Model catalog
Every model. One governed gateway.
110+ models across 11 providers by name, hundreds more through OpenRouter, and any OpenAI-compatible endpoint. Every call governed, every response with a signed receipt.
119 models · 11 providers · prices per 1M tokens
119 of 119 models
| Model | Canonical id | Context | Input $/1M | Output $/1M | Call it |
|---|---|---|---|---|---|
| Claude Fable 5Anthropic | claude-fable-5 | 200,000 | $10.00 | $50.00 | Use the native surface, see the docs |
| Claude Opus 4.8Anthropic | claude-opus-4-8 | 200,000 | $5.00 | $25.00 | Use the native surface, see the docs |
| Claude Opus 4.7Anthropic | claude-opus-4-7 | 200,000 | $5.00 | $25.00 | Use the native surface, see the docs |
| Claude Opus 4.6Anthropic | claude-opus-4-6 | 200,000 | $5.00 | $25.00 | Use the native surface, see the docs |
| Claude Opus 4.5Anthropic | claude-opus-4-5 | 200,000 | $5.00 | $25.00 | Use the native surface, see the docs |
| Claude Opus 4.1Anthropic | claude-opus-4-1 | 200,000 | $15.00 | $75.00 | Use the native surface, see the docs |
| Claude Sonnet 4.6Anthropic | claude-sonnet-4-6 | 200,000 | $3.00 | $15.00 | Use the native surface, see the docs |
| Claude Sonnet 4.5Anthropic | claude-sonnet-4-5 | 200,000 | $3.00 | $15.00 | Use the native surface, see the docs |
| Claude Haiku 4.5Anthropic | claude-haiku-4-5 | 200,000 | $1.00 | $5.00 | Use the native surface, see the docs |
| GPT-4.1OpenAI | gpt-4.1 | 1,047,576 | $2.00 | $8.00 | |
| GPT-4.1 miniOpenAI | gpt-4.1-mini | 1,047,576 | $0.40 | $1.60 | |
| GPT-4.1 nanoOpenAI | gpt-4.1-nano | 1,047,576 | $0.10 | $0.40 | |
| GPT-4oOpenAI | gpt-4o | 128,000 | $2.50 | $10.00 | |
| GPT-4o miniOpenAI | gpt-4o-mini | 128,000 | $0.15 | $0.60 | |
| o3OpenAI | o3 | 200,000 | $2.00 | $8.00 | |
| o4-miniOpenAI | o4-mini | 200,000 | $1.10 | $4.40 | |
| Gemini 2.5 ProGoogle | gemini-2.5-pro | 1,048,576 | $1.25 | $10.00 | Use the native surface, see the docs |
| Gemini 2.5 FlashGoogle | gemini-2.5-flash | 1,048,576 | $0.30 | $2.50 | Use the native surface, see the docs |
| Gemini 2.0 FlashGoogle | gemini-2.0-flash | 1,048,576 | $0.10 | $0.40 | Use the native surface, see the docs |
| GPT-5.5OpenAI | gpt-5.5 | 1,000,000 | $5.00 | $30.00 | |
| GPT-5.5 ProOpenAI | gpt-5.5-pro | see provider | $30.00 | $180.00 | |
| GPT-5.4OpenAI | gpt-5.4 | 1,000,000 | $2.50 | $15.00 | |
| GPT-5.4 miniOpenAI | gpt-5.4-mini | 400,000 | $0.75 | $4.50 | |
| GPT-5.4 nanoOpenAI | gpt-5.4-nano | 400,000 | $0.20 | $1.25 | |
| GPT-5.4 ProOpenAI | gpt-5.4-pro | see provider | $30.00 | $180.00 | |
| GPT-5.3 CodexOpenAI | gpt-5.3-codex | 400,000 | $1.75 | $14.00 | |
| o3 Deep ResearchOpenAI | o3-deep-research | 200,000 | $10.00 | $40.00 | |
| o4-mini Deep ResearchOpenAI | o4-mini-deep-research | 200,000 | $2.00 | $8.00 | |
| Gemini 3.5 FlashGoogle | gemini-3.5-flash | 1,048,576 | $1.50 | $9.00 | Use the native surface, see the docs |
| Gemini 3.1 Pro PreviewGoogle | gemini-3.1-pro-preview | 1,048,576 | $2.00 | $12.00 | Use the native surface, see the docs |
