Models and providers
Pick the right model for each task.
Use a hosted model, a local server, or a gateway. Switch the provider or model whenever the work changes.
Set up your model connection
Save your key with codewhale auth set --provider <id>. In a session, pick the provider with /provider and the model with /model; local servers use the endpoint and authentication you configure.
Provider setup guides- DEEPSEEK_API_KEY
- DeepSeek · The default model is deepseek-flash. Connect your DeepSeek account with an API key.
- ollama · vllm · sglang
- Local models · Run models with Ollama, vLLM, or SGLang, then point Codewhale at the local endpoint.
- OPENROUTER_API_KEY
- OpenRouter · Reach models from several providers through one gateway. Choose OpenRouter, then pick a model.
Models in this release
Every model id the source declares for v0.10.2, merged across provider spellings. “Added” is the date the model first entered the source, not the provider’s release date. Sort any column; the default order is most recently added.
grok-4.7reasoning | xAI | 500K | Sep 23, 2026 |
|---|---|---|---|
step-3.5-flashreasoning | StepFun | 256K | Sep 19, 2026 |
step-3.5-flash-2603reasoning | StepFun | 256K | Sep 19, 2026 |
step-5-previewreasoning | StepFun | 1M | Sep 19, 2026 |
qwen3.5-flashreasoning | Qwen | — | Sep 9, 2026 |
glm-5.3-flashreasoning | Z.ai | 1M | Aug 27, 2026 |
qwen3.8-flashreasoning | Qwen | 1M | Aug 27, 2026 |
deepseek-v4-flash-vision-expreasoning | DeepSeek | 1M | Aug 21, 2026 |
claude-opus-5reasoning | Anthropic | 1M | Aug 17, 2026 |
gemini-3.7-flash | 1.05M | Aug 17, 2026 | |
kimi-k2.7-code-highspeedreasoning | Moonshot/Kimi | 262K | Aug 17, 2026 |
gemini-2.5-flash | 1.05M | Aug 14, 2026 | |
gemini-2.5-pro | 1.05M | Aug 14, 2026 | |
gemini-3-pro-preview | 1.05M | Aug 14, 2026 | |
gemini-3.1-pro-preview | 1.05M | Aug 14, 2026 | |
gemini-3.5-flash | 1.05M | Aug 14, 2026 | |
gemini-3.5-flash-lite | 1.05M | Aug 14, 2026 | |
gemini-3.6-flash | 1.05M | Aug 14, 2026 | |
grok-4.6reasoning | xAI | 500K | Aug 12, 2026 |
mistral-code-latest | Mistral | 256K | Aug 9, 2026 |
mistral-large-latest | Mistral | 262K | Aug 9, 2026 |
mistral-medium-latestreasoning | Mistral | 262K | Aug 8, 2026 |
mistral-small-latestreasoning | Mistral | 262K | Aug 8, 2026 |
muse-spark-1.2-contributorreasoning | Meta | 1M | Aug 6, 2026 |
muse-spark-1.2reasoning | Meta | 1M | Aug 5, 2026 |
glm-5.3reasoning | Z.ai | 1M | Aug 3, 2026 |
deepseek-flashreasoning | DeepSeek | 1M | Aug 2, 2026 |
qwen3.8-maxreasoning | Qwen | 1M | Aug 2, 2026 |
qwen3.8-max-previewreasoning | Qwen | 1M | Aug 2, 2026 |
kimi-for-coding-highspeedreasoning | Moonshot/Kimi | 262K | Jul 27, 2026 |
qwen3.5-plusreasoning | Qwen | — | Jul 26, 2026 |
