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. On 2026-10-17 DeepSeek moved deepseek-flash to DeepSeek-V4.1-Flash-1017 at the same price, and Codewhale 0.10.1 runs it without an update. Connect with a DeepSeek 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 source v0.10.2

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.

Provider setup guides
Models in source v{version}
claude-fable-5-1reasoningAnthropic1M17 de out. de 2026
claude-haiku-5-5reasoningAnthropic1M17 de out. de 2026
claude-opus-5-5reasoningAnthropic1M17 de out. de 2026
claude-sonnet-5-5reasoningAnthropic1M17 de out. de 2026
gemini-3.8-flashGoogle1.05M17 de out. de 2026
gemini-4-argonGoogle1.05M17 de out. de 2026
gpt-6-lunareasoningOpenAI1.05M17 de out. de 2026
gpt-6-solreasoningOpenAI1.05M17 de out. de 2026
gpt-6.1-solreasoningOpenAI1.05M17 de out. de 2026
mimo-v2.6-flashreasoningXiaomi MiMo1.05M17 de out. de 2026
mimo-v2.6-proreasoningXiaomi MiMo1.05M17 de out. de 2026
muse-spark-1.3reasoningMeta1.05M17 de out. de 2026
muse-spark-1.3-contributorreasoningMeta1.05M17 de out. de 2026
muse-wonder-1.0reasoningMeta1.05M17 de out. de 2026
grok-4.7reasoningxAI500K23 de set. de 2026
step-3.5-flashreasoningStepFun256K19 de set. de 2026
step-3.5-flash-2603reasoningStepFun256K19 de set. de 2026
step-5-previewreasoningStepFun1M19 de set. de 2026
qwen3.5-flashreasoningQwen—9 de set. de 2026
glm-5.3-flashreasoningZ.ai1M27 de ago. de 2026
qwen3.8-flashreasoningQwen1M27 de ago. de 2026
deepseek-v4-flash-vision-expreasoningDeepSeek1M21 de ago. de 2026
claude-opus-5reasoningAnthropic1M17 de ago. de 2026
gemini-3.7-flashGoogle1.05M17 de ago. de 2026
kimi-k2.7-code-highspeedreasoningMoonshot/Kimi262K17 de ago. de 2026
gemini-2.5-flashGoogle1.05M14 de ago. de 2026
gemini-2.5-proGoogle1.05M14 de ago. de 2026
gemini-3-pro-previewGoogle1.05M14 de ago. de 2026
gemini-3.1-pro-previewGoogle1.05M14 de ago. de 2026
gemini-3.5-flashGoogle1.05M14 de ago. de 2026
gemini-3.5-flash-liteGoogle1.05M14 de ago. de 2026
gemini-3.6-flashGoogle1.05M14 de ago. de 2026
grok-4.6reasoningxAI500K12 de ago. de 2026
mistral-code-latestMistral256K9 de ago. de 2026
mistral-large-latestMistral262K9 de ago. de 2026
mistral-medium-latestreasoningMistral262K8 de ago. de 2026
mistral-small-latestreasoningMistral262K8 de ago. de 2026
muse-spark-1.2-contributorreasoningMeta1M6 de ago. de 2026
muse-spark-1.2reasoningMeta1M5 de ago. de 2026
glm-5.3reasoningZ.ai1M3 de ago. de 2026
deepseek-flashreasoningDeepSeek1M2 de ago. de 2026
qwen3.8-maxreasoningQwen1M2 de ago. de 2026
