Skip to content
Checking statusStatus

Models & protocols

Model IDs, tiers, and which endpoint serves which family.

Model IDs

Send one of these IDs as model. IDs are case-sensitive. You can also fetch the live list from GET /v1/models, or browse rates on the Models page.

Model IDFamilyTierContext
claude-fable-5-2ClaudeFrontier262K
claude-fable-5-1ClaudeFrontier262K
claude-fable-5ClaudeFrontier262K
claude-mythos-5ClaudeFrontier262K
claude-opus-5.5ClaudeFrontier262K
claude-opus-5ClaudeFrontier262K
claude-opus-4.8ClaudeFrontier262K
claude-opus-4.7ClaudeFrontier262K
claude-opus-4.6ClaudeFrontier262K
claude-opus-4.5ClaudeFrontier262K
claude-opus-4.1ClaudeFrontier262K
claude-opus-4ClaudeFrontier262K
claude-sonnet-5.5ClaudeBalanced131K
claude-sonnet-5.1ClaudeBalanced131K
claude-sonnet-5ClaudeBalanced131K
claude-sonnet-4.6ClaudeBalanced131K
claude-sonnet-4.5ClaudeBalanced131K
claude-sonnet-4ClaudeBalanced131K
claude-haiku-5.5ClaudeSpeed131K
claude-haiku-4.5ClaudeSpeed131K
claude-haiku-3.5ClaudeSpeed131K
gpt-astra-6ChatGPTFrontier262K
gemini-argon-4GeminiFrontier131K
gemini-4-carbonGeminiBalanced1.05M
gemini-3-proGeminiFrontier131K
gemini-2.5-proGeminiFrontier131K
gemini-2.5-flashGeminiBalanced131K
gemini-2.5-flash-liteGeminiSpeed131K
gpt-5ChatGPTFrontier262K
gpt-5-miniChatGPTBalanced131K
gpt-4.1ChatGPTBalanced131K
gpt-4.1-miniChatGPTSpeed131K
gpt-4oChatGPTBalanced131K
gpt-4o-miniChatGPTSpeed131K
deepseek-v4DeepSeekFrontier131K
deepseek-r1DeepSeekFrontier131K
deepseek-v3DeepSeekBalanced131K
grok-4GrokFrontier131K
grok-3GrokBalanced131K
kimi-k2-thinkingKimiFrontier131K
kimi-k2KimiFrontier131K
qwen-3-maxQwenFrontier131K
qwen-3-coderQwenBalanced131K
mistral-large-3MistralFrontier131K
codestralMistralBalanced131K
mistral-smallMistralSpeed131K
llama-4-maverickLlamaFrontier131K
llama-4-scoutLlamaBalanced131K
gemini-4-hydrogenGeminiBalanced1.05M
muse-emberLlamaSpeed1.05M
hy4HunyuanSpeed1.05M
glm-5.3-flashx-legalGLMSpeed1.05M
gpt-6.1-terra-proChatGPTBalanced1.05M
gpt-6.1-terraChatGPTBalanced1.05M
kimi-k3.1-proKimiBalanced1.05M
minimax-m3.1-flashMiniMaxSpeed1.05M
deepseek-v4.1-flash-1017DeepSeekSpeed1.05M
muse-spark-openLlamaBalanced1.05M
nemotron-3.5-super-vlNemotronSpeed1.05M
muse-wonderLlamaFrontier1.05M
mistral-large-4-0MistralBalanced1.05M
gpt-6.1-sol-proChatGPTBalanced1.05M
gpt-6.1-solChatGPTBalanced1.05M
glm-5.3-primeGLMBalanced1M
qwen3.8-max-primeQwenBalanced1M
command-a-plusCommandBalanced192K
gpt-6-luna-proChatGPTSpeed1.05M
gpt-6-lunaChatGPTSpeed1.05M
gpt-6-sol-proChatGPTBalanced1.05M
gpt-6-solChatGPTBalanced1.05M
mimo-v2.6-pro-ultraspeedMiMoBalanced1.05M
mimo-v2.6-flashMiMoSpeed1.05M
mimo-v2.6-proMiMoSpeed1.05M
grok-4.7GrokBalanced500K
qwen3.8-omni-flashQwenSpeed1M
glm-5.3-flashxGLMSpeed1.05M
deepseek-v4.1-flashDeepSeekSpeed1.05M
gpt-6-astra-proChatGPTFrontier1.05M
qwen3.8-max-0902QwenBalanced1M
muse-spark-1.3-contributorLlamaSpeed1.05M