kimi-k3reasoning | Moonshot/Kimi | 1.05M | Jul 17, 2026 |
thinkingmachines/inklingreasoning | Together | — | Jul 15, 2026 |
claude-fable-5reasoning | Anthropic | 1M | Jul 9, 2026 |
claude-sonnet-5reasoning | Anthropic | 1M | Jul 9, 2026 |
gpt-5.6reasoning | OpenAI | 1.05M | Jul 9, 2026 |
gpt-5.6-lunareasoning | OpenAI | 1.05M | Jul 9, 2026 |
gpt-5.6-solreasoning | OpenAI | 1.05M | Jul 9, 2026 |
gpt-5.6-terrareasoning | OpenAI | 1.05M | Jul 9, 2026 |
muse-spark-1.1reasoning | Meta | 1M | Jul 9, 2026 |
qwen3.7-plusreasoning | Qwen | 1M | Jul 9, 2026 |
grok-4.20-0309-non-reasoning | xAI | 2M | Jul 8, 2026 |
grok-4.20-0309-reasoningreasoning | xAI | 2M | Jul 8, 2026 |
grok-4.3reasoning | xAI | 1M | Jul 8, 2026 |
grok-4.5reasoning | xAI | 500K | Jul 8, 2026 |
grok-buildreasoning | xAI | 512K | Jul 8, 2026 |
grok-composer-2.5-fast | xAI | 200K | Jul 8, 2026 |
fugu-ultrareasoning | — | 1M | Jul 6, 2026 |
fugu-ultra-20260615reasoning | — | 1M | Jun 28, 2026 |
mimo-v2.5-pro-ultraspeedreasoning | Xiaomi MiMo | 1M | Jun 22, 2026 |
kimi-k2.5reasoning | Moonshot/Kimi | — | Jun 21, 2026 |
claude-haiku-4-5 | Anthropic | 200K | Jun 14, 2026 |
claude-opus-4-8reasoning | Anthropic | 1M | Jun 14, 2026 |
gpt-5-codexreasoning | OpenAI Codex | 400K | Jun 14, 2026 |
gpt-5.3-codexreasoning | OpenAI | 400K | Jun 14, 2026 |
gpt-5.5-proreasoning | OpenAI | 1.05M | Jun 14, 2026 |
glm-5.2reasoning | Z.ai | 1M | Jun 12, 2026 |
kimi-k2.7-codereasoning | Moonshot/Kimi | 262K | Jun 12, 2026 |
minimax-m2.7reasoning | MiniMax | 205K | Jun 12, 2026 |
minimax-m3reasoning | MiniMax | 1M | Jun 12, 2026 |
step-3.7-flashreasoning | StepFun | 256K | Jun 12, 2026 |
claude-sonnet-4-6reasoning | Anthropic | 1M | Jun 11, 2026 |
gpt-5.5reasoning | OpenAI | 1.05M | Jun 8, 2026 |
qwen3.6-flashreasoning | Qwen | 1M | Jun 2, 2026 |
qwen3.6-plusreasoning | Qwen | — | Jun 2, 2026 |
trinity-minireasoning | Arcee | 128K | Jun 2, 2026 |
glm-5.1reasoning | Z.ai | 203K | May 31, 2026 |
qwen3.6-35b-a3b | Qwen | — | May 31, 2026 |
qwen3.7-maxreasoning | Qwen | 1M | May 31, 2026 |
trinity-large-thinkingreasoning | Arcee | 262K | May 31, 2026 |
mimo-v2.5reasoning | Xiaomi MiMo | 1M | May 30, 2026 |
mimo-v2.5-proreasoning | Xiaomi MiMo | 1M | May 30, 2026 |
kimi-for-codingreasoning | Moonshot/Kimi | 262K | May 25, 2026 |
kimi-k2.6reasoning | Moonshot/Kimi | 262K | May 25, 2026 |
deepseek-coder:1.3b | DeepSeek | — | May 6, 2026 |
deepseek-v4-flashreasoning | DeepSeek | 1M | Apr 23, 2026 |
deepseek-v4-proreasoning | DeepSeek | 1M | Apr 23, 2026 |
deepseek-reasoner | DeepSeek | — | Mar 2, 2026 |
Supported providers
Providers declared in source v0.10.2. Run /provider to see the choices in your installed version; the setup guides cover credentials, endpoints, and model selection.