kimi-for-coding-highspeedreasoningMoonshot/Kimi262K27 de jul. de 2026
qwen3.5-plusreasoningQwen—26 de jul. de 2026
kimi-k3reasoningMoonshot/Kimi1.05M17 de jul. de 2026
thinkingmachines/inklingreasoningTogether—15 de jul. de 2026
claude-fable-5reasoningAnthropic1M9 de jul. de 2026
claude-sonnet-5reasoningAnthropic1M9 de jul. de 2026
gpt-5.6reasoningOpenAI1.05M9 de jul. de 2026
gpt-5.6-lunareasoningOpenAI1.05M9 de jul. de 2026
gpt-5.6-solreasoningOpenAI1.05M9 de jul. de 2026
gpt-5.6-terrareasoningOpenAI1.05M9 de jul. de 2026
muse-spark-1.1reasoningMeta1M9 de jul. de 2026
qwen3.7-plusreasoningQwen1M9 de jul. de 2026
grok-4.20-0309-non-reasoningxAI2M8 de jul. de 2026
grok-4.20-0309-reasoningreasoningxAI2M8 de jul. de 2026
grok-4.3reasoningxAI1M8 de jul. de 2026
grok-4.5reasoningxAI500K8 de jul. de 2026
grok-buildreasoningxAI512K8 de jul. de 2026
grok-composer-2.5-fastxAI200K8 de jul. de 2026
fugu-ultrareasoning—1M6 de jul. de 2026
fugu-ultra-20260615reasoning—1M28 de jun. de 2026
mimo-v2.5-pro-ultraspeedreasoningXiaomi MiMo1M22 de jun. de 2026
kimi-k2.5reasoningMoonshot/Kimi—21 de jun. de 2026
claude-haiku-4-5reasoningAnthropic200K14 de jun. de 2026
claude-opus-4-8reasoningAnthropic1M14 de jun. de 2026
gpt-5-codexreasoningOpenAI Codex400K14 de jun. de 2026
gpt-5.3-codexreasoningOpenAI400K14 de jun. de 2026
gpt-5.5-proreasoningOpenAI1.05M14 de jun. de 2026
glm-5.2reasoningZ.ai1M12 de jun. de 2026
kimi-k2.7-codereasoningMoonshot/Kimi262K12 de jun. de 2026
minimax-m2.7reasoningMiniMax205K12 de jun. de 2026
minimax-m3reasoningMiniMax1M12 de jun. de 2026
step-3.7-flashreasoningStepFun256K12 de jun. de 2026
claude-sonnet-4-6reasoningAnthropic1M11 de jun. de 2026
gpt-5.5reasoningOpenAI1.05M8 de jun. de 2026
qwen3.6-flashreasoningQwen1M2 de jun. de 2026
qwen3.6-plusreasoningQwen—2 de jun. de 2026
trinity-minireasoningArcee128K2 de jun. de 2026
glm-5.1reasoningZ.ai203K31 de mai. de 2026
qwen3.6-35b-a3bQwen—31 de mai. de 2026
qwen3.7-maxreasoningQwen1M31 de mai. de 2026
trinity-large-thinkingreasoningArcee262K31 de mai. de 2026
mimo-v2.5reasoningXiaomi MiMo1M30 de mai. de 2026
mimo-v2.5-proreasoningXiaomi MiMo1M30 de mai. de 2026
kimi-for-codingreasoningMoonshot/Kimi262K25 de mai. de 2026
kimi-k2.6reasoningMoonshot/Kimi262K25 de mai. de 2026
deepseek-coder:1.3bDeepSeek—6 de mai. de 2026
deepseek-v4-flashreasoningDeepSeek1M23 de abr. de 2026
deepseek-v4-proreasoningDeepSeek1M23 de abr. de 2026
deepseek-reasonerDeepSeek—2 de mar. de 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 setup guides
Supported providers
ProviderProvider IDCredential setting
