{"id":32848961,"url":"https://github.com/alorse/cc-compatible-models","last_synced_at":"2025-11-08T10:02:10.930Z","repository":{"id":322883596,"uuid":"1091294036","full_name":"Alorse/cc-compatible-models","owner":"Alorse","description":"Complete guide and pricing comparison for using alternative AI models with Claude Code - including DeepSeek, Qwen, Kimi K2, MiniMax, and GLM 4.6","archived":false,"fork":false,"pushed_at":"2025-11-06T20:29:23.000Z","size":4,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-11-06T22:21:45.912Z","etag":null,"topics":["ai-coding-assistant","ai-models","anthropic","api-integration","claude-code","deepseek","glm","kimi-k2","llm-comparison","llm-pricing","minimax","model-comparison","qwen"],"latest_commit_sha":null,"homepage":"","language":null,"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/Alorse.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":"2025-11-06T20:28:10.000Z","updated_at":"2025-11-06T20:32:28.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/Alorse/cc-compatible-models","commit_stats":null,"previous_names":["alorse/cc-compatible-models"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/Alorse/cc-compatible-models","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Alorse%2Fcc-compatible-models","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Alorse%2Fcc-compatible-models/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Alorse%2Fcc-compatible-models/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Alorse%2Fcc-compatible-models/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Alorse","download_url":"https://codeload.github.com/Alorse/cc-compatible-models/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Alorse%2Fcc-compatible-models/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":283333707,"owners_count":26818628,"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","status":"online","status_checked_at":"2025-11-08T02:00:06.281Z","response_time":57,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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-coding-assistant","ai-models","anthropic","api-integration","claude-code","deepseek","glm","kimi-k2","llm-comparison","llm-pricing","minimax","model-comparison","qwen"],"created_at":"2025-11-08T10:01:02.642Z","updated_at":"2025-11-08T10:02:10.923Z","avatar_url":"https://github.com/Alorse.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Claude Code-Compatible Models\n\nA comprehensive reference guide for developers looking to use Claude Code with cost-effective alternative AI providers. Includes up-to-date pricing, detailed setup instructions, and configuration examples for Anthropic, Alibaba Qwen, DeepSeek, MiniMax, Moonshot AI (Kimi K2), and Zhipu GLM models.\n\n\n| Provider | Model | Input $/1M tok | Output $/1M tok | Notes |\n|----------|-------|----------------|-----------------|-------|\n| Anthropic | Haiku 4.5 | $1.00 | $5.00 | Official API pricing. |\n| Anthropic | Opus 4.1 | $15.00 | $75.00 | Official API pricing. |\n| Anthropic | Sonnet 4.5 | $3.00 | $15.00 | Official API pricing. |\n| Alibaba | Qwen3 Coder | $0.22 | $0.95 | Uses Anthropic-compatible endpoint. |\n| DeepSeek | deepseek-chat | $0.28 | $0.42 | Context caching enabled by default. |\n| MiniMax | MiniMax-M2 | $0.30 | $1.20 | No prompt caching feature available. |\n| Moonshot AI | Kimi K2 | $0.14 | $2.49 | Automatic prompt caching (beta). |\n| Zhipu (ZAI) | GLM 4.6 | $0.60 | $2.20 | Subscription plan starts \"from $3/mo.