| Gemini 3.1 Flash-LiteGoogle | gemini-3.1-flash-lite | 1,048,576 | $0.25 | $1.50 | Use the native surface, see the docs |
| Gemini 3 Flash PreviewGoogle | gemini-3-flash-preview | 1,048,576 | $0.50 | $3.00 | Use the native surface, see the docs |
| Gemini 2.5 Flash-LiteGoogle | gemini-2.5-flash-lite | 1,048,576 | $0.10 | $0.40 | Use the native surface, see the docs |
| Llama 3.3 70B VersatileGroq | llama-3.3-70b-versatile | 131,072 | $0.59 | $0.79 | |
| Llama 3.1 8B InstantGroq | llama-3.1-8b-instant | 131,072 | $0.05 | $0.08 | |
| Llama 4 Scout 17Bx16EGroq | llama-4-scout-17b-16e-instruct | 131,072 | $0.11 | $0.34 | |
| GPT-OSS 120BGroq | gpt-oss-120b | 131,072 | $0.15 | $0.60 | |
| GPT-OSS 20BGroq | gpt-oss-20b | 131,072 | $0.07 | $0.30 | |
| GPT-OSS Safeguard 20BGroq | gpt-oss-safeguard-20b | 131,072 | $0.07 | $0.30 | |
| Qwen3 32BGroq | qwen3-32b | 131,072 | $0.29 | $0.59 | |
| Qwen3.6 27BGroq | qwen3.6-27b | 131,072 | $0.60 | $3.00 | |
| Kimi K2 Instruct 0905Groq | kimi-k2-instruct-0905 | see provider | $1.00 | $3.00 | |
| Groq CompoundGroq | compound | 131,072 | see provider | see provider | |
| Groq Compound MiniGroq | compound-mini | 131,072 | see provider | see provider | |
| Kimi K2.7 CodeTogether AI | kimi-k2.7-code | 262,144 | $0.95 | $4.00 | |
| Kimi K2.6Together AI | kimi-k2.6 | 262,144 | $1.20 | $4.50 | |
| GLM-5.2Together AI | glm-5.2 | 262,144 | $1.40 | $4.40 | |
| GLM-5.1Together AI | glm-5.1 | 202,752 | $1.40 | $4.40 | |
| MiniMax M3Together AI | minimax-m3 | 524,288 | $0.30 | $1.20 | |
| MiniMax M2.7Together AI | minimax-m2.7 | 202,752 | $0.30 | $1.20 | |
| Qwen3.7 MaxTogether AI | qwen3.7-max | see provider | $1.25 | $3.75 | |
| Qwen3.7 PlusTogether AI | qwen3.7-plus | 1,000,000 | $0.32 | $1.28 | |
| Qwen3.6 PlusTogether AI | qwen3.6-plus | 1,000,000 | $0.50 | $3.00 | |
| Qwen3.5 9BTogether AI | qwen3.5-9b | 262,144 | $0.17 | $0.25 | |
| Qwen3 235B A22B 2507Together AI | qwen3-235b-a22b-instruct-2507-tput | 262,144 | $0.20 | $0.60 | |
| Qwen 2.5 7B TurboTogether AI | qwen2.5-7b-instruct-turbo | 32,768 | $0.30 | $0.30 | |
| Llama 3.3 70B TurboTogether AI | llama-3.3-70b-instruct-turbo | 131,072 | see provider | see provider | |
| Llama 3 8B LiteTogether AI | meta-llama-3-8b-instruct-lite | 8,192 | $0.14 | $0.14 | |
| Nemotron 3 Ultra 550BTogether AI | nemotron-3-ultra-550b-a55b | 512,300 | $0.60 | $3.60 | |
| LFM2 24B A2BTogether AI | lfm2-24b-a2b | 32,768 | $0.03 | $0.12 | |
| GLM 5.2Fireworks AI | glm-5p2 | see provider | $1.40 | $4.40 | |
| GLM 5.1Fireworks AI | glm-5p1 | see provider | $1.40 | $4.40 | |
| Kimi K2.7 CodeFireworks AI | kimi-k2p7-code | see provider | $0.95 | $4.00 | |
| Kimi K2.6Fireworks AI | kimi-k2p6 | see provider | $0.95 | $4.00 | |
| Qwen3.7 PlusFireworks AI | qwen3p7-plus | see provider | $0.40 | $1.60 | |
| Llama 3.3 70B InstructFireworks AI | llama-v3p3-70b-instruct | see provider | $0.90 | $0.90 | |
| Llama 3.1 70B InstructFireworks AI | llama-v3p1-70b-instruct | see provider | $0.90 | $0.90 | |
| Mistral Large 3Mistral AI | mistral-large-latest | 262,144 | $0.50 | $1.50 | |