DeepSeekdeepseekDEEPSEEK_API_KEY
DeepSeek Anthropicdeepseek-anthropicDEEPSEEK_API_KEY / ANTHROPIC_API_KEY
NVIDIA NIMnvidia-nimNVIDIA_API_KEY / NVIDIA_NIM_API_KEY
OpenAI-compatibleopenaiOPENAI_API_KEY
AtlasCloudatlascloudATLASCLOUD_API_KEY
Wanjie Arkwanjie-arkWANJIE_ARK_API_KEY / WANJIE_API_KEY / WANJIE_MAAS_API_KEY
Volcengine ArkvolcengineVOLCENGINE_API_KEY / VOLCENGINE_ARK_API_KEY / ARK_API_KEY
OpenRouteropenrouterOPENROUTER_API_KEY
OrcaRouterorcarouterORCAROUTER_API_KEY
Xiaomi MiMoxiaomi-mimoXIAOMI_MIMO_TOKEN_PLAN_API_KEY / MIMO_TOKEN_PLAN_API_KEY / XIAOMI_MIMO_API_KEY / XIAOMI_API_KEY / MIMO_API_KEY
Novita AInovitaNOVITA_API_KEY
Fireworks AIfireworksFIREWORKS_API_KEY
SiliconFlowsiliconflowSILICONFLOW_API_KEY
SiliconFlow CNsiliconflow-CNSILICONFLOW_API_KEY
Arcee AIarceeARCEE_API_KEY
Moonshot/KimimoonshotMOONSHOT_API_KEY / KIMI_API_KEY
SGLangsglangSGLANG_API_KEY
vLLMvllmVLLM_API_KEY
OllamaollamaOLLAMA_API_KEY
Ollama Cloudollama-cloudOLLAMA_CLOUD_API_KEY / OLLAMA_API_KEY
Hugging FacehuggingfaceHUGGINGFACE_API_KEY / HF_TOKEN
Together AItogetherTOGETHER_API_KEY
Baidu QianfanqianfanQIANFAN_API_KEY / BAIDU_QIANFAN_API_KEY
OpenAI Codexopenai-codexChatGPT OAuth via `codewhale auth chatgpt`; optional consented Codex CLI credentials (OPENAI_CODEX_ACCESS_TOKEN / CODEX_ACCESS_TOKEN override)
AnthropicanthropicANTHROPIC_API_KEY
OpenModelopenmodelOPENMODEL_API_KEY
Z.aizaiZAI_API_KEY / Z_AI_API_KEY
StepFunstepfunSTEPFUN_API_KEY / STEP_API_KEY
MiniMaxminimaxMINIMAX_API_KEY
MiniMax (Anthropic-compatible)minimax-anthropicMINIMAX_API_KEY
DeepInfradeepinfraDEEPINFRA_API_KEY / DEEPINFRA_TOKEN
Sakana AIsakanaFUGU_API_KEY / SAKANA_API_KEY
Meituan LongCatlongcatLONGCAT_API_KEY
OpenCode Goopencode-goOPENCODE_GO_API_KEY
OpenCode Zenopencode-zenOPENCODE_ZEN_API_KEY / OPENCODE_API_KEY
Meta Model APImetaMETA_MODEL_API_KEY / MODEL_API_KEY
xAIxaiXAI_API_KEY
Mistral AImistralMISTRAL_API_KEY
Google GeminigoogleGOOGLE_API_KEY / GEMINI_API_KEY
ModelScopemodelscopeMODELSCOPE_API_KEY
TelecomJS TokenHubtelecomjsTELECOMJS_API_KEY
Eden AIedenaiEDENAI_API_KEY
ZenMuxzenmuxZENMUX_API_KEY
CSDN 星图 (Starmap)csdnCSDN_API_KEY
ConcentrateconcentrateCONCENTRATE_API_KEY
CodewhalecodewhaleCODEWHALE_API_KEY
Model Studio Token Planmodelstudio-token-planMODELSTUDIO_API_KEY
Model Studio Token Plan (Anthropic-compatible)modelstudio-token-plan-anthropicMODELSTUDIO_API_KEY
Model Studio Coding Planmodelstudio-coding-planMODELSTUDIO_API_KEY
Model Studio Coding Plan (Anthropic-compatible)modelstudio-coding-plan-anthropicMODELSTUDIO_API_KEY

Missing your provider? Request support