muse-spark-1.3LlamaBalanced1.05M
gemini-3.8-flashGeminiBalanced1.05M
hy4-previewHunyuanBalanced1.05M
qwen3.8-flashQwenSpeed1M
glm-5.3-flashGLMSpeed1.05M
muse-spark-1.2-contributorLlamaSpeed1.05M
deepseek-v4-flash-vision-expDeepSeekSpeed1.05M
hy-mt2-1.8bHunyuanSpeed8K
hy-mt2-30b-a3bHunyuanSpeed8K
hy-mt2-7bHunyuanSpeed8K
glm-5.3GLMSpeed1.05M
qwen3.8-27bQwenSpeed1.05M
gemini-3.7-flashGeminiBalanced1.05M
qwen3.8-2.4t-a95bQwenBalanced1.05M
deepseek-v4-pro-0813DeepSeekBalanced1.05M
grok-4.6GrokBalanced500K
nemotron-3.5-lightningNemotronSpeed262K
muse-glimmer-30bLlamaSpeed131K
muse-spark-1.2LlamaBalanced1.05M
deepseek-v4-flash-0731DeepSeekSpeed1.05M
qwen3.7-flashQwenSpeed1M
gemini-3.6-flashGeminiBalanced1.05M
gemini-3.5-flash-liteGeminiBalanced1.05M
kimi-k3KimiBalanced1.05M
muse-spark-1.1LlamaBalanced1.05M
gpt-5.6-luna-proChatGPTSpeed1.05M
gpt-5.6-lunaChatGPTSpeed1.05M
gpt-5.6-terra-proChatGPTBalanced1.05M
gpt-5.6-terraChatGPTBalanced1.05M
gpt-5.6-sol-proChatGPTFrontier1.05M
gpt-5.6-solChatGPTFrontier1.05M
grok-4.5GrokBalanced500K
hy3HunyuanSpeed262K
glm-5.2GLMBalanced1.05M
kimi-k2.7-codeKimiBalanced262K
nemotron-3.5-content-safetyNemotronSpeed131K
nemotron-3-ultra-550b-a55bNemotronBalanced262K
qwen3.7-plusQwenSpeed1M
minimax-m3MiniMaxSpeed1.05M
qwen3.7-maxQwenBalanced1M
grok-build-0.1GrokBalanced256K
gemini-3.5-flashGeminiBalanced1.05M
gemini-3.1-flash-liteGeminiBalanced1.05M
grok-4.3GrokBalanced1M
mistral-medium-3-5MistralBalanced262K
qwen3.5-plus-20260420QwenBalanced1M
qwen3.6-flashQwenSpeed1M
qwen3.6-35b-a3bQwenSpeed262K
qwen3.6-27bQwenBalanced262K
gpt-5.5-proChatGPTFrontier1.05M
gpt-5.5ChatGPTFrontier1.05M
deepseek-v4-flashDeepSeekSpeed1.05M
hy3-previewHunyuanSpeed262K
mimo-v2.5-proMiMoSpeed1.02M
mimo-v2.5MiMoBalanced1M
kimi-k2.6KimiBalanced262K
glm-5.1GLMBalanced204K
gemma-4-26b-a4b-itGeminiSpeed262K
gemma-4-31b-itGeminiSpeed262K
qwen3.6-plusQwenBalanced1M
glm-5v-turboGLMBalanced202K
grok-4.20-multi-agentGrokBalanced2M
grok-4.20GrokBalanced2M
minimax-m2.7MiniMaxSpeed196K
gpt-5.4-nanoChatGPTSpeed400K
gpt-5.4-miniChatGPTBalanced400K
glm-5-turboGLMBalanced202K
nemotron-3-super-120b-a12bNemotronSpeed262K
qwen3.5-9bQwenSpeed262K
gpt-5.4-proChatGPTFrontier1.05M
gpt-5.4ChatGPTFrontier1.05M
gemini-3.1-flash-lite-previewGeminiBalanced1.05M
qwen3.5-35b-a3bQwenSpeed262K
qwen3.5-27bQwenBalanced262K
qwen3.5-122b-a10bQwenBalanced262K
qwen3.5-flash-02-23QwenSpeed1M
gemini-3.1-pro-preview-customtoolsGeminiBalanced1.05M
gpt-5.3-codexChatGPTBalanced400K
gemini-3.1-pro-previewGeminiBalanced1.05M
qwen3.5-plus-02-15QwenBalanced1M
qwen3.5-397b-a17bQwenBalanced262K
minimax-m2.5MiniMaxSpeed200K
glm-5GLMBalanced204K
qwen3-coder-nextQwenSpeed262K
kimi-k2.5KimiBalanced262K
glm-4.7-flashGLMSpeed200K
gpt-5.2-codexChatGPTBalanced400K
glm-4.7GLMBalanced204K
gemini-3-flash-previewGeminiBalanced1.05M
nemotron-3-nano-30b-a3bNemotronSpeed262K