| Mistral Medium 3.5Mistral AI | mistral-medium-latest | 262,144 | $1.50 | $7.50 | |
| Mistral Small 4Mistral AI | mistral-small-latest | 262,144 | $0.15 | $0.60 | |
| CodestralMistral AI | codestral-latest | 256,000 | $0.30 | $0.90 | |
| Magistral MediumMistral AI | magistral-medium-latest | see provider | $2.00 | $5.00 | |
| Magistral SmallMistral AI | magistral-small-latest | see provider | $0.50 | $1.50 | |
| Ministral 3 3BMistral AI | ministral-3b-latest | 131,072 | $0.10 | $0.10 | |
| Ministral 3 8BMistral AI | ministral-8b-latest | 262,144 | $0.15 | $0.15 | |
| Ministral 3 14BMistral AI | ministral-14b-latest | 262,144 | $0.20 | $0.20 | |
| Devstral 2Mistral AI | devstral-2512 | 262,144 | $0.40 | $2.00 | |
| Devstral Small 2Mistral AI | devstral-small-latest | see provider | $0.10 | $0.30 | |
| DeepSeek V4 FlashDeepSeek | deepseek-v4-flash | 1,048,576 | $0.14 | $0.28 | |
| DeepSeek V4 ProDeepSeek | deepseek-v4-pro | 1,048,576 | $0.43 | $0.87 | |
| DeepSeek ChatDeepSeek | deepseek-chat | see provider | $0.14 | $0.28 | |
| DeepSeek ReasonerDeepSeek | deepseek-reasoner | see provider | $0.14 | $0.28 | |
| Grok 4.3xAI | grok-4.3 | 1,000,000 | $1.25 | $2.50 | |
| Grok 4.20 ReasoningxAI | grok-4.20-0309-reasoning | see provider | $1.25 | $2.50 | |
| Grok 4.20 Non-ReasoningxAI | grok-4.20-0309-non-reasoning | see provider | $1.25 | $2.50 | |
| Grok 4.20 Multi-AgentxAI | grok-4.20-multi-agent-0309 | see provider | $1.25 | $2.50 | |
| Grok Build 0.1xAI | grok-build-0.1 | 256,000 | $1.00 | $2.00 | |
| SonarPerplexity | sonar | 127,072 | $1.00 | $1.00 | |
| Sonar ProPerplexity | sonar-pro | 200,000 | $3.00 | $15.00 | |
| Sonar Reasoning ProPerplexity | sonar-reasoning-pro | 128,000 | $2.00 | $8.00 | |
| Sonar Deep ResearchPerplexity | sonar-deep-research | 128,000 | $2.00 | $8.00 | |
| Llama 4 MaverickOpenRouter | llama-4-maverick | 1,048,576 | $0.15 | $0.60 | |
| Llama 4 ScoutOpenRouter | llama-4-scout | 10,000,000 | $0.10 | $0.30 | |
| Llama 3.3 70B InstructOpenRouter | llama-3.3-70b-instruct | 131,072 | $0.10 | $0.32 | |
| Llama 3.1 8B InstructOpenRouter | llama-3.1-8b-instruct | 131,072 | $0.02 | $0.03 | |
| Llama Guard 4 12BOpenRouter | llama-guard-4-12b | 163,840 | $0.18 | $0.18 | |
| DeepSeek R1OpenRouter | deepseek-r1 | 163,840 | $0.70 | $2.50 | |
| DeepSeek V3.2OpenRouter | deepseek-v3.2 | 131,072 | $0.23 | $0.34 | |
| Qwen3 CoderOpenRouter | qwen3-coder | 1,048,576 | $0.22 | $1.80 | |
| Qwen3 MaxOpenRouter | qwen3-max | 262,144 | $0.78 | $3.90 | |
| Qwen3 Next 80B A3BOpenRouter | qwen3-next-80b-a3b-instruct | 262,144 | $0.09 | $1.10 | |
| Kimi K2 ThinkingOpenRouter | kimi-k2-thinking | 262,144 | $0.60 | $2.50 | |
| Kimi K2.5OpenRouter | kimi-k2.5 | 262,144 | $0.38 | $2.02 | |
| GLM-5OpenRouter | glm-5 | 202,752 | $0.60 | $1.92 | |
| GLM-4.7OpenRouter | glm-4.7 | 202,752 | $0.40 | $1.75 | |
| GLM-4.7 FlashOpenRouter | glm-4.7-flash | 202,752 | $0.06 | $0.40 | |
| MiniMax M2.5OpenRouter | minimax-m2.5 | 204,800 | $0.12 | $0.48 | |
| Nemotron 3 Super 120BOpenRouter | nemotron-3-super-120b-a12b | 1,000,000 | $0.08 | $0.45 | |
| Nemotron 3 Nano 30BOpenRouter | nemotron-3-nano-30b-a3b | 262,144 | $0.05 | $0.20 | |
| Phi-4OpenRouter | phi-4 | 16,384 | $0.07 | $0.14 | |
| Gemma 4 31BOpenRouter | gemma-4-31b-it | 262,144 | $0.12 | $0.35 | |
| Gemma 3 27BOpenRouter | gemma-3-27b-it | 131,072 | $0.08 | $0.16 | |
| Command AOpenRouter | command-a | 256,000 | $2.50 | $10.00 | |
| Jamba Large 1.7OpenRouter | jamba-large-1.7 | 256,000 | $2.00 | $8.00 | |
| Nova 2 LiteOpenRouter | nova-2-lite-v1 | 1,000,000 | $0.30 | $2.50 | |
| Mercury 2OpenRouter | mercury-2 | 128,000 | $0.25 | $0.75 | |
| Hermes 4 405BOpenRouter | hermes-4-405b | 131,072 | $1.00 | $3.00 | |
| Olmo 3 32B ThinkOpenRouter | olmo-3-32b-think | 65,536 | $0.15 | $0.50 | |
| Hunyuan A13BOpenRouter | hunyuan-a13b-instruct | 131,072 | $0.14 | $0.57 |
Prices are indicative list prices per 1M tokens. Rows marked "see provider" have no firm public list price; the gateway still meters them from the SDK-reported cost.
How to call
How to call any of these.
Point any OpenAI client at the gateway's base URL, keep your provider key in Authorization (forwarded upstream, never stored), and add your AxioRank key. Guardrails, policy, and the signed receipt happen in the middle. Models served by another provider add one header: X-AxioRank-Upstream.
Your first governed call
curl https://app.axiorank.com/api/proxy/v1/chat/completions \
-H "content-type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "X-AxioRank-Key: axr_live_..." \
-d '{"model":"gpt-4o-mini","messages":[{"role":"user","content":"Summarize Q3 results"}]}'Setup, routing, failover
Base URL, headers, upstream presets, the native Anthropic and Gemini surfaces, and model-routing aliases.
Read the AI Gateway docsSee it govern a call
The live playground runs a real call through the gateway and hands you the signed receipt to verify offline.
Explore the AI GatewayBy provider
The full catalog, by provider.
A deep-linkable reference. Every provider and every model keeps a stable anchor, so you can point a teammate (or an agent) straight at a row.
Anthropic (9)OpenAI (16)Google (8)Groq (11)Together AI (16)Fireworks AI (7)Mistral AI (11)DeepSeek (4)xAI (5)Perplexity (4)OpenRouter (28)
Anthropic9 models
| Model | Canonical id | Context | Input $/1M | Output $/1M | Surface |
|---|---|---|---|---|---|
| Claude Fable 5 | claude-fable-5 | 200,000 | $10.00 | $50.00 | Native |
| Claude Opus 4.8 | claude-opus-4-8 | 200,000 | $5.00 | $25.00 | Native |
| Claude Opus 4.7 | claude-opus-4-7 | 200,000 | $5.00 | $25.00 | Native |
| Claude Opus 4.6 | claude-opus-4-6 | 200,000 | $5.00 | $25.00 | Native |
| Claude Opus 4.5 | claude-opus-4-5 | 200,000 | $5.00 | $25.00 | Native |
| Claude Opus 4.1 | claude-opus-4-1 | 200,000 | $15.00 | $75.00 | Native |
| Claude Sonnet 4.6 | claude-sonnet-4-6 | 200,000 | $3.00 | $15.00 | Native |
| Claude Sonnet 4.5 | claude-sonnet-4-5 | 200,000 | $3.00 | $15.00 | Native |
| Claude Haiku 4.5 | claude-haiku-4-5 | 200,000 | $1.00 | $5.00 | Native |
OpenAI16 models
| Model | