{"id":14907086,"url":"https://github.com/cheahjs/free-llm-api-resources","last_synced_at":"2026-02-04T22:45:03.622Z","repository":{"id":257790745,"uuid":"824301644","full_name":"cheahjs/free-llm-api-resources","owner":"cheahjs","description":"A list of free LLM inference resources accessible via API.","archived":false,"fork":false,"pushed_at":"2026-01-28T00:34:16.000Z","size":366,"stargazers_count":8034,"open_issues_count":26,"forks_count":781,"subscribers_count":125,"default_branch":"main","last_synced_at":"2026-01-28T15:38:55.783Z","etag":null,"topics":["ai","claude","gemini","llama","llm","openai"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/cheahjs.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-07-04T20:10:17.000Z","updated_at":"2026-01-28T14:56:53.000Z","dependencies_parsed_at":"2025-11-28T02:06:28.384Z","dependency_job_id":null,"html_url":"https://github.com/cheahjs/free-llm-api-resources","commit_stats":null,"previous_names":["cheahjs/free-llm-api-resources"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/cheahjs/free-llm-api-resources","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cheahjs%2Ffree-llm-api-resources","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cheahjs%2Ffree-llm-api-resources/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cheahjs%2Ffree-llm-api-resources/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cheahjs%2Ffree-llm-api-resources/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cheahjs","download_url":"https://codeload.github.com/cheahjs/free-llm-api-resources/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cheahjs%2Ffree-llm-api-resources/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29098250,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-04T21:05:08.033Z","status":"ssl_error","status_checked_at":"2026-02-04T21:04:53.031Z","response_time":62,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["ai","claude","gemini","llama","llm","openai"],"created_at":"2024-09-22T16:01:12.754Z","updated_at":"2026-02-04T22:45:03.617Z","avatar_url":"https://github.com/cheahjs.png","language":"Python","funding_links":[],"categories":["A01_文本生成_文本对话","Repos","Python","Langchain","🗂️ GPTs Lists","🤖 AI \u0026 Machine Learning","🧠 AI Applications \u0026 Platforms","ai","Open-Source LLM \u0026 Agent Projects"],"sub_categories":["大语言对话模型及数据","Hall Of Fame:","Resources"],"readme":"\u003c!---\nWARNING: DO NOT EDIT THIS FILE DIRECTLY. IT IS GENERATED BY src/pull_available_models.py\n---\u003e\n# Free LLM API resources\n\nThis lists various services that provide free access or credits towards API-based LLM usage.\n\n\u003e [!NOTE]  \n\u003e Please don't abuse these services, else we might lose them.\n\n\u003e [!WARNING]  \n\u003e This list explicitly excludes any services that are not legitimate (eg reverse engineers an existing chatbot)\n\n- [Free Providers](#free-providers)\n  - [OpenRouter](#openrouter)\n  - [Google AI Studio](#google-ai-studio)\n  - [NVIDIA NIM](#nvidia-nim)\n  - [Mistral (La Plateforme)](#mistral-la-plateforme)\n  - [Mistral (Codestral)](#mistral-codestral)\n  - [HuggingFace Inference Providers](#huggingface-inference-providers)\n  - [Vercel AI Gateway](#vercel-ai-gateway)\n  - [Cerebras](#cerebras)\n  - [Groq](#groq)\n  - [Cohere](#cohere)\n  - [GitHub Models](#github-models)\n  - [Cloudflare