gpt-5.2-chatChatGPTBalanced128K
gpt-5.2-proChatGPTFrontier400K
gpt-5.2ChatGPTBalanced400K
devstral-2512MistralBalanced262K
glm-4.6vGLMSpeed131K
gpt-5.1-codex-maxChatGPTBalanced400K
ministral-14b-2512MistralSpeed262K
ministral-8b-2512MistralSpeed262K
ministral-3b-2512MistralSpeed131K
deepseek-v3.2DeepSeekSpeed163K
gpt-5.1ChatGPTBalanced400K
gpt-5.1-codexChatGPTBalanced400K
gpt-5.1-codex-miniChatGPTBalanced400K
sonar-pro-searchSonarFrontier200K
voxtral-small-24b-2507MistralSpeed32K
gpt-oss-safeguard-20bChatGPTSpeed131K
qwen3-vl-8b-instructQwenSpeed262K
qwen3-vl-30b-a3b-thinkingQwenSpeed262K
qwen3-vl-30b-a3b-instructQwenSpeed262K
gpt-5-proChatGPTFrontier400K
glm-4.6GLMBalanced204K
deepseek-v3.2-expDeepSeekSpeed163K
qwen3-vl-235b-a22b-instructQwenSpeed262K
deepseek-v3.1-terminusDeepSeekSpeed163K
qwen3-coder-flashQwenSpeed1M
qwen3-next-80b-a3b-instructQwenSpeed262K
kimi-k2-0905KimiBalanced262K
deepseek-chat-v3.1DeepSeekSpeed163K
mistral-medium-3.1MistralBalanced131K
glm-4.5vGLMBalanced65K
gpt-5-nanoChatGPTSpeed400K
gpt-oss-120bChatGPTSpeed131K
gpt-oss-20bChatGPTSpeed131K
qwen3-coder-30b-a3b-instructQwenSpeed262K
qwen3-30b-a3b-instruct-2507QwenSpeed262K
glm-4.5GLMBalanced131K
glm-4.5-airGLMSpeed131K
qwen3-235b-a22b-thinking-2507QwenBalanced128K
qwen3-235b-a22b-2507QwenSpeed262K
hunyuan-a13b-instructHunyuanSpeed131K
mistral-small-3.2-24b-instructMistralSpeed256K
o3-proChatGPTFrontier200K
gemini-2.5-pro-previewGeminiBalanced1.05M
mistral-medium-3MistralBalanced131K
llama-guard-4-12bLlamaSpeed163K
qwen3-30b-a3bQwenSpeed40K
qwen3-14bQwenSpeed40K
qwen3-32bQwenSpeed131K
o3ChatGPTBalanced200K
gpt-4.1-nanoChatGPTSpeed1.05M
deepseek-chat-v3-0324DeepSeekSpeed163K
mistral-small-3.1-24b-instructMistralSpeed128K
gemma-3-4b-itGeminiSpeed131K
gemma-3-12b-itGeminiSpeed131K
command-aCommandBalanced256K
gemma-3-27b-itGeminiSpeed131K
sonar-reasoning-proSonarBalanced128K
sonar-proSonarFrontier200K
sonar-deep-researchSonarBalanced128K
mistral-sabaMistralSpeed32K
qwen2.5-vl-72b-instructQwenSpeed128K
qwen-plusQwenSpeed1M
mistral-small-24b-instruct-2501MistralSpeed32K
sonarSonarSpeed127K
command-r7b-12-2024CommandSpeed128K
llama-3.3-70b-instructLlamaSpeed131K
gpt-4o-2024-11-20ChatGPTBalanced128K
mistral-large-2407MistralBalanced131K
qwen-2.5-coder-32b-instructQwenSpeed32K
llama-3.2-1b-instructLlamaSpeed60K
llama-3.2-3b-instructLlamaSpeed131K
qwen-2.5-72b-instructQwenSpeed32K
command-r-08-2024CommandSpeed128K
command-r-plus-08-2024CommandBalanced128K
gpt-4o-2024-08-06ChatGPTBalanced128K
llama-3.1-70b-instructLlamaSpeed131K
llama-3.1-8b-instructLlamaSpeed131K
mistral-nemoMistralSpeed131K
gpt-4o-mini-2024-07-18ChatGPTSpeed128K
gemma-2-27b-itGeminiSpeed8K
gpt-4o-2024-05-13ChatGPTFrontier128K
mixtral-8x22b-instructMistralBalanced65K
mistral-largeMistralBalanced128K
gpt-3.5-turbo-0613ChatGPTBalanced4K
gpt-3.5-turbo-16kChatGPTBalanced16K
gpt-4ChatGPTFrontier8K

Protocol support

Claude models are native to the Anthropic Messages API; GPT models are native to the OpenAI Responses API. Chat Completions works with every model, which is what most third-party tools use.

EndpointClaude modelsGPT models
POST /v1/messagesYesNo
POST /v1/responsesNoYes
POST /v1/chat/completionsYesYes
GET /v1/modelsYesYes

Choosing a tier

Most models in a tier bill at the same rate (the newest, Claude Fable 5.2, Mythos 5, Opus 5.5, Haiku 5.5 and GPT-6 Astra, at 1.5x), so choose by capability:

  • Frontier

    The most capable models, for deep reasoning and long-horizon agent work.

    e.g. claude-fable-5-2, claude-mythos-5, claude-opus-5.5, gpt-astra-6, gemini-argon-4, gemini-3-pro, gpt-5, deepseek-v4, deepseek-r1, grok-4, kimi-k2-thinking, kimi-k2, qwen-3-max, mistral-large-3, llama-4-maverick

  • Balanced

    Strong everyday models that trade a little depth for speed and cost.

    e.g. claude-sonnet-5.5, gemini-4-carbon, gemini-2.5-flash, gpt-5-mini, qwen-3-coder, codestral, llama-4-scout

  • Speed

    Fast, lightweight models for high-volume and latency-sensitive work.

    e.g. claude-haiku-5.5, gemini-2.5-flash-lite, mistral-small

A common pattern: plan and review with a Frontier model, do the bulk of the work with a Balanced one, and fan out sub-agents or classification on a Speed model. Claude and ChatGPT models can be mixed freely.

In the dashboard chat, smart routing can answer a simple follow-up with a lighter model, marked Auto; you can turn it off. See How routing works.