| Provider | Provider ID | Credential setting |
|---|---|---|
| DeepSeek | deepseek | DEEPSEEK_API_KEY |
| DeepSeek Anthropic | deepseek-anthropic | DEEPSEEK_API_KEY / ANTHROPIC_API_KEY |
| NVIDIA NIM | nvidia-nim | NVIDIA_API_KEY / NVIDIA_NIM_API_KEY |
| OpenAI-compatible | openai | OPENAI_API_KEY |
| AtlasCloud | atlascloud | ATLASCLOUD_API_KEY |
| Wanjie Ark | wanjie-ark | WANJIE_ARK_API_KEY / WANJIE_API_KEY / WANJIE_MAAS_API_KEY |
| Volcengine Ark | volcengine | VOLCENGINE_API_KEY / VOLCENGINE_ARK_API_KEY / ARK_API_KEY |
| OpenRouter | openrouter | OPENROUTER_API_KEY |
| OrcaRouter | orcarouter | ORCAROUTER_API_KEY |
| Xiaomi MiMo | xiaomi-mimo | XIAOMI_MIMO_TOKEN_PLAN_API_KEY / MIMO_TOKEN_PLAN_API_KEY / XIAOMI_MIMO_API_KEY / XIAOMI_API_KEY / MIMO_API_KEY |
| Novita AI | novita | NOVITA_API_KEY |
| Fireworks AI | fireworks | FIREWORKS_API_KEY |
| SiliconFlow | siliconflow | SILICONFLOW_API_KEY |
| SiliconFlow CN | siliconflow-CN | SILICONFLOW_API_KEY |
| Arcee AI | arcee | ARCEE_API_KEY |
| Moonshot/Kimi | moonshot | MOONSHOT_API_KEY / KIMI_API_KEY |
| SGLang | sglang | SGLANG_API_KEY |
| vLLM | vllm | VLLM_API_KEY |
| Ollama | ollama | OLLAMA_API_KEY |
| Ollama Cloud | ollama-cloud | OLLAMA_CLOUD_API_KEY / OLLAMA_API_KEY |
| Hugging Face | huggingface | HUGGINGFACE_API_KEY / HF_TOKEN |
| Together AI | together | TOGETHER_API_KEY |
| Baidu Qianfan | qianfan | QIANFAN_API_KEY / BAIDU_QIANFAN_API_KEY |
| OpenAI Codex | openai-codex | ChatGPT OAuth via `codewhale auth chatgpt`; optional consented Codex CLI credentials (OPENAI_CODEX_ACCESS_TOKEN / CODEX_ACCESS_TOKEN override) |
| Anthropic | anthropic | ANTHROPIC_API_KEY |
| OpenModel | openmodel | OPENMODEL_API_KEY |
| Z.ai | zai | ZAI_API_KEY / Z_AI_API_KEY |
| StepFun | stepfun | STEPFUN_API_KEY / STEP_API_KEY |
| MiniMax | minimax | MINIMAX_API_KEY |
| MiniMax (Anthropic-compatible) | minimax-anthropic | MINIMAX_API_KEY |
| DeepInfra | deepinfra | DEEPINFRA_API_KEY / DEEPINFRA_TOKEN |
| Sakana AI | sakana | FUGU_API_KEY / SAKANA_API_KEY |
| Meituan LongCat | longcat | LONGCAT_API_KEY |
| OpenCode Go | opencode-go | OPENCODE_GO_API_KEY |
| OpenCode Zen | opencode-zen | OPENCODE_ZEN_API_KEY / OPENCODE_API_KEY |
| Meta Model API | meta | META_MODEL_API_KEY / MODEL_API_KEY |
| xAI | xai | XAI_API_KEY |
| Mistral AI | mistral | MISTRAL_API_KEY |
| Google Gemini | google | GOOGLE_API_KEY / GEMINI_API_KEY |
| ModelScope | modelscope | MODELSCOPE_API_KEY |
| TelecomJS TokenHub | telecomjs | TELECOMJS_API_KEY |
| Eden AI | edenai | EDENAI_API_KEY |
| ZenMux | zenmux | ZENMUX_API_KEY |
| CSDN 星图 (Starmap) | csdn | CSDN_API_KEY |
| Concentrate | concentrate | CONCENTRATE_API_KEY |
| Codewhale | codewhale | CODEWHALE_API_KEY |
| Model Studio Token Plan | modelstudio-token-plan | MODELSTUDIO_API_KEY |
| Model Studio Token Plan (Anthropic-compatible) | modelstudio-token-plan-anthropic | MODELSTUDIO_API_KEY |
| Model Studio Coding Plan | modelstudio-coding-plan | MODELSTUDIO_API_KEY |
| Model Studio Coding Plan (Anthropic-compatible) | modelstudio-coding-plan-anthropic | MODELSTUDIO_API_KEY |
Missing your provider? Request support