5-pro-exp-03-25 | $0 | $0 | 1,048,576 | 65535 |\n| gemini/gemini-2.5-flash-preview-04-17 | $0.15 | $0.6 | 1,048,576 | 65535 |\n| gemini-2.5-flash-preview-04-17 | $0.15 | $0.6 | 1,048,576 | 65535 |\n| gemini-2.0-flash | $0.1 | $0.4 | 1,048,576 | 8192 |\n| gemini-2.0-flash-lite | $0.08 | $0.3 | 1,048,576 | 8192 |\n| gemini-2.0-flash-lite-001 | $0.08 | $0.3 | 1,048,576 | 8192 |\n| gemini-2.5-pro-preview-05-06 | $1.25 | $10 | 1,048,576 | 65535 |\n| gemini-2.5-pro-preview-03-25 | $1.25 | $10 | 1,048,576 | 65535 |\n| gemini/gemini-2.0-flash-lite | $0.08 | $0.3 | 1,048,576 | 8192 |\n| gemini/gemini-2.5-pro-preview-05-06 | $1.25 | $10 | 1,048,576 | 65535 |\n| gemini/gemini-2.5-pro-preview-03-25 | $1.25 | $10 | 1,048,576 | 65535 |\n| vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas | $0.25 | $0.7 | 10,000,000 | 1e+07 |\n| vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas | $0.25 | $0.7 | 10,000,000 | 1e+07 |\n| vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas | $0.35 | $1.15 | 1,000,000 | 1e+06 |\n| vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas | $0.35 | $1.15 | 1,000,000 | 1e+06 |\n| vertex_ai/mistral-small-2503@001 | $1 | $3 | 32,000 | 8191 |\n| vertex_ai/mistral-small-2503 | $1 | $3 | 128,000 | 128000 |\n| multimodalembedding | $0.8 | $0 | 2,048 | nan |\n| multimodalembedding@001 | $0.8 | $0 | 2,048 | nan |\n| command-a-03-2025 | $2.5 | $10 | 256,000 | 8000 |\n| mistralai/mistral-small-3.1-24b-instruct | $0.1 | $0.3 | nan | nan |\n| openrouter/openai/o3-mini | $1.1 | $4.4 | 128,000 | 65536 |\n| openrouter/openai/o3-mini-high | $1.1 | $4.4 | 128,000 | 65536 |\n| us.amazon.nova-premier-v1:0 | $2.5 | $12.5 | 1,000,000 | 10000 |\n| meta.llama4-maverick-17b-instruct-v1:0 | $0.24 | $0.97 | 128,000 | 4096 |\n| us.meta.llama4-maverick-17b-instruct-v1:0 | $0.24 | $0.97 | 128,000 | 4096 |\n| meta.llama4-scout-17b-instruct-v1:0 | $0.17 | $0.66 | 128,000 | 4096 |\n| us.meta.llama4-scout-17b-instruct-v1:0 | $0.17 | $0.66 | 128,000 | 4096 |\n| together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | $0.27 | $0.85 | nan | nan |\n| together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct | $0.18 | $0.59 | nan | nan |\n| together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo | -- | -- | nan | nan |\n| together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo | -- | -- | nan | nan |\n| together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo | -- | -- | nan | nan |\n| together_ai/deepseek-ai/DeepSeek-V3 | $1.25 | $1.25 | 65,536 | 8192 |\n| together_ai/mistralai/Mistral-Small-24B-Instruct-2501 | -- | -- | nan | nan |\n| perplexity/sonar-deep-research | $2 | $8 | 128,000 | nan |\n| fireworks_ai/accounts/fireworks/models/deepseek-r1 | $3 | $8 | 128,000 | 20480 |\n| fireworks_ai/accounts/fireworks/models/deepseek-r1-basic | $0.55 | $2.19 | 128,000 | 20480 |\n| fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct | $3 | $3 | 128,000 | 16384 |\n| fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic | $0.22 | $0.88 | 131,072 | 131072 |\n| fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic | $0.15 | $0.6 | 131,072 | 131072 |\n| fireworks-ai-up-to-4b | $0.2 | $0.2 | nan | nan |\n| fireworks-ai-4.1b-to-16b | $0.2 | $0.2 | nan | nan |\n| fireworks-ai-above-16b | $0.9 | $0.9 | nan | nan |\n| databricks/databricks-claude-3-7-sonnet | $2.5 | $17.86 | 200,000 | 128000 |\n| databricks/databricks-meta-llama-3-3-70b-instruct | $1 | $3 | 128,000 | 128000 |\n| azure_ai/deepseek-v3-0324 | $1.14 | $4.56 | 128,000 | 8192 |\n| azure_ai/Llama-4-Scout-17B-16E-Instruct | $0.2 | $0.78 | 10,000,000 | 16384 |\n| azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8 | $1.41 | $0.35 | 1,000,000 | 16384 |\n| cerebras/llama-3.3-70b | $0.85 | $1.2 | 128,000 | 128000 |\n| perplexity/sonar-reasoning | $1 | $5 | 128,000 | nan |\n| perplexity/sonar-reasoning-pro | $2 | $8 | 128,000 | nan |\n| nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct | $0.09 | $0.29 | nan | nan |\n| nscale/Qwen/Qwen2.5-Coder-3B-Instruct | $0.01 | $0.03 | nan | nan |\n| nscale/Qwen/Qwen2.5-Coder-7B-Instruct | $0.01 | $0.03 | nan | nan |\n| nscale/Qwen/Qwen2.5-Coder-32B-Instruct | $0.06 | $0.2 | nan | nan |\n| nscale/Qwen/QwQ-32B | $0.18 | $0.2 | nan | nan |\n| nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B | $0.38 | $0.38 | nan | nan |\n| nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B | $0.02 | $0.02 | nan | nan |\n| nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B | $0.09 | $0.09 | nan | nan |\n| nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B | $0.2 | $0.2 | nan | nan |\n| nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B | $0.07 | $0.07 | nan | nan |\n| nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | $0.15 | $0.15 | nan | nan |\n| nscale/mistralai/mixtral-8x22b-instruct-v0.1 | $0.6 | $0.6 | nan | nan |\n| nscale/meta-llama/Llama-3.1-8B-Instruct | $0.03 | $0.03 | nan | nan |\n| nscale/meta-llama/Llama-3.3-70B-Instruct | $0.2 | $0.2 | nan | nan |\n| nscale/black-forest-labs/FLUX.1-schnell | -- | -- | nan | nan |\n| nscale/stabilityai/stable-diffusion-xl-base-1.0 | -- | -- | nan | nan |\n| azure/gpt-4o-mini-tts | $2.5 | $10 | nan | nan |\n| azure_ai/embed-v-4-0 | $0.12 | $0 | 128,000 | nan |\n| eu.anthropic.claude-3-7-sonnet-20250219-v1:0 | $3 | $15 | 200,000 | 8192 |\n| xai/grok-3 | $3 | $15 | 131,072 | 131072 |\n| groq/llama-guard-3-8b | $0.2 | $0.2 | 8,192 | 8192 |\n| groq/meta-llama/llama-4-scout-17b-16e-instruct | $0.11 | $0.34 | 131,072 | 8192 |\n| groq/meta-llama/llama-4-maverick-17b-128e-instruct | $0.2 | $0.6 | 131,072 | 8192 |\n| groq/mistral-saba-24b | $0.79 | $0.79 | 32,000 | 32000 |\n| groq/qwen-qwq-32b | $0.29 | $0.39 | 128,000 | 128000 |\n| groq/playai-tts | -- | -- | 10,000 | 10000 |\n| claude-opus-4-20250514 | $15 | $75 | 200,000 | 32000 |\n| claude-sonnet-4-20250514 | $3 | $15 | 200,000 | 64000 |\n| gemini/gemini-2.5-flash-preview-tts | $0.15 | $0.6 | 1,048,576 | 65535 |\n| gemini/gemini-2.5-flash-preview-05-20 | $0.3 | $2.5 | 1,048,576 | 65535 |\n| gemini-2.5-flash-preview-05-20 | $0.3 | $2.5 | 1,048,576 | 65535 |\n| gemini-2.0-flash-preview-image-generation | $0.1 | $0.4 | 1,048,576 | 8192 |\n| gemini-2.5-pro-preview-tts | $1.25 | $10 | 1,048,576 | 65535 |\n| gemini/gemini-2.0-flash-preview-image-generation | $0.1 | $0.4 | 1,048,576 | 8192 |\n| gemini/gemini-2.5-pro-preview-tts | $1.25 | $10 | 1,048,576 | 65535 |\n| vertex_ai/claude-opus-4@20250514 | $15 | $75 | 200,000 | 32000 |\n| vertex_ai/claude-sonnet-4@20250514 | $3 | $15 | 200,000 | 64000 |\n| anthropic.claude-opus-4-20250514-v1:0 | $15 | $75 | 200,000 | 32000 |\n| anthropic.claude-sonnet-4-20250514-v1:0 | $3 | $15 | 200,000 | 64000 |\n| us.anthropic.claude-opus-4-20250514-v1:0 | $15 | $75 | 200,000 | 32000 |\n| us.anthropic.claude-sonnet-4-20250514-v1:0 | $3 | $15 | 200,000 | 64000 |\n| eu.anthropic.claude-opus-4-20250514-v1:0 | $15 | $75 | 200,000 | 32000 |\n| eu.anthropic.claude-sonnet-4-20250514-v1:0 | $3 | $15 | 200,000 | 64000 |\n| databricks/databricks-llama-4-maverick | $5 | $15 | 128,000 | 128000 |\n| sambanova/Llama-4-Maverick-17B-128E-Instruct | $0.63 | $1.8 | 131,072 | 131072 |\n| sambanova/Llama-4-Scout-17B-16E-Instruct | $0.4 | $0.7 | 8,192 | 8192 |\n| sambanova/Meta-Llama-Guard-3-8B | $0.3 | $0.3 | 16,384 | 16384 |\n| sambanova/Qwen3-32B | $0.4 | $0.8 | 8,192 | 8192 |\n| sambanova/QwQ-32B | $0.5 | $1 | 16,384 | 16384 |\n| sambanova/Qwen2-Audio-7B-Instruct | $0.5 | $100 | 4,096 | 4096 |\n| sambanova/DeepSeek-R1-Distill-Llama-70B | $0.7 | $1.4 | 131,072 | 131072 |\n| sambanova/DeepSeek-R1 | $5 | $7 | 32,768 | 32768 |\n| sambanova/DeepSeek-V3-0324 | $3 | $4.5 | 32,768 | 32768 |\n| featherless_ai/featherless-ai/Qwerky-72B | -- | -- | 32,768 | 4096 |\n| featherless_ai/featherless-ai/Qwerky-QwQ-32B | -- | -- | 32,768 | 4096 |\n| azure_ai/mistral-medium-2505 | $0.4 | $2 | 131,072 | 8191 |\n| mistral/devstral-small-2505 | $0.1 | $0.3 | 128,000 | 128000 |\n| gpt-4o-mini-audio-preview | $0.15 | $0.6 | 128,000 | 16384 |\n| mistral/mistral-medium-2505 | $0.4 | $2 | 131,072 | 8191 |\n| embed-v4.0 | $0.12 | $0 | 1,024 | nan |\n| cerebras/qwen-3-32b | $0.4 | $0.8 | 128,000 | 128000 |\n| gemini-embedding-001 | $0.15 | $0 | 2,048 | nan |\n| claude-4-opus-20250514 | $15 | $75 | 200,000 | 32000 |\n| claude-4-sonnet-20250514 | $3 | $15 | 1,000,000 | 1e+06 |\n| fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct | $0.9 | $0.9 | 16,384 | 16384 |\n| fireworks_ai/accounts/fireworks/models/deepseek-r1-0528 | $3 | $8 | 160,000 | 160000 |\n| codex-mini-latest | $1.5 | $6 | 200,000 | 100000 |\n| azure/codex-mini-latest | $1.5 | $6 | 200,000 | 100000 |\n| gemini-2.5-pro-preview-06-05 | $1.25 | $10 | 1,048,576 | 65535 |\n| gemini/gemini-2.5-pro-preview-06-05 | $1.25 | $10 | 1,048,576 | 65535 |\n| openai/gpt-4 | $30 | $60 | 8,192 | 4096 |\n| openai/gpt-4o | $2.5 | $10 | 128,000 | 16384 |\n| openai/gpt-4o-audio-preview | $2.5 | $10 | 128,000 | 16384 |\n| openai/gpt-4o-audio-preview-2024-10-01 | $2.5 | $10 | 128,000 | 16384 |\n| openai/gpt-4o-mini | $0.15 | $0.6 | 128,000 | 16384 |\n| openai/gpt-4o-mini-2024-07-18 | $0.15 | $0.6 | 128,000 | 16384 |\n| openai/o1-mini | $1.1 | $4.4 | 128,000 | 65536 |\n| openai/o1-mini-2024-09-12 | $3 | $12 | 128,000 | 65536 |\n| openai/o1-preview | $15 | $60 | 128,000 | 32768 |\n| openai/o1-preview-2024-09-12 | $15 | $60 | 128,000 | 32768 |\n| openai/chatgpt-4o-latest | $5 | $15 | 128,000 | 4096 |\n| openai/gpt-4o-2024-05-13 | $5 | $15 | 128,000 | 4096 |\n| openai/gpt-4o-2024-08-06 | $2.5 | $10 | 128,000 | 16384 |\n| openai/gpt-4-turbo-preview | $10 | $30 | 128,000 | 4096 |\n| openai/gpt-4-0314 | $30 | $60 | 8,192 | 4096 |\n| openai/gpt-4-0613 | $30 | $60 | 8,192 | 4096 |\n| openai/gpt-4-32k | $60 | $120 | 32,768 | 4096 |\n| openai/gpt-4-32k-0314 | $60 | $120 | 32,768 | 4096 |\n| openai/gpt-4-32k-0613 | $60 | $120 | 32,768 | 4096 |\n| openai/gpt-4-turbo | $10 | $30 | 128,000 | 4096 |\n| openai/gpt-4-turbo-2024-04-09 | $10 | $30 | 128,000 | 4096 |\n| openai/gpt-4-1106-preview | $10 | $30 | 128,000 | 4096 |\n| openai/gpt-4-0125-preview | $10 | $30 | 128,000 | 4096 |\n| openai/gpt-4-vision-preview | $10 | $30 | 128,000 | 4096 |\n| openai/gpt-4-1106-vision-preview | $10 | $30 | 128,000 | 4096 |\n| openai/gpt-3.5-turbo | $1.5 | $2 | 16,385 | 4096 |\n| openai/gpt-3.5-turbo-0301 | $1.5 | $2 | 4,097 | 4096 |\n| openai/gpt-3.5-turbo-0613 | $1.5 | $2 | 4,097 | 4096 |\n| openai/gpt-3.5-turbo-1106 | $1 | $2 | 16,385 | 4096 |\n| openai/gpt-3.5-turbo-0125 | $0.5 | $1.5 | 16,385 | 4096 |\n| openai/gpt-3.5-turbo-16k | $3 | $4 | 16,385 | 4096 |\n| openai/gpt-3.5-turbo-16k-0613 | $3 | $4 | 16,385 | 4096 |\n| openai/ft:gpt-3.5-turbo | $3 | $6 | 16,385 | 4096 |\n| openai/ft:gpt-3.5-turbo-0125 | $3 | $6 | 16,385 | 4096 |\n| openai/ft:gpt-3.5-turbo-1106 | $3 | $6 | 16,385 | 4096 |\n| openai/ft:gpt-3.5-turbo-0613 | $3 | $6 | 4,096 | 4096 |\n| openai/ft:gpt-4-0613 | $30 | $60 | 8,192 | 4096 |\n| openai/ft:gpt-4o-2024-08-06 | $3.75 | $15 | 128,000 | 16384 |\n| openai/ft:gpt-4o-mini-2024-07-18 | $0.3 | $1.2 | 128,000 | 16384 |\n| openai/text-embedding-3-large | $0.13 | $0 | 8,191 | nan |\n| openai/text-embedding-3-small | $0.02 | $0 | 8,191 | nan |\n| openai/text-embedding-ada-002 | $0.1 | $0 | 8,191 | nan |\n| openai/text-embedding-ada-002-v2 | $0.1 | $0 | 8,191 | nan |\n| openai/text-moderation-stable | $0 | $0 | 32,768 | 0 |\n| openai/text-moderation-007 | $0 | $0 | 32,768 | 0 |\n| openai/text-moderation-latest | $0 | $0 | 32,768 | 0 |\n| openai/256-x-256/dall-e-2 | -- | -- | nan | nan |\n| openai/512-x-512/dall-e-2 | -- | -- | nan | nan |\n| openai/1024-x-1024/dall-e-2 | -- | -- | nan | nan |\n| openai/hd/1024-x-1792/dall-e-3 | -- | -- | nan | nan |\n| openai/hd/1792-x-1024/dall-e-3 | -- | -- | nan | nan |\n| openai/hd/1024-x-1024/dall-e-3 | -- | -- | nan | nan |\n| openai/standard/1024-x-1792/dall-e-3 | -- | -- | nan | nan |\n| openai/standard/1792-x-1024/dall-e-3 | -- | -- | nan | nan |\n| openai/standard/1024-x-1024/dall-e-3 | -- | -- | nan | nan |\n| openai/whisper-1 | -- | -- | nan | nan |\n| openai/tts-1 | -- | -- | nan | nan |\n| openai/tts-1-hd | -- | -- | nan | nan |\n| openai/gpt-4o-2024-11-20 | $2.5 | $10 | 128,000 | 16384 |\n| openai/ft:gpt-4o-2024-11-20 | $3.75 | $15 | 128,000 | 16384 |\n| openai/omni-moderation-latest | $0 | $0 | 32,768 | 0 |\n| openai/omni-moderation-latest-intents | $0 | $0 | 32,768 | 0 |\n| openai/omni-moderation-2024-09-26 | $0 | $0 | 32,768 | 0 |\n| openai/gpt-4o-audio-preview-2024-12-17 | $2.5 | $10 | 128,000 | 16384 |\n| openai/gpt-4o-mini-audio-preview-2024-12-17 | $0.15 | $0.6 | 128,000 | 16384 |\n| openai/o1 | $15 | $60 | 200,000 | 100000 |\n| openai/o1-2024-12-17 | $15 | $60 | 200,000 | 100000 |\n| openai/gpt-4o-realtime-preview-2024-10-01 | $5 | $20 | 128,000 | 4096 |\n| openai/gpt-4o-realtime-preview | $5 | $20 | 128,000 | 4096 |\n| openai/gpt-4o-realtime-preview-2024-12-17 | $5 | $20 | 128,000 | 4096 |\n| openai/gpt-4o-mini-realtime-preview | $0.6 | $2.4 | 128,000 | 4096 |\n| openai/gpt-4o-mini-realtime-preview-2024-12-17 | $0.6 | $2.4 | 128,000 | 4096 |\n| openai/o3-mini | $1.1 | $4.4 | 200,000 | 100000 |\n| openai/o3-mini-2025-01-31 | $1.1 | $4.4 | 200,000 | 100000 |\n| openai/gpt-4.5-preview | $75 | $150 | 128,000 | 16384 |\n| openai/gpt-4.5-preview-2025-02-27 | $75 | $150 | 128,000 | 16384 |\n| openai/o1-pro | $150 | $600 | 200,000 | 100000 |\n| openai/o1-pro-2025-03-19 | $150 | $600 | 200,000 | 100000 |\n| openai/gpt-4o-search-preview-2025-03-11 | $2.5 | $10 | 128,000 | 16384 |\n| openai/gpt-4o-search-preview | $2.5 | $10 | 128,000 | 16384 |\n| openai/gpt-4o-mini-search-preview-2025-03-11 | $0.15 | $0.6 | 128,000 | 16384 |\n| openai/gpt-4o-mini-search-preview | $0.15 | $0.6 | 128,000 | 16384 |\n| openai/gpt-4.1 | $2 | $8 | 1,047,576 | 32768 |\n| openai/gpt-4.1-2025-04-14 | $2 | $8 | 1,047,576 | 32768 |\n| openai/gpt-4.1-mini | $0.4 | $1.6 | 1,047,576 | 32768 |\n| openai/gpt-4.1-mini-2025-04-14 | $0.4 | $1.6 | 1,047,576 | 32768 |\n| openai/gpt-4.1-nano | $0.1 | $0.4 | 1,047,576 | 32768 |\n| openai/gpt-4.1-nano-2025-04-14 | $0.1 | $0.4 | 1,047,576 | 32768 |\n| openai/o3 | $2 | $8 | 200,000 | 100000 |\n| openai/o3-2025-04-16 | $2 | $8 | 200,000 | 100000 |\n| openai/o4-mini | $1.1 | $4.4 | 200,000 | 100000 |\n| openai/o4-mini-2025-04-16 | $1.1 | $4.4 | 200,000 | 100000 |\n| openai/gpt-image-1 | -- | -- | nan | nan |\n| openai/low/1024-x-1024/gpt-image-1 | -- | -- | nan | nan |\n| openai/medium/1024-x-1024/gpt-image-1 | -- | -- | nan | nan |\n| openai/high/1024-x-1024/gpt-image-1 | -- | -- | nan | nan |\n| openai/low/1024-x-1536/gpt-image-1 | -- | -- | nan | nan |\n| openai/medium/1024-x-1536/gpt-image-1 | -- | -- | nan | nan |\n| openai/high/1024-x-1536/gpt-image-1 | -- | -- | nan | nan |\n| openai/low/1536-x-1024/gpt-image-1 | -- | -- | nan | nan |\n| openai/medium/1536-x-1024/gpt-image-1 | -- | -- | nan | nan |\n| openai/high/1536-x-1024/gpt-image-1 | -- | -- | nan | nan |\n| openai/gpt-4o-transcribe | $2.5 | $10 | 16,000 | 2000 |\n| openai/gpt-4o-mini-transcribe | $1.25 | $5 | 16,000 | 2000 |\n| openai/gpt-4o-mini-tts | $2.5 | $10 | nan | nan |\n| openai/gpt-4o-mini-audio-preview | $0.15 | $0.6 | 128,000 | 16384 |\n| openai/codex-mini-latest | $1.5 | $6 | 200,000 | 100000 |\n| gpt-4o-audio-preview-2025-06-03 | $2.5 | $10 | 128,000 | 16384 |\n| openai/gpt-4o-audio-preview-2025-06-03 | $2.5 | $10 | 128,000 | 16384 |\n| o3-pro | $20 | $80 | 200,000 | 100000 |\n| o3-pro-2025-06-10 | $20 | $80 | 200,000 | 100000 |\n| mistral/magistral-medium-2506 | $2 | $5 | 40,000 | 40000 |\n| mistral/magistral-small-2506 | $0.5 | $1.5 | 40,000 | 40000 |\n| vertex_ai/claude-opus-4 | $15 | $75 | 200,000 | 32000 |\n| vertex_ai/claude-sonnet-4 | $3 | $15 | 200,000 | 64000 |\n| openai/o3-pro | $20 | $80 | 200,000 | 100000 |\n| openai/o3-pro-2025-06-10 | $20 | $80 | 200,000 | 100000 |\n| deepgram/nova-3 | -- | -- | nan | nan |\n| deepgram/nova-3-general | -- | -- | nan | nan |\n| deepgram/nova-3-medical | -- | -- | nan | nan |\n| deepgram/nova-2 | -- | -- | nan | nan |\n| deepgram/nova-2-general | -- | -- | nan | nan |\n| deepgram/nova-2-meeting | -- | -- | nan | nan |\n| deepgram/nova-2-phonecall | -- | -- | nan | nan |\n| deepgram/nova-2-voicemail | -- | -- | nan | nan |\n| deepgram/nova-2-finance | -- | -- | nan | nan |\n| deepgram/nova-2-conversationalai | -- | -- | nan | nan |\n| deepgram/nova-2-video | -- | -- | nan | nan |\n| deepgram/nova-2-drivethru | -- | -- | nan | nan |\n| deepgram/nova-2-automotive | -- | -- | nan | nan |\n| deepgram/nova-2-atc | -- | -- | nan | nan |\n| deepgram/nova | -- | -- | nan | nan |\n| deepgram/nova-general | -- | -- | nan | nan |\n| deepgram/nova-phonecall | -- | -- | nan | nan |\n| deepgram/enhanced | -- | -- | nan | nan |\n| deepgram/enhanced-general | -- | -- | nan | nan |\n| deepgram/enhanced-meeting | -- | -- | nan | nan |\n| deepgram/enhanced-phonecall | -- | -- | nan | nan |\n| deepgram/enhanced-finance | -- | -- | nan | nan |\n| deepgram/base | -- | -- | nan | nan |\n| deepgram/base-general | -- | -- | nan | nan |\n| deepgram/base-meeting | -- | -- | nan | nan |\n| deepgram/base-phonecall | -- | -- | nan | nan |\n| deepgram/base-voicemail | -- | -- | nan | nan |\n| deepgram/base-finance | -- | -- | nan | nan |\n| deepgram/base-conversationalai | -- | -- | nan | nan |\n| deepgram/base-video | -- | -- | nan | nan |\n| deepgram/whisper | -- | -- | nan | nan |\n| deepgram/whisper-tiny | -- | -- | nan | nan |\n| deepgram/whisper-base | -- | -- | nan | nan |\n| deepgram/whisper-small | -- | -- | nan | nan |\n| deepgram/whisper-medium | -- | -- | nan | nan |\n| deepgram/whisper-large | -- | -- | nan | nan |\n| azure/gpt-4o-transcribe | $2.5 | $10 | 16,000 | 2000 |\n| azure/gpt-4o-mini-transcribe | $1.25 | $5 | 16,000 | 2000 |\n| mistral/magistral-medium-latest | $2 | $5 | 40,000 | 40000 |\n| mistral/magistral-small-latest | $0.5 | $1.5 | 40,000 | 40000 |\n| xai/grok-3-latest | $3 | $15 | 131,072 | 131072 |\n| xai/grok-3-mini | $0.3 | $0.5 | 131,072 | 131072 |\n| xai/grok-3-mini-latest | $0.3 | $0.5 | 131,072 | 131072 |\n| xai/grok-3-mini-fast | $0.6 | $4 | 131,072 | 131072 |\n| vertex_ai/imagen-4.0-generate-preview-06-06 | -- | -- | nan | nan |\n| vertex_ai/imagen-4.0-ultra-generate-preview-06-06 | -- | -- | nan | nan |\n| vertex_ai/imagen-4.0-fast-generate-preview-06-06 | -- | -- | nan | nan |\n| gemini/gemini-2.5-pro | $1.25 | $10 | 1,048,576 | 65535 |\n| gemini-2.5-flash | $0.3 | $2.5 | 1,048,576 | 65535 |\n| gemini-2.5-flash-lite-preview-06-17 | $0.1 | $0.4 | 1,048,576 | 65535 |\n| openrouter/deepseek/deepseek-r1-0528 | $0.5 | $2.15 | 65,336 | 8192 |\n| openrouter/google/gemini-2.5-pro | $1.25 | $10 | 1,048,576 | 8192 |\n| openrouter/google/gemini-2.5-flash | $0.3 | $2.5 | 1,048,576 | 8192 |\n| openrouter/anthropic/claude-sonnet-4 | $3 | $15 | 200,000 | 64000 |\n| gemini/gemini-2.5-flash | $0.3 | $2.5 | 1,048,576 | 65535 |\n| gemini/gemini-2.5-flash-lite-preview-06-17 | $0.1 | $0.4 | 1,048,576 | 65535 |\n| gemini-2.5-pro | $1.25 | $10 | 1,048,576 | 65535 |\n| apac.amazon.nova-micro-v1:0 | $0.04 | $0.15 | 128,000 | 10000 |\n| apac.amazon.nova-lite-v1:0 | $0.06 | $0.25 | 300,000 | 10000 |\n| apac.amazon.nova-pro-v1:0 | $0.84 | $3.36 | 300,000 | 10000 |\n| apac.anthropic.claude-3-haiku-20240307-v1:0 | $0.25 | $1.25 | 200,000 | 4096 |\n| apac.anthropic.claude-3-sonnet-20240229-v1:0 | $3 | $15 | 200,000 | 4096 |\n| apac.anthropic.claude-3-5-sonnet-20240620-v1:0 | $3 | $15 | 200,000 | 4096 |\n| apac.anthropic.claude-3-5-sonnet-20241022-v2:0 | $3 | $15 | 200,000 | 8192 |\n| apac.anthropic.claude-sonnet-4-20250514-v1:0 | $3 | $15 | 200,000 | 64000 |\n| azure/codex-mini | $1.5 | $6 | 200,000 | 100000 |\n| openrouter/mistralai/mistral-small-3.1-24b-instruct | $0.1 | $0.3 | nan | nan |\n| openrouter/mistralai/mistral-small-3.2-24b-instruct | $0.1 | $0.3 | nan | nan |\n| azure/o3-pro | $20 | $80 | 200,000 | 100000 |\n| azure/o3-pro-2025-06-10 | $20 | $80 | 200,000 | 100000 |\n| o3-deep-research | $10 | $40 | 200,000 | 100000 |\n| o3-deep-research-2025-06-26 | $10 | $40 | 200,000 | 100000 |\n| o4-mini-deep-research | $2 | $8 | 200,000 | 100000 |\n| o4-mini-deep-research-2025-06-26 | $2 | $8 | 200,000 | 100000 |\n| openai/o3-deep-research | $10 | $40 | 200,000 | 100000 |\n| openai/o3-deep-research-2025-06-26 | $10 | $40 | 200,000 | 100000 |\n| openai/o4-mini-deep-research | $2 | $8 | 200,000 | 100000 |\n| openai/o4-mini-deep-research-2025-06-26 | $2 | $8 | 200,000 | 100000 |\n| deepseek/deepseek-r1 | $0.55 | $2.19 | 65,536 | 8192 |\n| deepseek/deepseek-v3 | $0.27 | $1.1 | 65,536 | 8192 |\n| elevenlabs/scribe_v1 | -- | -- | nan | nan |\n| elevenlabs/scribe_v1_experimental | -- | -- | nan | nan |\n| watsonx/mistralai/mistral-large | $3 | $10 | 131,072 | 16384 |\n| azure/o3-deep-research | $10 | $40 | 200,000 | 100000 |\n| azure_ai/grok-3 | $3.3 | $16.5 | 131,072 | 131072 |\n| azure_ai/global/grok-3 | $3 | $15 | 131,072 | 131072 |\n| azure_ai/global/grok-3-mini | $0.25 | $1.27 | 131,072 | 131072 |\n| azure_ai/grok-3-mini | $0.28 | $1.38 | 131,072 | 131072 |\n| azure_ai/cohere-rerank-v3.5 | $0 | $0 | 4,096 | 4096 |\n| mistral/devstral-small-2507 | $0.1 | $0.3 | 128,000 | 128000 |\n| mistral/devstral-medium-2507 | $0.4 | $2 | 128,000 | 128000 |\n| xai/grok-4 | $3 | $15 | 256,000 | 256000 |\n| xai/grok-4-0709 | $3 | $15 | 256,000 | 256000 |\n| xai/grok-4-latest | $3 | $15 | 256,000 | 256000 |\n| groq/moonshotai-kimi-k2-instruct | $1 | $3 | 131,072 | 16384 |\n| jamba-large-1.7 | $2 | $8 | 256,000 | 256000 |\n| jamba-mini-1.7 | $0.2 | $0.4 | 256,000 | 256000 |\n| eu.mistral.pixtral-large-2502-v1:0 | $2 | $6 | 128,000 | 4096 |\n| us.mistral.pixtral-large-2502-v1:0 | $2 | $6 | 128,000 | 4096 |\n| together_ai/deepseek-ai/DeepSeek-R1 | $3 | $7 | 128,000 | 20480 |\n| together_ai/moonshotai/Kimi-K2-Instruct | $1 | $3 | nan | nan |\n| dashscope/qwen-max | -- | -- | 30,720 | 8192 |\n| dashscope/qwen-plus-latest | -- | -- | 129,024 | 16384 |\n| dashscope/qwen-turbo-latest | -- | -- | 129,024 | 16384 |\n| dashscope/qwen3-30b-a3b | -- | -- | 129,024 | 16384 |\n| moonshot/moonshot-v1-8k | $0.2 | $2 | 8,192 | 8192 |\n| moonshot/moonshot-v1-32k | $1 | $3 | 32,768 | 32768 |\n| moonshot/moonshot-v1-128k | $2 | $5 | 131,072 | 131072 |\n| moonshot/moonshot-v1-auto | $2 | $5 | 131,072 | 131072 |\n| moonshot/kimi-k2-0711-preview | $0.6 | $2.5 | 131,072 | 131072 |\n| moonshot/moonshot-v1-32k-0430 | $1 | $3 | 32,768 | 32768 |\n| moonshot/moonshot-v1-128k-0430 | $2 | $5 | 131,072 | 131072 |\n| moonshot/moonshot-v1-8k-0430 | $0.2 | $2 | 8,192 | 8192 |\n| azure_ai/jais-30b-chat | $3200 | $9710 | 8,192 | 8192 |\n| groq/moonshotai/kimi-k2-instruct | $1 | $3 | 131,072 | 16384 |\n| openrouter/switchpoint/router | $0.85 | $3.4 | 131,072 | 131072 |\n| v0/v0-1.0-md | $3 | $15 | 128,000 | 128000 |\n| v0/v0-1.5-md | $3 | $15 | 128,000 | 128000 |\n| v0/v0-1.5-lg | $15 | $75 | 512,000 | 512000 |\n| bedrock/us-gov-east-1/amazon.titan-embed-text-v1 | $0.1 | $0 | 8,192 | nan |\n| bedrock/us-gov-east-1/amazon.titan-embed-text-v2:0 | $0.2 | $0 | 8,192 | nan |\n| bedrock/us-gov-east-1/amazon.titan-text-express-v1 | $1.3 | $1.7 | 42,000 | 8000 |\n| bedrock/us-gov-east-1/amazon.titan-text-lite-v1 | $0.3 | $0.4 | 42,000 | 4000 |\n| bedrock/us-gov-east-1/amazon.titan-text-premier-v1:0 | $0.5 | $1.5 | 42,000 | 32000 |\n| bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0 | $3.6 | $18 | 200,000 | 8192 |\n| bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0 | $0.3 | $1.5 | 200,000 | 4096 |\n| bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0 | $2.65 | $3.5 | 8,000 | 2048 |\n| bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0 | $0.3 | $2.65 | 8,000 | 2048 |\n| bedrock/us-gov-west-1/amazon.titan-embed-text-v1 | $0.1 | $0 | 8,192 | nan |\n| bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0 | $0.2 | $0 | 8,192 | nan |\n| bedrock/us-gov-west-1/amazon.titan-text-express-v1 | $1.3 | $1.7 | 42,000 | 8000 |\n| bedrock/us-gov-west-1/amazon.titan-text-lite-v1 | $0.3 | $0.4 | 42,000 | 4000 |\n| bedrock/us-gov-west-1/amazon.titan-text-premier-v1:0 | $0.5 | $1.5 | 42,000 | 32000 |\n| bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0 | $3.6 | $18 | 200,000 | 8192 |\n| bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0 | $0.3 | $1.5 | 200,000 | 4096 |\n| bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0 | $2.65 | $3.5 | 8,000 | 2048 |\n| bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0 | $0.3 | $2.65 | 8,000 | 2048 |\n| bedrock/us-gov-east-1/amazon.nova-pro-v1:0 | $0.96 | $3.84 | 300,000 | 10000 |\n| bedrock/us-gov-west-1/amazon.nova-pro-v1:0 | $0.96 | $3.84 | 300,000 | 10000 |\n| moonshot/kimi-latest | $2 | $5 | 131,072 | 131072 |\n| moonshot/kimi-latest-8k | $0.2 | $2 | 8,192 | 8192 |\n| moonshot/kimi-latest-32k | $1 | $3 | 32,768 | 32768 |\n| moonshot/kimi-latest-128k | $2 | $5 | 131,072 | 131072 |\n| moonshot/kimi-thinking-preview | $30 | $30 | 131,072 | 131072 |\n| moonshot/moonshot-v1-8k-vision-preview | $0.2 | $2 | 8,192 | 8192 |\n| moonshot/moonshot-v1-32k-vision-preview | $1 | $3 | 32,768 | 32768 |\n| moonshot/moonshot-v1-128k-vision-preview | $2 | $5 | 131,072 | 131072 |\n| groq/qwen/qwen3-32b | $0.29 | $0.59 | 131,000 | 131000 |\n| openrouter/qwen/qwen-vl-plus | $0.21 | $0.63 | 8,192 | 2048 |\n| fireworks_ai/accounts/fireworks/models/kimi-k2-instruct | $0.6 | $2.5 | 131,072 | 16384 |\n| lambda_ai/deepseek-llama3.3-70b | $0.2 | $0.6 | 131,072 | 131072 |\n| lambda_ai/deepseek-r1-0528 | $0.2 | $0.6 | 131,072 | 131072 |\n| lambda_ai/deepseek-r1-671b | $0.8 | $0.8 | 131,072 | 131072 |\n| lambda_ai/deepseek-v3-0324 | $0.2 | $0.6 | 131,072 | 131072 |\n| lambda_ai/hermes3-405b | $0.8 | $0.8 | 131,072 | 131072 |\n| lambda_ai/hermes3-70b | $0.12 | $0.3 | 131,072 | 131072 |\n| lambda_ai/hermes3-8b | $0.02 | $0.04 | 131,072 | 131072 |\n| lambda_ai/lfm-40b | $0.1 | $0.2 | 131,072 | 131072 |\n| lambda_ai/lfm-7b | $0.02 | $0.04 | 131,072 | 131072 |\n| lambda_ai/llama-4-maverick-17b-128e-instruct-fp8 | $0.05 | $0.1 | 131,072 | 8192 |\n| lambda_ai/llama-4-scout-17b-16e-instruct | $0.05 | $0.1 | 16,384 | 8192 |\n| lambda_ai/llama3.1-405b-instruct-fp8 | $0.8 | $0.8 | 131,072 | 131072 |\n| lambda_ai/llama3.1-70b-instruct-fp8 | $0.12 | $0.3 | 131,072 | 131072 |\n| lambda_ai/llama3.1-8b-instruct | $0.02 | $0.04 | 131,072 | 131072 |\n| lambda_ai/llama3.1-nemotron-70b-instruct-fp8 | $0.12 | $0.3 | 131,072 | 131072 |\n| lambda_ai/llama3.2-11b-vision-instruct | $0.02 | $0.02 | 131,072 | 131072 |\n| lambda_ai/llama3.2-3b-instruct | $0.02 | $0.02 | 131,072 | 131072 |\n| lambda_ai/llama3.3-70b-instruct-fp8 | $0.12 | $0.3 | 131,072 | 131072 |\n| lambda_ai/qwen25-coder-32b-instruct | $0.05 | $0.1 | 131,072 | 131072 |\n| lambda_ai/qwen3-32b-fp8 | $0.05 | $0.1 | 131,072 | 131072 |\n| recraft/recraftv3 | -- | -- | nan | nan |\n| recraft/recraftv2 | -- | -- | nan | nan |\n| morph/morph-v3-fast | $0.8 | $1.2 | 16,000 | 16000 |\n| morph/morph-v3-large | $0.9 | $1.9 | 16,000 | 16000 |\n| gemini/gemini-2.0-flash-live-001 | $0.35 | $1.5 | 1,048,576 | 65535 |\n| gemini-2.0-flash-live-preview-04-09 | $0.5 | $2 | 1,048,576 | 65535 |\n| vertex_ai/meta/llama-3.1-8b-instruct-maas | $0 | $0 | 128,000 | 2048 |\n| vertex_ai/meta/llama-3.1-70b-instruct-maas | $0 | $0 | 128,000 | 2048 |\n| vertex_ai/meta/llama-3.1-405b-instruct-maas | $5 | $16 | 128,000 | 2048 |\n| hyperbolic/moonshotai/Kimi-K2-Instruct | $2 | $2 | 131,072 | 131072 |\n| hyperbolic/deepseek-ai/DeepSeek-R1-0528 | $0.25 | $0.25 | 131,072 | 131072 |\n| hyperbolic/Qwen/Qwen3-235B-A22B | $2 | $2 | 131,072 | 131072 |\n| hyperbolic/deepseek-ai/DeepSeek-V3-0324 | $0.4 | $0.4 | 32,768 | 32768 |\n| hyperbolic/Qwen/QwQ-32B | $0.2 | $0.2 | 131,072 | 131072 |\n| hyperbolic/deepseek-ai/DeepSeek-R1 | $0.4 | $0.4 | 32,768 | 32768 |\n| hyperbolic/deepseek-ai/DeepSeek-V3 | $0.2 | $0.2 | 32,768 | 32768 |\n| hyperbolic/meta-llama/Llama-3.3-70B-Instruct | $0.12 | $0.3 | 131,072 | 131072 |\n| hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct | $0.12 | $0.3 | 32,768 | 32768 |\n| hyperbolic/meta-llama/Llama-3.2-3B-Instruct | $0.12 | $0.3 | 32,768 | 32768 |\n| hyperbolic/Qwen/Qwen2.5-72B-Instruct | $0.12 | $0.3 | 131,072 | 131072 |\n| hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct | $0.12 | $0.3 | 131,072 | 131072 |\n| hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B | $0.12 | $0.3 | 32,768 | 32768 |\n| hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct | $0.12 | $0.3 | 32,768 | 32768 |\n| hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct | $0.12 | $0.3 | 32,768 | 32768 |\n| hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct | $0.12 | $0.3 | 32,768 | 32768 |\n| gemini/gemini-2.5-flash-lite | $0.1 | $0.4 | 1,048,576 | 65535 |\n| gemini-2.5-flash-lite | $0.1 | $0.4 | 1,048,576 | 65535 |\n| gpt-4o-realtime-preview-2025-06-03 | $5 | $20 | 128,000 | 4096 |\n| openrouter/bytedance/ui-tars-1.5-7b | $0.1 | $0.2 | 131,072 | 2048 |\n| openrouter/qwen/qwen3-coder | $1 | $5 | 1,000,000 | 1e+06 |\n| openai/gpt-4o-realtime-preview-2025-06-03 | $5 | $20 | 128,000 | 4096 |\n| gemini/imagen-4.0-generate-preview-06-06 | -- | -- | nan | nan |\n| gemini/imagen-4.0-ultra-generate-preview-06-06 | -- | -- | nan | nan |\n| gemini/imagen-4.0-fast-generate-preview-06-06 | -- | -- | nan | nan |\n| gemini/imagen-3.0-generate-002 | -- | -- | nan | nan |\n| gemini/imagen-3.0-generate-001 | -- | -- | nan | nan |\n| gemini/imagen-3.0-fast-generate-001 | -- | -- | nan | nan |\n| openrouter/x-ai/grok-4 | $3 | $15 | 256,000 | 256000 |\n| claude-opus-4-1-20250805 | $15 | $75 | 200,000 | 32000 |\n| anthropic.claude-opus-4-1-20250805-v1:0 | $15 | $75 | 200,000 | 32000 |\n| us.anthropic.claude-opus-4-1-20250805-v1:0 | $15 | $75 | 200,000 | 32000 |\n| eu.anthropic.claude-opus-4-1-20250805-v1:0 | $15 | $75 | 200,000 | 32000 |\n| fireworks_ai/accounts/fireworks/models/glm-4p5 | $0.55 | $2.19 | 128,000 | 96000 |\n| fireworks_ai/accounts/fireworks/models/glm-4p5-air | $0.22 | $0.88 | 128,000 | 96000 |\n| fireworks_ai/accounts/fireworks/models/gpt-oss-120b | $0.15 | $0.6 | 131,072 | 131072 |\n| fireworks_ai/accounts/fireworks/models/gpt-oss-20b | $0.05 | $0.2 | 131,072 | 131072 |\n| vertex_ai/claude-opus-4-1 | $15 | $75 | 200,000 | 4096 |\n| vertex_ai/claude-opus-4-1@20250805 | $15 | $75 | 200,000 | 4096 |\n| openai.gpt-oss-20b-1:0 | $0.07 | $0.3 | 128,000 | 128000 |\n| openai.gpt-oss-120b-1:0 | $0.15 | $0.6 | 128,000 | 128000 |\n| gpt-5 | $1.25 | $10 | 400,000 | 128000 |\n| gpt-5-mini | $0.25 | $2 | 400,000 | 128000 |\n| gpt-5-nano | $0.05 | $0.4 | 400,000 | 128000 |\n| gpt-5-chat | $1.25 | $10 | 400,000 | 128000 |\n| gpt-5-chat-latest | $1.25 | $10 | 400,000 | 128000 |\n| gpt-5-2025-08-07 | $1.25 | $10 | 400,000 | 128000 |\n| gpt-5-mini-2025-08-07 | $0.25 | $2 | 400,000 | 128000 |\n| gpt-5-nano-2025-08-07 | $0.05 | $0.4 | 400,000 | 128000 |\n| azure/gpt-5 | $1.25 | $10 | 272,000 | 128000 |\n| azure/gpt-5-2025-08-07 | $1.25 | $10 | 272,000 | 128000 |\n| azure/gpt-5-mini | $0.25 | $2 | 272,000 | 128000 |\n| azure/gpt-5-mini-2025-08-07 | $0.25 | $2 | 272,000 | 128000 |\n| azure/gpt-5-nano-2025-08-07 | $0.05 | $0.4 | 272,000 | 128000 |\n| azure/gpt-5-nano | $0.05 | $0.4 | 272,000 | 128000 |\n| azure/gpt-5-chat | $1.25 | $10 | 272,000 | 128000 |\n| azure/gpt-5-chat-latest | $1.25 | $10 | 272,000 | 128000 |\n| groq/openai/gpt-oss-20b | $0.1 | $0.5 | 131,072 | 32768 |\n| groq/openai/gpt-oss-120b | $0.15 | $0.75 | 131,072 | 32766 |\n| claude-opus-4-1 | $15 | $75 | 200,000 | 32000 |\n| oci/meta.llama-4-maverick-17b-128e-instruct-fp8 | $0.72 | $0.72 | 512,000 | 4000 |\n| oci/meta.llama-4-scout-17b-16e-instruct | $0.72 | $0.72 | 192,000 | 4000 |\n| oci/meta.llama-3.3-70b-instruct | $0.72 | $0.72 | 128,000 | 4000 |\n| oci/meta.llama-3.2-90b-vision-instruct | $2 | $2 | 128,000 | 4000 |\n| oci/meta.llama-3.1-405b-instruct | $10.68 | $10.68 | 128,000 | 4000 |\n| oci/xai.grok-4 | $3 | $0.15 | 128,000 | 128000 |\n| oci/xai.grok-3 | $3 | $0.15 | 131,072 | 131072 |\n| oci/xai.grok-3-mini | $0.3 | $0.5 | 131,072 | 131072 |\n| oci/xai.grok-3-fast | $5 | $25 | 131,072 | 131072 |\n| oci/xai.grok-3-mini-fast | $0.6 | $4 | 131,072 | 131072 |\n| openai/gpt-5 | $1.25 | $10 | 400,000 | 128000 |\n| openai/gpt-5-mini | $0.25 | $2 | 400,000 | 128000 |\n| openai/gpt-5-nano | $0.05 | $0.4 | 400,000 | 128000 |\n| openai/gpt-5-chat | $1.25 | $10 | 400,000 | 128000 |\n| openai/gpt-5-chat-latest | $1.25 | $10 | 400,000 | 128000 |\n| openai/gpt-5-2025-08-07 | $1.25 | $10 | 400,000 | 128000 |\n| openai/gpt-5-mini-2025-08-07 | $0.25 | $2 | 400,000 | 128000 |\n| openai/gpt-5-nano-2025-08-07 | $0.05 | $0.4 | 400,000 | 128000 |\n| cerebras/openai/gpt-oss-20b | $0.07 | $0.3 | 131,072 | 32768 |\n| cerebras/openai/gpt-oss-120b | $0.25 | $0.69 | 131,072 | 32768 |\n| openrouter/openai/gpt-oss-20b | $0.18 | $0.8 | 131,072 | 32768 |\n| openrouter/openai/gpt-oss-120b | $0.18 | $0.8 | 131,072 | 32768 |\n| gradient_ai/anthropic-claude-3.7-sonnet | $3 | $15 | nan | nan |\n| gradient_ai/anthropic-claude-3.5-sonnet | $3 | $15 | nan | nan |\n| gradient_ai/anthropic-claude-3.5-haiku | $0.8 | $4 | nan | nan |\n| gradient_ai/anthropic-claude-3-opus | $15 | $75 | nan | nan |\n| gradient_ai/deepseek-r1-distill-llama-70b | $0.99 | $0.99 | nan | nan |\n| gradient_ai/llama3.3-70b-instruct | $0.65 | $0.65 | nan | nan |\n| gradient_ai/llama3-8b-instruct | $0.2 | $0.2 | nan | nan |\n| gradient_ai/mistral-nemo-instruct-2407 | $0.3 | $0.3 | nan | nan |\n| gradient_ai/openai-o3 | $2 | $8 | nan | nan |\n| gradient_ai/openai-o3-mini | $1.1 | $4.4 | nan | nan |\n| gradient_ai/openai-gpt-4o | -- | -- | nan | nan |\n| gradient_ai/openai-gpt-4o-mini | -- | -- | nan | nan |\n| gradient_ai/alibaba-qwen3-32b | -- | -- | nan | nan |\n| vertex_ai/deepseek-ai/deepseek-r1-0528-maas | $1.35 | $5.4 | 65,336 | 8192 |\n| azure_ai/FLUX-1.1-pro | -- | -- | nan | nan |\n| azure_ai/FLUX.1-Kontext-pro | -- | -- | nan | nan |\n| openrouter/deepseek/deepseek-chat-v3-0324 | $0.14 | $0.28 | 65,536 | 8192 |\n| vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas | $1 | $4 | 262,144 | 32768 |\n| vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas | $0.25 | $1 | 262,144 | 16384 |\n| together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput | $0.2 | $6 | 262,000 | nan |\n| together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 | $2 | $2 | 256,000 | nan |\n| together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507 | $0.65 | $3 | 256,000 | nan |\n| together_ai/Qwen/Qwen3-235B-A22B-fp8-tput | $0.2 | $0.6 | 40,000 | nan |\n| together_ai/deepseek-ai/DeepSeek-R1-0528-tput | $0.55 | $2.19 | 128,000 | nan |\n| together_ai/openai/gpt-oss-120b | $0.15 | $0.6 | 128,000 | nan |\n| together_ai/OpenAI/gpt-oss-20B | $0.05 | $0.2 | 128,000 | nan |\n| together_ai/zai-org/GLM-4.5-Air-FP8 | $0.2 | $1.1 | 128,000 | nan |\n| fireworks_ai/accounts/fireworks/models/deepseek-v3-0324 | $0.9 | $0.9 | 163,840 | 163840 |\n| vertex_ai/imagen-4.0-generate-001 | -- | -- | nan | nan |\n| vertex_ai/imagen-4.0-ultra-generate-001 | -- | -- | nan | nan |\n| vertex_ai/imagen-4.0-fast-generate-001 | -- | -- | nan | nan |\n| gemini/imagen-4.0-generate-001 | -- | -- | nan | nan |\n| gemini/imagen-4.0-ultra-generate-001 | -- | -- | nan | nan |\n| gemini/imagen-4.0-fast-generate-001 | -- | -- | nan | nan |\n| deepinfra/deepseek-ai/DeepSeek-V3 | $0.38 | $0.89 | 163,840 | 163840 |\n| deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | $0.02 | $0.02 | 131,072 | 131072 |\n| deepinfra/google/gemma-2-9b-it | $0.03 | $0.06 | 8,192 | 8192 |\n| deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo | $1 | $3 | 32,768 | 32768 |\n| deepinfra/Qwen/Qwen2-7B-Instruct | $0.06 | $0.06 | 32,768 | 32768 |\n| deepinfra/Qwen/QVQ-72B-Preview | $0.25 | $0.5 | 32,000 | 32000 |\n| deepinfra/meta-llama/Llama-3.3-70B-Instruct | $0.23 | $0.4 | 131,072 | 131072 |\n| deepinfra/microsoft/Phi-4-multimodal-instruct | $0.05 | $0.1 | 131,072 | 131072 |\n| deepinfra/mistralai/Devstral-Small-2507 | $0.07 | $0.28 | 128,000 | 128000 |\n| deepinfra/microsoft/WizardLM-2-7B | $0.06 | $0.06 | 32,768 | 32768 |\n| deepinfra/meta-llama/Llama-3.2-90B-Vision-Instruct | $0.35 | $0.4 | 32,768 | 32768 |\n| deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506 | $0.05 | $0.1 | 128,000 | 128000 |\n| deepinfra/deepseek-ai/DeepSeek-V3-0324 | $0.28 | $0.88 | 163,840 | 163840 |\n| deepinfra/anthropic/claude-3-7-sonnet-latest | $3.3 | $16.5 | 200,000 | 200000 |\n| deepinfra/cognitivecomputations/dolphin-2.9.1-llama-3-70b | $0.35 | $0.4 | 8,192 | 8192 |\n| deepinfra/Qwen/Qwen2.5-Coder-32B-Instruct | $0.06 | $0.15 | 32,768 | 32768 |\n| deepinfra/Qwen/Qwen3-235B-A22B | $0.13 | $0.6 | 40,960 | 40960 |\n| deepinfra/deepseek-ai/DeepSeek-V3-0324-Turbo | $1 | $3 | 32,768 | 32768 |\n| deepinfra/microsoft/WizardLM-2-8x22B | $0.48 | $0.48 | 65,536 | 65536 |\n| deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo | $0.02 | $0.05 | 8,192 | 8192 |\n| deepinfra/meta-llama/Llama-Guard-4-12B | $0.18 | $0.18 | 163,840 | 163840 |\n| deepinfra/meta-llama/Llama-3.2-1B-Instruct | $0 | $0.01 | 131,072 | 131072 |\n| deepinfra/google/gemma-2-27b-it | $0.27 | $0.27 | 8,192 | 8192 |\n| deepinfra/Qwen/Qwen2.5-VL-32B-Instruct | $0.2 | $0.6 | 128,000 | 128000 |\n| deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct | $0.12 | $0.3 | 131,072 | 131072 |\n| deepinfra/mistralai/Mixtral-8x22B-Instruct-v0.1 | $0.65 | $0.65 | 65,536 | 65536 |\n| deepinfra/Qwen/Qwen2.5-7B-Instruct | $0.04 | $0.1 | 32,768 | 32768 |\n| deepinfra/google/gemini-1.5-flash-8b | $0.04 | $0.15 | 1,000,000 | 1e+06 |\n| deepinfra/NousResearch/Hermes-3-Llama-3.1-70B | $0.1 | $0.28 | 131,072 | 131072 |\n| deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B | $0.1 | $0.4 | 131,072 | 131072 |\n| deepinfra/meta-llama/Llama-Guard-3-8B | $0.06 | $0.06 | 131,072 | 131072 |\n| deepinfra/mistralai/Mistral-Small-24B-Instruct-2501 | $0.05 | $0.08 | 32,768 | 32768 |\n| deepinfra/anthropic/claude-4-opus | $16.5 | $82.5 | 200,000 | 200000 |\n| deepinfra/openchat/openchat-3.6-8b | $0.06 | $0.06 | 8,192 | 8192 |\n| deepinfra/google/gemma-3-27b-it | $0.09 | $0.17 | 131,072 | 131072 |\n| deepinfra/Austism/chronos-hermes-13b-v2 | $0.13 | $0.13 | 4,096 | 4096 |\n| deepinfra/Sao10K/L3.1-70B-Euryale-v2.2 | $0.65 | $0.75 | 131,072 | 131072 |\n| deepinfra/Qwen/QwQ-32B-Preview | $0.12 | $0.18 | 32,768 | 32768 |\n| deepinfra/anthropic/claude-4-sonnet | $3.3 | $16.5 | 200,000 | 200000 |\n| deepinfra/microsoft/Phi-3-medium-4k-instruct | $0.14 | $0.14 | 4,096 | 4096 |\n| deepinfra/mattshumer/Reflection-Llama-3.1-70B | $0.35 | $0.4 | 8,192 | 8192 |\n| deepinfra/Sao10K/L3.3-70B-Euryale-v2.3 | $0.65 | $0.75 | 131,072 | 131072 |\n| deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct | $0.23 | $0.4 | 131,072 | 131072 |\n| deepinfra/deepseek-ai/DeepSeek-V3.1 | $0.3 | $1 | 163,840 | 163840 |\n| deepinfra/Qwen/Qwen2.5-Coder-7B | $0.02 | $0.05 | 32,768 | 32768 |\n| deepinfra/deepseek-ai/DeepSeek-Prover-V2-671B | $0.5 | $2.18 | 163,840 | 163840 |\n| deepinfra/zai-org/GLM-4.5 | $0.55 | $2 | 131,072 | 131072 |\n| deepinfra/meta-llama/Llama-3.2-3B-Instruct | $0.01 | $0.02 | 131,072 | 131072 |\n| deepinfra/google/gemini-1.5-flash | $0.08 | $0.3 | 1,000,000 | 1e+06 |\n| deepinfra/KoboldAI/LLaMA2-13B-Tiefighter | $0.1 | $0.1 | 4,096 | 4096 |\n| deepinfra/google/gemini-2.5-pro | $0.88 | $7 | 1,000,000 | 1e+06 |\n| deepinfra/Qwen/Qwen3-30B-A3B | $0.08 | $0.29 | 40,960 | 40960 |\n| deepinfra/Qwen/QwQ-32B | $0.08 | $0.15 | 131,072 | 131072 |\n| deepinfra/moonshotai/Kimi-K2-Instruct | $0.5 | $2 | 131,072 | 131072 |\n| deepinfra/Sao10K/L3-70B-Euryale-v2.1 | $0.7 | $0.8 | 8,192 | 8192 |\n| deepinfra/microsoft/phi-4-reasoning-plus | $0.07 | $0.35 | 32,768 | 32768 |\n| deepinfra/google/gemma-3-12b-it | $0.05 | $0.1 | 131,072 | 131072 |\n| deepinfra/google/gemini-2.5-flash | $0.21 | $1.75 | 1,000,000 | 1e+06 |\n| deepinfra/deepseek-ai/DeepSeek-R1 | $0.45 | $2.15 | 163,840 | 163840 |\n| deepinfra/mistralai/Mistral-7B-Instruct-v0.3 | $0.03 | $0.05 | 32,768 | 32768 |\n| deepinfra/Qwen/Qwen2.5-72B-Instruct | $0.12 | $0.39 | 32,768 | 32768 |\n| deepinfra/Qwen/Qwen3-14B | $0.06 | $0.24 | 40,960 | 40960 |\n| deepinfra/allenai/olmOCR-7B-0725-FP8 | $0.27 | $1.5 | 16,384 | 16384 |\n| deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct | $0.4 | $1.6 | 262,144 | 262144 |\n| deepinfra/microsoft/phi-4 | $0.07 | $0.14 | 16,384 | 16384 |\n| deepinfra/NousResearch/Hermes-3-Llama-3.1-405B | $0.7 | $0.8 | 131,072 | 131072 |\n| deepinfra/zai-org/GLM-4.5-Air | $0.2 | $1.1 | 131,072 | 131072 |\n| deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | $0.08 | $0.15 | 131,072 | 131072 |\n| deepinfra/openai/gpt-oss-120b | $0.09 | $0.45 | 131,072 | 131072 |\n| deepinfra/google/codegemma-7b-it | $0.07 | $0.07 | 8,192 | 8192 |\n| deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo | $0.3 | $1.2 | 262,144 | 262144 |\n| deepinfra/mistralai/Mistral-Nemo-Instruct-2407 | $0.02 | $0.04 | 131,072 | 131072 |\n| deepinfra/openbmb/MiniCPM-Llama3-V-2_5 | $0.34 | $0.34 | 8,192 | 8192 |\n| deepinfra/bigcode/starcoder2-15b-instruct-v0.1 | $0.15 | $0.15 | 4,096 | 4096 |\n| deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | $0.15 | $0.6 | 1,048,576 | 1.04858e+06 |\n| deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct | $0.08 | $0.3 | 327,680 | 327680 |\n| deepinfra/google/gemini-2.0-flash-001 | $0.1 | $0.4 | 1,000,000 | 1e+06 |\n| deepinfra/Gryphe/MythoMax-L2-13b-turbo | $0.13 | $0.13 | 4,096 | 4096 |\n| deepinfra/google/gemma-1.1-7b-it | $0.07 | $0.07 | 8,192 | 8192 |\n| deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | $0.1 | $0.28 | 131,072 | 131072 |\n| deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct | $0.03 | $0.05 | 131,072 | 131072 |\n| deepinfra/Qwen/Qwen3-32B | $0.1 | $0.3 | 40,960 | 40960 |\n| deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507 | $0.13 | $0.6 | 262,144 | 262144 |\n| deepinfra/nvidia/Nemotron-4-340B-Instruct | $4.2 | $4.2 | 4,096 | 4096 |\n| deepinfra/deepseek-ai/DeepSeek-R1-0528 | $0.5 | $2.15 | 163,840 | 163840 |\n| deepinfra/deepseek-ai/DeepSeek-R1-Turbo | $1 | $3 | 163,840 | 163840 |\n| deepinfra/NovaSky-AI/Sky-T1-32B-Preview | $0.12 | $0.18 | 32,768 | 32768 |\n| deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507 | $0.13 | $0.6 | 262,144 | 262144 |\n| deepinfra/mistralai/Mistral-Small-3.1-24B-Instruct-2503 | $0.05 | $0.1 | 128,000 | 128000 |\n| deepinfra/Qwen/Qwen2-72B-Instruct | $0.35 | $0.4 | 32,768 | 32768 |\n| deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-Turbo | $0.5 | $0.5 | 8,192 | 8192 |\n| deepinfra/Sao10K/L3-8B-Lunaris-v1 | $0.03 | $0.06 | 8,192 | 8192 |\n| deepinfra/google/gemma-3-4b-it | $0.02 | $0.04 | 131,072 | 131072 |\n| deepinfra/mistralai/Mistral-7B-Instruct-v0.2 | $0.06 | $0.06 | 32,768 | 32768 |\n| deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo | $0.04 | $0.12 | 131,072 | 131072 |\n| deepinfra/mistralai/Devstral-Small-2505 | $0.06 | $0.12 | 128,000 | 128000 |\n| deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct | $0.05 | $0.05 | 131,072 | 131072 |\n| deepinfra/openai/gpt-oss-20b | $0.04 | $0.16 | 131,072 | 131072 |\n| voyage/voyage-context-3 | $0.18 | $0 | 120,000 | nan |\n| openrouter/deepseek/deepseek-chat-v3.1 | $0.2 | $0.8 | 163,840 | 163840 |\n| aiml/flux/kontext-pro/text-to-image | -- | -- | nan | nan |\n| aiml/flux/kontext-max/text-to-image | -- | -- | nan | nan |\n| aiml/flux-pro/v1.1-ultra | -- | -- | nan | nan |\n| aiml/flux-pro/v1.1 | -- | -- | nan | nan |\n| aiml/flux-realism | -- | -- | nan | nan |\n| aiml/flux/schnell | -- | -- | nan | nan |\n| aiml/flux/dev | -- | -- | nan | nan |\n| aiml/flux-pro | -- | -- | nan | nan |\n| aiml/dall-e-3 | -- | -- | nan | nan |\n| aiml/dall-e-2 | -- | -- | nan | nan |\n| gemini/gemini-2.5-flash-image-preview | $0.3 | $2.5 | 1,048,576 | 65535 |\n| gemini-2.5-flash-image-preview | $0.3 | $2.5 | 1,048,576 | 65535 |\n| openrouter/anthropic/claude-opus-4 | $15 | $75 | 200,000 | 32000 |\n| openrouter/anthropic/claude-opus-4.1 | $15 | $75 | 200,000 | 32000 |\n| fireworks_ai/accounts/fireworks/models/deepseek-v3p1 | $0.56 | $1.68 | 128,000 | 8192 |\n| openrouter/openai/gpt-5-mini | $0.25 | $2 | 400,000 | 128000 |\n| openrouter/openai/gpt-5-nano | $0.05 | $0.4 | 400,000 | 128000 |\n| openrouter/openai/gpt-5-chat | $1.25 | $10 | 400,000 | 128000 |\n| xai/grok-code-fast-1 | $0.2 | $1.5 | 256,000 | 256000 |\n| xai/grok-code-fast | $0.2 | $1.5 | 256,000 | 256000 |\n| xai/grok-code-fast-1-0825 | $0.2 | $1.5 | 256,000 | 256000 |\n| gpt-realtime | $4 | $16 | 32,000 | 4096 |\n| gpt-realtime-2025-08-28 | $4 | $16 | 32,000 | 4096 |\n| vercel_ai_gateway/alibaba/qwen3-coder | $0.4 | $1.6 | 262,144 | 66536 |\n| vercel_ai_gateway/mistral/codestral-embed | $0.15 | $0 | 0 | 0 |\n| vercel_ai_gateway/google/gemini-2.5-pro | $2.5 | $10 | 1,048,576 | 65536 |\n| vercel_ai_gateway/deepseek/deepseek-v3 | $0.9 | $0.9 | 128,000 | 8192 |\n| vercel_ai_gateway/amazon/nova-lite | $0.06 | $0.24 | 300,000 | 8192 |\n| vercel_ai_gateway/meta/llama-4-scout | $0.1 | $0.3 | 131,072 | 8192 |\n| vercel_ai_gateway/meta/llama-3.2-1b | $0.1 | $0.1 | 128,000 | 8192 |\n| vercel_ai_gateway/mistral/mistral-small | $0.1 | $0.3 | 32,000 | 4000 |\n| vercel_ai_gateway/google/gemini-2.5-flash | $0.3 | $2.5 | 1,000,000 | 65536 |\n| vercel_ai_gateway/inception/mercury-coder-small | $0.25 | $1 | 32,000 | 16384 |\n| vercel_ai_gateway/openai/text-embedding-3-small | $0.02 | $0 | 0 | 0 |\n| vercel_ai_gateway/xai/grok-2-vision | $2 | $10 | 32,768 | 32768 |\n| vercel_ai_gateway/xai/grok-2 | $2 | $10 | 131,072 | 4000 |\n| vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b | $0.75 | $0.99 | 131,072 | 131072 |\n| vercel_ai_gateway/meta/llama-3.1-70b | $0.72 | $0.72 | 128,000 | 8192 |\n| vercel_ai_gateway/xai/grok-3 | $3 | $15 | 131,072 | 131072 |\n| vercel_ai_gateway/alibaba/qwen-3-235b | $0.2 | $0.6 | 40,960 | 16384 |\n| vercel_ai_gateway/xai/grok-3-fast | $5 | $25 | 131,072 | 131072 |\n| vercel_ai_gateway/vercel/v0-1.5-md | $3 | $15 | 128,000 | 32768 |\n| vercel_ai_gateway/openai/o4-mini | $1.1 | $4.4 | 200,000 | 100000 |\n| vercel_ai_gateway/mistral/magistral-medium | $2 | $5 | 128,000 | 64000 |\n| vercel_ai_gateway/amazon/titan-embed-text-v2 | $0.02 | $0 | 0 | 0 |\n| vercel_ai_gateway/alibaba/qwen-3-30b | $0.1 | $0.3 | 40,960 | 16384 |\n| vercel_ai_gateway/zai/glm-4.5-air | $0.2 | $1.1 | 128,000 | 96000 |\n| vercel_ai_gateway/openai/gpt-4-turbo | $10 | $30 | 128,000 | 4096 |\n| vercel_ai_gateway/mistral/mistral-large | $2 | $6 | 32,000 | 4000 |\n| vercel_ai_gateway/perplexity/sonar-pro | $3 | $15 | 200,000 | 8000 |\n| vercel_ai_gateway/meta/llama-3.2-90b | $0.72 | $0.72 | 128,000 | 8192 |\n| vercel_ai_gateway/meta/llama-3-8b | $0.05 | $0.08 | 8,192 | 8192 |\n| vercel_ai_gateway/google/text-embedding-005 | $0.02 | $0 | 0 | 0 |\n| vercel_ai_gateway/mistral/pixtral-large | $2 | $6 | 128,000 | 4000 |\n| vercel_ai_gateway/anthropic/claude-3.5-sonnet | $3 | $15 | 200,000 | 8192 |\n| vercel_ai_gateway/amazon/nova-micro | $0.04 | $0.14 | 128,000 | 8192 |\n| vercel_ai_gateway/cohere/command-r | $0.15 | $0.6 | 128,000 | 4096 |\n| vercel_ai_gateway/morph/morph-v3-large | $0.9 | $1.9 | 32,768 | 16384 |\n| vercel_ai_gateway/mistral/mixtral-8x22b-instruct | $1.2 | $1.2 | 65,536 | 2048 |\n| vercel_ai_gateway/xai/grok-4 | $3 | $15 | 256,000 | 256000 |\n| vercel_ai_gateway/meta/llama-3.1-8b | $0.05 | $0.08 | 131,000 | 131072 |\n| vercel_ai_gateway/anthropic/claude-3-opus | $15 | $75 | 200,000 | 4096 |\n| vercel_ai_gateway/zai/glm-4.5 | $0.6 | $2.2 | 131,072 | 131072 |\n| vercel_ai_gateway/openai/gpt-4o | $2.5 | $10 | 128,000 | 16384 |\n| vercel_ai_gateway/openai/o3-mini | $1.1 | $4.4 | 200,000 | 100000 |\n| vercel_ai_gateway/mistral/ministral-8b | $0.1 | $0.1 | 128,000 | 4000 |\n| vercel_ai_gateway/openai/o3 | $2 | $8 | 200,000 | 100000 |\n| vercel_ai_gateway/vercel/v0-1.0-md | $3 | $15 | 128,000 | 32000 |\n| vercel_ai_gateway/google/text-multilingual-embedding-002 | $0.02 | $0 | 0 | 0 |\n| vercel_ai_gateway/amazon/nova-pro | $0.8 | $3.2 | 300,000 | 8192 |\n| vercel_ai_gateway/morph/morph-v3-fast | $0.8 | $1.2 | 32,768 | 16384 |\n| vercel_ai_gateway/openai/gpt-3.5-turbo | $0.5 | $1.5 | 16,385 | 4096 |\n| vercel_ai_gateway/mistral/codestral | $0.3 | $0.9 | 256,000 | 4000 |\n| vercel_ai_gateway/meta/llama-3.2-11b | $0.16 | $0.16 | 128,000 | 8192 |\n| vercel_ai_gateway/meta/llama-3-70b | $0.59 | $0.79 | 8,192 | 8192 |\n| vercel_ai_gateway/xai/grok-3-mini-fast | $0.6 | $4 | 131,072 | 131072 |\n| vercel_ai_gateway/openai/text-embedding-3-large | $0.13 | $0 | 0 | 0 |\n| vercel_ai_gateway/google/gemini-2.0-flash-lite | $0.08 | $0.3 | 1,048,576 | 8192 |\n| vercel_ai_gateway/mistral/ministral-3b | $0.04 | $0.04 | 128,000 | 4000 |\n| vercel_ai_gateway/perplexity/sonar-reasoning-pro | $2 | $8 | 127,000 | 8000 |\n| vercel_ai_gateway/google/gemini-embedding-001 | $0.15 | $0 | 0 | 0 |\n| vercel_ai_gateway/anthropic/claude-3-haiku | $0.25 | $1.25 | 200,000 | 4096 |\n| vercel_ai_gateway/openai/o1 | $15 | $60 | 200,000 | 100000 |\n| vercel_ai_gateway/deepseek/deepseek-r1 | $0.55 | $2.19 | 128,000 | 8192 |\n| vercel_ai_gateway/mistral/mistral-embed | $0.1 | $0 | 0 | 0 |\n| vercel_ai_gateway/openai/gpt-4.1-mini | $0.4 | $1.6 | 1,047,576 | 32768 |\n| vercel_ai_gateway/openai/gpt-4o-mini | $0.15 | $0.6 | 128,000 | 16384 |\n| vercel_ai_gateway/alibaba/qwen-3-14b | $0.08 | $0.24 | 40,960 | 16384 |\n| vercel_ai_gateway/anthropic/claude-4-opus | $15 | $75 | 200,000 | 32000 |\n| vercel_ai_gateway/mistral/mistral-saba-24b | $0.79 | $0.79 | 32,768 | 32768 |\n| vercel_ai_gateway/perplexity/sonar-reasoning | $1 | $5 | 127,000 | 8000 |\n| vercel_ai_gateway/anthropic/claude-3.5-haiku | $0.8 | $4 | 200,000 | 8192 |\n| vercel_ai_gateway/cohere/command-a | $2.5 | $10 | 256,000 | 8000 |\n| vercel_ai_gateway/google/gemma-2-9b | $0.2 | $0.2 | 8,192 | 8192 |\n| vercel_ai_gateway/meta/llama-3.2-3b | $0.15 | $0.15 | 128,000 | 8192 |\n| vercel_ai_gateway/openai/gpt-4.1-nano | $0.1 | $0.4 | 1,047,576 | 32768 |\n| vercel_ai_gateway/anthropic/claude-4-sonnet | $3 | $15 | 200,000 | 64000 |\n| vercel_ai_gateway/perplexity/sonar | $1 | $1 | 127,000 | 8000 |\n| vercel_ai_gateway/meta/llama-4-maverick | $0.2 | $0.6 | 131,072 | 8192 |\n| vercel_ai_gateway/openai/text-embedding-ada-002 | $0.1 | $0 | 0 | 0 |\n| vercel_ai_gateway/xai/grok-3-mini | $0.3 | $0.5 | 131,072 | 131072 |\n| vercel_ai_gateway/cohere/embed-v4.0 | $0.12 | $0 | 0 | 0 |\n| vercel_ai_gateway/meta/llama-3.3-70b | $0.72 | $0.72 | 128,000 | 8192 |\n| vercel_ai_gateway/cohere/command-r-plus | $2.5 | $10 | 128,000 | 4096 |\n| vercel_ai_gateway/openai/gpt-3.5-turbo-instruct | $1.5 | $2 | 8,192 | 4096 |\n| vercel_ai_gateway/mistral/devstral-small | $0.07 | $0.28 | 128,000 | 128000 |\n| vercel_ai_gateway/anthropic/claude-3.7-sonnet | $3 | $15 | 200,000 | 64000 |\n| vercel_ai_gateway/google/gemini-2.0-flash | $0.15 | $0.6 | 1,048,576 | 8192 |\n| vercel_ai_gateway/mistral/pixtral-12b | $0.15 | $0.15 | 128,000 | 4000 |\n| vercel_ai_gateway/mistral/magistral-small | $0.5 | $1.5 | 128,000 | 64000 |\n| vercel_ai_gateway/moonshotai/kimi-k2 | $0.55 | $2.2 | 131,072 | 16384 |\n| vercel_ai_gateway/alibaba/qwen-3-32b | $0.1 | $0.3 | 40,960 | 16384 |\n| vercel_ai_gateway/openai/gpt-4.1 | $2 | $8 | 1,047,576 | 32768 |\n| openai/gpt-realtime | $4 | $16 | 32,000 | 4096 |\n| openai/gpt-realtime-2025-08-28 | $4 | $16 | 32,000 | 4096 |\n\n\u003c!-- PRICING_TABLE_END --\u003e","funding_links":[],"categories":["A01_文本生成_文本对话","Python","**Section 6** : Large Language Model: Challenges and Solutions"],"sub_categories":["大语言对话模型及数据","**Numbers LLM**"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FAgentOps-AI%2Ftokencost","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FAgentOps-AI%2Ftokencost","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FAgentOps-AI%2Ftokencost/lists"}