Workers AI](#cloudflare-workers-ai)\n  - [Google Cloud Vertex AI](#google-cloud-vertex-ai)\n- [Providers with trial credits](#providers-with-trial-credits)\n  - [Fireworks](#fireworks)\n  - [Baseten](#baseten)\n  - [Nebius](#nebius)\n  - [Novita](#novita)\n  - [AI21](#ai21)\n  - [Upstage](#upstage)\n  - [NLP Cloud](#nlp-cloud)\n  - [Alibaba Cloud (International) Model Studio](#alibaba-cloud-international-model-studio)\n  - [Modal](#modal)\n  - [Inference.net](#inferencenet)\n  - [Hyperbolic](#hyperbolic)\n  - [SambaNova Cloud](#sambanova-cloud)\n  - [Scaleway Generative APIs](#scaleway-generative-apis)\n\n## Free Providers\n\n### [OpenRouter](https://openrouter.ai)\n\n**Limits:**\n\n[20 requests/minute\u003cbr\u003e50 requests/day\u003cbr\u003eUp to 1000 requests/day with $10 lifetime topup](https://openrouter.ai/docs/api-reference/limits)\n\nModels share a common quota.\n\n- [Gemma 3 12B Instruct](https://openrouter.ai/google/gemma-3-12b-it:free)\n- [Gemma 3 27B Instruct](https://openrouter.ai/google/gemma-3-27b-it:free)\n- [Gemma 3 4B Instruct](https://openrouter.ai/google/gemma-3-4b-it:free)\n- [Hermes 3 Llama 3.1 405B](https://openrouter.ai/nousresearch/hermes-3-llama-3.1-405b:free)\n- [Llama 3.1 405B Instruct](https://openrouter.ai/meta-llama/llama-3.1-405b-instruct:free)\n- [Llama 3.2 3B Instruct](https://openrouter.ai/meta-llama/llama-3.2-3b-instruct:free)\n- [Llama 3.3 70B Instruct](https://openrouter.ai/meta-llama/llama-3.3-70b-instruct:free)\n- [Mistral Small 3.1 24B Instruct](https://openrouter.ai/mistralai/mistral-small-3.1-24b-instruct:free)\n- [Qwen 2.5 VL 7B Instruct](https://openrouter.ai/qwen/qwen-2.5-vl-7b-instruct:free)\n- [allenai/molmo-2-8b:free](https://openrouter.ai/allenai/molmo-2-8b:free)\n- [arcee-ai/trinity-large-preview:free](https://openrouter.ai/arcee-ai/trinity-large-preview:free)\n- [arcee-ai/trinity-mini:free](https://openrouter.ai/arcee-ai/trinity-mini:free)\n- [cognitivecomputations/dolphin-mistral-24b-venice-edition:free](https://openrouter.ai/cognitivecomputations/dolphin-mistral-24b-venice-edition:free)\n- [deepseek/deepseek-r1-0528:free](https://openrouter.ai/deepseek/deepseek-r1-0528:free)\n- [google/gemma-3n-e2b-it:free](https://openrouter.ai/google/gemma-3n-e2b-it:free)\n- [google/gemma-3n-e4b-it:free](https://openrouter.ai/google/gemma-3n-e4b-it:free)\n- [liquid/lfm-2.5-1.2b-instruct:free](https://openrouter.ai/liquid/lfm-2.5-1.2b-instruct:free)\n- [liquid/lfm-2.5-1.2b-thinking:free](https://openrouter.ai/liquid/lfm-2.5-1.2b-thinking:free)\n- [moonshotai/kimi-k2:free](https://openrouter.ai/moonshotai/kimi-k2:free)\n- [nvidia/nemotron-3-nano-30b-a3b:free](https://openrouter.ai/nvidia/nemotron-3-nano-30b-a3b:free)\n- [nvidia/nemotron-nano-12b-v2-vl:free](https://openrouter.ai/nvidia/nemotron-nano-12b-v2-vl:free)\n- [nvidia/nemotron-nano-9b-v2:free](https://openrouter.ai/nvidia/nemotron-nano-9b-v2:free)\n- [openai/gpt-oss-120b:free](https://openrouter.ai/openai/gpt-oss-120b:free)\n- [openai/gpt-oss-20b:free](https://openrouter.ai/openai/gpt-oss-20b:free)\n- [qwen/qwen3-4b:free](https://openrouter.ai/qwen/qwen3-4b:free)\n- [qwen/qwen3-coder:free](https://openrouter.ai/qwen/qwen3-coder:free)\n- [qwen/qwen3-next-80b-a3b-instruct:free](https://openrouter.ai/qwen/qwen3-next-80b-a3b-instruct:free)\n- [tngtech/deepseek-r1t-chimera:free](https://openrouter.ai/tngtech/deepseek-r1t-chimera:free)\n- [tngtech/deepseek-r1t2-chimera:free](https://openrouter.ai/tngtech/deepseek-r1t2-chimera:free)\n- [tngtech/tng-r1t-chimera:free](https://openrouter.ai/tngtech/tng-r1t-chimera:free)\n- [upstage/solar-pro-3:free](https://openrouter.ai/upstage/solar-pro-3:free)\n- [z-ai/glm-4.5-air:free](https://openrouter.ai/z-ai/glm-4.5-air:free)\n\n### [Google AI Studio](https://aistudio.google.com)\n\nData is used for training when used outside of the UK/CH/EEA/EU.\n\n\u003ctable\u003e\u003cthead\u003e\u003ctr\u003e\u003cth\u003eModel Name\u003c/th\u003e\u003cth\u003eModel Limits\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\n\u003ctr\u003e\u003ctd\u003eGemini 3 Flash\u003c/td\u003e\u003ctd\u003e250,000 tokens/minute\u003cbr\u003e20 requests/day\u003cbr\u003e5 requests/minute\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eGemini 2.5 Flash\u003c/td\u003e\u003ctd\u003e250,000 tokens/minute\u003cbr\u003e20 requests/day\u003cbr\u003e5 requests/minute\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eGemini 2.5 Flash-Lite\u003c/td\u003e\u003ctd\u003e250,000 tokens/minute\u003cbr\u003e20 requests/day\u003cbr\u003e10 requests/minute\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eGemma 3 27B Instruct\u003c/td\u003e\u003ctd\u003e15,000 tokens/minute\u003cbr\u003e14,400 requests/day\u003cbr\u003e30 requests/minute\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eGemma 3 12B Instruct\u003c/td\u003e\u003ctd\u003e15,000 tokens/minute\u003cbr\u003e14,400 requests/day\u003cbr\u003e30 requests/minute\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eGemma 3 4B Instruct\u003c/td\u003e\u003ctd\u003e15,000 tokens/minute\u003cbr\u003e14,400 requests/day\u003cbr\u003e30 requests/minute\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eGemma 3 1B Instruct\u003c/td\u003e\u003ctd\u003e15,000 tokens/minute\u003cbr\u003e14,400 requests/day\u003cbr\u003e30 requests/minute\u003c/td\u003e\u003c/tr\u003e\n\u003c/tbody\u003e\u003c/table\u003e\n\n### [NVIDIA NIM](https://build.nvidia.com/explore/discover)\n\nPhone number verification required.\nModels tend to be context window limited.\n\n**Limits:** 40 requests/minute\n\n- [Various open models](https://build.nvidia.com/models)\n\n### [Mistral (La Plateforme)](https://console.mistral.ai/)\n\n* Free tier (Experiment plan) requires opting into data training\n* Requires phone number verification.\n\n**Limits (per-model):** 1 request/second, 500,000 tokens/minute, 1,000,000,000 tokens/month\n\n- [Open and Proprietary Mistral models](https://docs.mistral.ai/getting-started/models/models_overview/)\n\n### [Mistral (Codestral)](https://codestral.mistral.ai/)\n\n* Currently free to use\n* Monthly subscription based\n* Requires phone number verification\n\n**Limits:** 30 requests/minute, 2,000 requests/day\n\n- Codestral\n\n### [HuggingFace Inference Providers](https://huggingface.co/docs/inference-providers/en/index)\n\nHuggingFace Serverless Inference limited to models smaller than 10GB. Some popular models are supported even if they exceed 10GB.\n\n**Limits:** [$0.10/month in credits](https://huggingface.co/docs/inference-providers/en/pricing)\n\n- Various open models across supported providers\n\n### [Vercel AI Gateway](https://vercel.com/docs/ai-gateway)\n\nRoutes to various supported providers.\n\n**Limits:** [$5/month](https://vercel.com/docs/ai-gateway/pricing)\n\n\n### [Cerebras](https://cloud.cerebras.ai/)\n\n\u003ctable\u003e\u003cthead\u003e\u003ctr\u003e\u003cth\u003eModel Name\u003c/th\u003e\u003cth\u003eModel Limits\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\n\u003ctr\u003e\u003ctd\u003egpt-oss-120b\u003c/td\u003e\u003ctd\u003e30 requests/minute\u003cbr\u003e60,000 tokens/minute\u003cbr\u003e900 requests/hour\u003cbr\u003e1,000,000 tokens/hour\u003cbr\u003e14,400 requests/day\u003cbr\u003e1,000,000 tokens/day\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eQwen 3 235B A22B Instruct\u003c/td\u003e\u003ctd\u003e30 requests/minute\u003cbr\u003e60,000 tokens/minute\u003cbr\u003e900 requests/hour\u003cbr\u003e1,000,000 tokens/hour\u003cbr\u003e14,400 requests/day\u003cbr\u003e1,000,000 tokens/day\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eLlama 3.3 70B\u003c/td\u003e\u003ctd\u003e30 requests/minute\u003cbr\u003e64,000 tokens/minute\u003cbr\u003e900 requests/hour\u003cbr\u003e1,000,000 tokens/hour\u003cbr\u003e14,400 requests/day\u003cbr\u003e1,000,000 tokens/day\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eQwen 3 32B\u003c/td\u003e\u003ctd\u003e30 requests/minute\u003cbr\u003e64,000 tokens/minute\u003cbr\u003e900 requests/hour\u003cbr\u003e1,000,000 tokens/hour\u003cbr\u003e14,400 requests/day\u003cbr\u003e1,000,000 tokens/day\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eLlama 3.1 8B\u003c/td\u003e\u003ctd\u003e30 requests/minute\u003cbr\u003e60,000 tokens/minute\u003cbr\u003e900 requests/hour\u003cbr\u003e1,000,000 tokens/hour\u003cbr\u003e14,400 requests/day\u003cbr\u003e1,000,000 tokens/day\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eZ.ai GLM-4.6\u003c/td\u003e\u003ctd\u003e10 requests/minute\u003cbr\u003e60,000 tokens/minute\u003cbr\u003e100 requests/hour\u003cbr\u003e100,000 tokens/hour\u003cbr\u003e100 requests/day\u003cbr\u003e1,000,000 tokens/day\u003c/td\u003e\u003c/tr\u003e\n\u003c/tbody\u003e\u003c/table\u003e\n\n### [Groq](https://console.groq.com)\n\n\u003ctable\u003e\u003cthead\u003e\u003ctr\u003e\u003cth\u003eModel Name\u003c/th\u003e\u003cth\u003eModel Limits\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\n\u003ctr\u003e\u003ctd\u003eAllam 2 7B\u003c/td\u003e\u003ctd\u003e7,000 requests/day\u003cbr\u003e6,000 tokens/minute\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eLlama 3.1 8B\u003c/td\u003e\u003ctd\u003e14,400 requests/day\u003cbr\u003e6,000 tokens/minute\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eLlama 3.3 70B\u003c/td\u003e\u003ctd\u003e1,000 requests/day\u003cbr\u003e12,000 tokens/minute\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eLlama 4 Maverick 17B 128E Instruct\u003c/td\u003e\u003ctd\u003e1,000 requests/day\u003cbr\u003e6,000 tokens/minute\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eLlama 4 Scout Instruct\u003c/td\u003e\u003ctd\u003e1,000 requests/day\u003cbr\u003e30,000 tokens/minute\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eWhisper Large v3\u003c/td\u003e\u003ctd\u003e7,200 audio-seconds/minute\u003cbr\u003e2,000 requests/day\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eWhisper Large v3 Turbo\u003c/td\u003e\u003ctd\u003e7,200 audio-seconds/minute\u003cbr\u003e2,000 requests/day\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003ecanopylabs/orpheus-arabic-saudi\u003c/td\u003e\u003ctd\u003e\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003ecanopylabs/orpheus-v1-english\u003c/td\u003e\u003ctd\u003e\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003egroq/compound\u003c/td\u003e\u003ctd\u003e250 requests/day\u003cbr\u003e70,000 tokens/minute\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003egroq/compound-mini\u003c/td\u003e\u003ctd\u003e250 requests/day\u003cbr\u003e70,000 tokens/minute\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003emeta-llama/llama-guard-4-12b\u003c/td\u003e\u003ctd\u003e14,400 requests/day\u003cbr\u003e15,000 tokens/minute\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003emeta-llama/llama-prompt-guard-2-22m\u003c/td\u003e\u003ctd\u003e\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003emeta-llama/llama-prompt-guard-2-86m\u003c/td\u003e\u003ctd\u003e\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003emoonshotai/kimi-k2-instruct\u003c/td\u003e\u003ctd\u003e1,000 requests/day\u003cbr\u003e10,000 tokens/minute\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003emoonshotai/kimi-k2-instruct-0905\u003c/td\u003e\u003ctd\u003e1,000 requests/day\u003cbr\u003e10,000 tokens/minute\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eopenai/gpt-oss-120b\u003c/td\u003e\u003ctd\u003e1,000 requests/day\u003cbr\u003e8,000 tokens/minute\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eopenai/gpt-oss-20b\u003c/td\u003e\u003ctd\u003e1,000 requests/day\u003cbr\u003e8,000 tokens/minute\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eopenai/gpt-oss-safeguard-20b\u003c/td\u003e\u003ctd\u003e1,000 requests/day\u003cbr\u003e8,000 tokens/minute\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eqwen/qwen3-32b\u003c/td\u003e\u003ctd\u003e1,000 requests/day\u003cbr\u003e6,000 tokens/minute\u003c/td\u003e\u003c/tr\u003e\n\u003c/tbody\u003e\u003c/table\u003e\n\n### [Cohere](https://cohere.com)\n\n**Limits:**\n\n[20 requests/minute\u003cbr\u003e1,000 requests/month](https://docs.cohere.com/docs/rate-limits)\n\nModels share a common monthly quota.\n\n- c4ai-aya-expanse-32b\n- c4ai-aya-expanse-8b\n- c4ai-aya-vision-32b\n- c4ai-aya-vision-8b\n- command-a-03-2025\n- command-a-reasoning-08-2025\n- command-a-translate-08-2025\n- command-a-vision-07-2025\n- command-r-08-2024\n- command-r-plus-08-2024\n- command-r7b-12-2024\n- command-r7b-arabic-02-2025\n\n### [GitHub Models](https://github.com/marketplace/models)\n\nExtremely restrictive input/output token limits.\n\n**Limits:** [Dependent on Copilot subscription tier (Free/Pro/Pro+/Business/Enterprise)](https://docs.github.com/en/github-models/prototyping-with-ai-models#rate-limits)\n\n- AI21 Jamba 1.5 Large\n- Codestral 25.01\n- Cohere Command A\n- Cohere Command R 08-2024\n- Cohere Command R+ 08-2024\n- DeepSeek-R1\n- DeepSeek-R1-0528\n- DeepSeek-V3-0324\n- Grok 3\n- Grok 3 Mini\n- Llama 4 Maverick 17B 128E Instruct FP8\n- Llama 4 Scout 17B 16E Instruct\n- Llama-3.2-11B-Vision-Instruct\n- Llama-3.2-90B-Vision-Instruct\n- Llama-3.3-70B-Instruct\n- MAI-DS-R1\n- Meta-Llama-3.1-405B-Instruct\n- Meta-Llama-3.1-8B-Instruct\n- Ministral 3B\n- Mistral Medium 3 (25.05)\n- Mistral Small 3.1\n- OpenAI GPT-4.1\n- OpenAI GPT-4.1-mini\n- OpenAI GPT-4.1-nano\n- OpenAI GPT-4o\n- OpenAI GPT-4o mini\n- OpenAI Text Embedding 3 (large)\n- OpenAI Text Embedding 3 (small)\n- OpenAI gpt-5\n- OpenAI gpt-5-chat (preview)\n- OpenAI gpt-5-mini\n- OpenAI gpt-5-nano\n- OpenAI o1\n- OpenAI o1-mini\n- OpenAI o1-preview\n- OpenAI o3\n- OpenAI o3-mini\n- OpenAI o4-mini\n- Phi-4\n- Phi-4-mini-instruct\n- Phi-4-mini-reasoning\n- Phi-4-multimodal-instruct\n- Phi-4-reasoning\n\n### [Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai)\n\n**Limits:** [10,000 neurons/day](https://developers.cloudflare.com/workers-ai/platform/pricing/#free-allocation)\n\n- @cf/aisingapore/gemma-sea-lion-v4-27b-it\n- @cf/ibm-granite/granite-4.0-h-micro\n- @cf/openai/gpt-oss-120b\n- @cf/openai/gpt-oss-20b\n- @cf/qwen/qwen3-30b-a3b-fp8\n- DeepSeek R1 Distill Qwen 32B\n- Deepseek Coder 6.7B Base (AWQ)\n- Deepseek Coder 6.7B Instruct (AWQ)\n- Deepseek Math 7B Instruct\n- Discolm German 7B v1 (AWQ)\n- Falcom 7B Instruct\n- Gemma 2B Instruct (LoRA)\n- Gemma 3 12B Instruct\n- Gemma 7B Instruct\n- Gemma 7B Instruct (LoRA)\n- Hermes 2 Pro Mistral 7B\n- Llama 2 13B Chat (AWQ)\n- Llama 2 7B Chat (FP16)\n- Llama 2 7B Chat (INT8)\n- Llama 2 7B Chat (LoRA)\n- Llama 3 8B Instruct\n- Llama 3 8B Instruct (AWQ)\n- Llama 3.1 8B Instruct (AWQ)\n- Llama 3.1 8B Instruct (FP8)\n- Llama 3.2 11B Vision Instruct\n- Llama 3.2 1B Instruct\n- Llama 3.2 3B Instruct\n- Llama 3.3 70B Instruct (FP8)\n- Llama 4 Scout Instruct\n- Llama Guard 3 8B\n- Mistral 7B Instruct v0.1\n- Mistral 7B Instruct v0.1 (AWQ)\n- Mistral 7B Instruct v0.2\n- Mistral 7B Instruct v0.2 (LoRA)\n- Mistral Small 3.1 24B Instruct\n- Neural Chat 7B v3.1 (AWQ)\n- OpenChat 3.5 0106\n- OpenHermes 2.5 Mistral 7B (AWQ)\n- Phi-2\n- Qwen 1.5 0.5B Chat\n- Qwen 1.5 1.8B Chat\n- Qwen 1.5 14B Chat (AWQ)\n- Qwen 1.5 7B Chat (AWQ)\n- Qwen 2.5 Coder 32B Instruct\n- Qwen QwQ 32B\n- SQLCoder 7B 2\n- Starling LM 7B Beta\n- TinyLlama 1.1B Chat v1.0\n- Una Cybertron 7B v2 (BF16)\n- Zephyr 7B Beta (AWQ)\n\n### [Google Cloud Vertex AI](https://console.cloud.google.com/vertex-ai/model-garden)\n\nVery stringent payment verification for Google Cloud.\n\n\u003ctable\u003e\u003cthead\u003e\u003ctr\u003e\u003cth\u003eModel Name\u003c/th\u003e\u003cth\u003eModel Limits\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\n\u003ctr\u003e\u003ctd\u003e\u003ca href=\"https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3-2-90b-vision-instruct-maas\" target=\"_blank\"\u003eLlama 3.2 90B Vision Instruct\u003c/a\u003e\u003c/td\u003e\u003ctd\u003e30 requests/minute\u003cbr\u003eFree during preview\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003e\u003ca href=\"https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3-1-405b-instruct-maas\" target=\"_blank\"\u003eLlama 3.1 70B Instruct\u003c/a\u003e\u003c/td\u003e\u003ctd\u003e60 requests/minute\u003cbr\u003eFree during preview\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003e\u003ca href=\"https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3-1-405b-instruct-maas\" target=\"_blank\"\u003eLlama 3.1 8B Instruct\u003c/a\u003e\u003c/td\u003e\u003ctd\u003e60 requests/minute\u003cbr\u003eFree during preview\u003c/td\u003e\u003c/tr\u003e\n\u003c/tbody\u003e\u003c/table\u003e\n\n\n\n## Providers with trial credits\n\n### [Fireworks](https://fireworks.ai/)\n\n**Credits:** $1\n\n**Models:** [Various open models](https://fireworks.ai/models)\n\n### [Baseten](https://app.baseten.co/)\n\n**Credits:** $30\n\n**Models:** [Any supported model - pay by compute time](https://www.baseten.co/library/)\n\n### [Nebius](https://studio.nebius.com/)\n\n**Credits:** $1\n\n**Models:** [Various open models](https://studio.nebius.ai/models)\n\n### [Novita](https://novita.ai/?ref=ytblmjc\u0026utm_source=affiliate)\n\n**Credits:** $0.5 for 1 year\n\n**Models:** [Various open models](https://novita.ai/models)\n\n### [AI21](https://studio.ai21.com/)\n\n**Credits:** $10 for 3 months\n\n**Models:** Jamba family of models\n\n### [Upstage](https://console.upstage.ai/)\n\n**Credits:** $10 for 3 months\n\n**Models:** Solar Pro/Mini\n\n### [NLP Cloud](https://nlpcloud.com/home)\n\n**Credits:** $15\n\n**Requirements:** Phone number verification\n\n**Models:** Various open models\n\n### [Alibaba Cloud (International) Model Studio](https://bailian.console.alibabacloud.com/)\n\n**Credits:** 1 million tokens/model\n\n**Models:** [Various open and proprietary Qwen models](https://www.alibabacloud.com/en/product/modelstudio)\n\n### [Modal](https://modal.com)\n\n**Credits:** $5/month upon sign up, $30/month with payment method added\n\n**Models:** Any supported model - pay by compute time\n\n### [Inference.net](https://inference.net)\n\n**Credits:** $1, $25 on responding to email survey\n\n**Models:** Various open models\n\n### [Hyperbolic](https://app.hyperbolic.xyz/)\n\n**Credits:** $1\n\n**Models:**\n- DeepSeek V3\n- DeepSeek V3 0324\n- Llama 3.1 405B Base\n- Llama 3.1 405B Instruct\n- Llama 3.1 70B Instruct\n- Llama 3.1 8B Instruct\n- Llama 3.2 3B Instruct\n- Llama 3.3 70B Instruct\n- Pixtral 12B (2409)\n- Qwen QwQ 32B\n- Qwen2.5 72B Instruct\n- Qwen2.5 Coder 32B Instruct\n- Qwen2.5 VL 72B Instruct\n- Qwen2.5 VL 7B Instruct\n- deepseek-ai/deepseek-r1-0528\n- openai/gpt-oss-120b\n- openai/gpt-oss-120b-turbo\n- openai/gpt-oss-20b\n- qwen/qwen3-235b-a22b\n- qwen/qwen3-235b-a22b-instruct-2507\n- qwen/qwen3-coder-480b-a35b-instruct\n- qwen/qwen3-next-80b-a3b-instruct\n- qwen/qwen3-next-80b-a3b-thinking\n\n### [SambaNova Cloud](https://cloud.sambanova.ai/)\n\n**Credits:** $5 for 3 months\n\n**Models:**\n- E5-Mistral-7B-Instruct\n- Llama 3.1 8B\n- Llama 3.3 70B\n- Llama 3.3 70B\n- Llama-4-Maverick-17B-128E-Instruct\n- Qwen/Qwen3-235B\n- Qwen/Qwen3-32B\n- Whisper-Large-v3\n- deepseek-ai/DeepSeek-R1-0528\n- deepseek-ai/DeepSeek-R1-Distill-Llama-70B\n- deepseek-ai/DeepSeek-V3-0324\n- deepseek-ai/DeepSeek-V3.1\n- deepseek-ai/DeepSeek-V3.1-Terminus\n- deepseek-ai/DeepSeek-V3.2\n- openai/gpt-oss-120b\n- tbd\n\n### [Scaleway Generative APIs](https://console.scaleway.com/generative-api/models)\n\n**Credits:** 1,000,000 free tokens\n\n**Models:**\n- BGE-Multilingual-Gemma2\n- DeepSeek R1 Distill Llama 70B\n- Gemma 3 27B Instruct\n- Llama 3.1 8B Instruct\n- Llama 3.3 70B Instruct\n- Mistral Nemo 2407\n- Pixtral 12B (2409)\n- Whisper Large v3\n- devstral-2-123b-instruct-2512\n- gpt-oss-120b\n- holo2-30b-a3b\n- mistral-small-3.2-24b-instruct-2506\n- qwen3-235b-a22b-instruct-2507\n- qwen3-coder-30b-a3b-instruct\n- qwen3-embedding-8b\n- voxtral-small-24b-2507\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcheahjs%2Ffree-llm-api-resources","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcheahjs%2Ffree-llm-api-resources","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcheahjs%2Ffree-llm-api-resources/lists"}