\" |\n\n---\n\n## Provider Setup Guides\n\n### Anthropic (Official)\n\n**Installation:**\n```bash\nnpm install -g @anthropic-ai/claude-code\n# or on Unix systems:\ncurl -fsSL https://claude.ai/install.sh | bash\n```\n\n**Authentication:**\n\nThere are two main options:\n\n1. **Claude Console (OAuth)**: Requires active billing at [console.anthropic.com](https://console.anthropic.com). A \"Claude Code\" workspace is automatically created for usage tracking.\n\n2. **Claude.ai Subscription**: Subscribe to Claude Pro or Max plan and log in with your Claude.ai account.\n\n**Enterprise Options:**\n- Configure Claude Code to use Amazon Bedrock or Google Vertex AI with your existing cloud infrastructure.\n\n**Documentation:** [https://docs.claude.com/en/docs/claude-code/setup](https://docs.claude.com/en/docs/claude-code/setup)\n\n---\n\n### Alibaba - Qwen\n\n**Getting API Key:**\n1. Visit [Alibaba Cloud Model Studio](https://www.alibabacloud.com/help/en/model-studio)\n2. Create an account and generate a DashScope API key\n\n**Configuration:**\n\nEdit `~/.claude/settings.json`:\n\n```json\n{\n  \"env\": {\n    \"ANTHROPIC_BASE_URL\": \"https://dashscope-intl.aliyuncs.com/apps/anthropic\",\n    \"ANTHROPIC_AUTH_TOKEN\": \"YOUR_DASHSCOPE_API_KEY\",\n    \"ANTHROPIC_MODEL\": \"qwen-plus\",\n    \"ANTHROPIC_SMALL_FAST_MODEL\": \"qwen-flash\"\n  }\n}\n```\n\n**Recommended Model Combinations:**\n- **Main Model** (`ANTHROPIC_MODEL`): `qwen-max`, `qwen-plus`, or Qwen-Coder series for complex tasks\n- **Fast Model** (`ANTHROPIC_SMALL_FAST_MODEL`): `qwen-flash` or `qwen-turbo` for simple jobs\n\n**Launch:**\n```bash\ncd your-project-directory\nclaude\n```\n\n**Documentation:** [https://www.alibabacloud.com/help/en/model-studio/claude-code](https://www.alibabacloud.com/help/en/model-studio/claude-code)\n\n---\n\n### DeepSeek\n\n**Getting API Key:**\nVisit [DeepSeek Platform](https://platform.deepseek.com) to obtain your API key.\n\n**Configuration:**\n\nEdit `~/.claude/settings.json`:\n\n```json\n{\n  \"env\": {\n    \"ANTHROPIC_BASE_URL\": \"https://api.deepseek.com/anthropic\",\n    \"ANTHROPIC_AUTH_TOKEN\": \"YOUR_DEEPSEEK_API_KEY\",\n    \"API_TIMEOUT_MS\": \"600000\",\n    \"ANTHROPIC_MODEL\": \"deepseek-chat\",\n    \"ANTHROPIC_SMALL_FAST_MODEL\": \"deepseek-chat\",\n    \"CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC\": \"1\"\n  }\n}\n```\n\n**Using DeepSeek Reasoner (R1):**\nReplace `deepseek-chat` with `deepseek-reasoner` in the configuration above.\n\n**Launch:**\n```bash\ncd your-project-directory\nclaude\n```\n\n**Troubleshooting:**\n- Invalid token error: Verify `ANTHROPIC_AUTH_TOKEN` is set to your real DeepSeek API key\n- No response: Confirm `ANTHROPIC_BASE_URL` is correct: `https://api.deepseek.com/anthropic`\n\n**Documentation:** [https://api-docs.deepseek.com/guides/anthropic_api](https://api-docs.deepseek.com/guides/anthropic_api)\n\n---\n\n### MiniMax\n\n**Getting API Key:**\n1. Visit [MiniMax Developer Platform](https://platform.minimax.io)\n2. Navigate to the interface key section\n3. Create a new secret key with a project name\n4. Copy and save the key securely (shown only once)\n\n**Configuration:**\n\nEdit `~/.claude/settings.json`:\n\n```json\n{\n  \"env\": {\n    \"ANTHROPIC_BASE_URL\": \"https://api.minimax.io/anthropic\",\n    \"ANTHROPIC_AUTH_TOKEN\": \"YOUR_MINIMAX_API_KEY\",\n    \"API_TIMEOUT_MS\": \"3000000\",\n    \"ANTHROPIC_MODEL\": \"MiniMax-M2\",\n    \"ANTHROPIC_SMALL_FAST_MODEL\": \"MiniMax-M2\",\n    \"ANTHROPIC_DEFAULT_SONNET_MODEL\": \"MiniMax-M2\",\n    \"ANTHROPIC_DEFAULT_OPUS_MODEL\": \"MiniMax-M2\",\n    \"ANTHROPIC_DEFAULT_HAIKU_MODEL\": \"MiniMax-M2\",\n    \"CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC\": \"1\"\n  }\n}\n```\n\n**Launch:**\n```bash\ncd your-project-directory\nclaude\n```\n\n**Documentation:** [https://platform.minimax.io/docs/guides/text-ai-coding-tools](https://platform.minimax.io/docs/guides/text-ai-coding-tools)\n\n---\n\n### Moonshot AI - Kimi K2\n\n**Getting API Key:**\n1. Visit [Moonshot Platform](https://platform.moonshot.ai/)\n2. Create an account and generate an API key\n\n**Configuration:**\n\nEdit `~/.claude/settings.json`:\n\n```json\n{\n  \"env\": {\n    \"ANTHROPIC_BASE_URL\": \"https://api.moonshot.ai/anthropic\",\n    \"ANTHROPIC_AUTH_TOKEN\": \"YOUR_MOONSHOT_API_KEY\",\n    \"ANTHROPIC_MODEL\": \"kimi-k2-turbo-preview\",\n    \"ANTHROPIC_SMALL_FAST_MODEL\": \"kimi-k2-turbo-preview\"\n  }\n}\n```\n\n**Launch:**\n```bash\ncd your-project-directory\nclaude\n```\n\n**Features:**\n- 256K context length for handling complex codebases\n- Seamless Claude Code compatibility with agentic tool use\n- Automatic prompt caching (currently in 3-month public beta)\n\n**Documentation:** [https://platform.moonshot.ai/docs/guide/agent-support](https://platform.moonshot.ai/docs/guide/agent-support)\n\n---\n\n### Zhipu (ZAI) - GLM 4.6\n\n**Getting API Key:**\n1. Visit [Z.AI Platform](https://open.bigmodel.cn/) (Mainland China) or [api.z.ai](https://api.z.ai) (International)\n2. Create an account and generate an API key\n\n**Configuration:**\n\nEdit `~/.claude/settings.json`:\n\n```json\n{\n  \"env\": {\n    \"ANTHROPIC_BASE_URL\": \"https://api.z.ai/api/anthropic\",\n    \"ANTHROPIC_AUTH_TOKEN\": \"YOUR_ZAI_API_KEY\",\n    \"ANTHROPIC_DEFAULT_HAIKU_MODEL\": \"glm-4.5-air\",\n    \"ANTHROPIC_DEFAULT_SONNET_MODEL\": \"glm-4.6\",\n    \"ANTHROPIC_DEFAULT_OPUS_MODEL\": \"glm-4.6\"\n  }\n}\n```\n\n**For Mainland China:**\nReplace base URL with: `https://open.bigmodel.cn/api/anthropic`\n\n**Launch:**\n```bash\ncd your-project-directory\nclaude\n```\n\n**Documentation:** [https://docs.z.ai/scenario-example/develop-tools/claude](https://docs.z.ai/scenario-example/develop-tools/claude)\n\n---\n\n## General Tips\n\n1. **Version Check**: Ensure Claude Code is up to date with `claude --version` and update with `claude update`\n\n2. **Timeout Settings**: Some providers require higher timeout values (especially for complex reasoning tasks). The `API_TIMEOUT_MS` setting helps prevent premature timeouts.\n\n3. **Model Selection**: Most providers support automatic model selection based on task complexity using `ANTHROPIC_MODEL` (main) and `ANTHROPIC_SMALL_FAST_MODEL` (quick tasks).\n\n4. **Regional Considerations**: China-based providers often have separate endpoints for mainland China vs. international users.\n\n5. **Testing Configuration**: After setup, run `claude` in a test directory and verify the model responds correctly.\n\n6. **Cost Optimization**:\n   - Use cache-enabled providers (Anthropic, DeepSeek, Kimi) for repetitive tasks\n   - Select appropriate model sizes for the task complexity\n   - Consider batch processing for non-urgent workloads\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falorse%2Fcc-compatible-models","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falorse%2Fcc-compatible-models","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falorse%2Fcc-compatible-models/lists"}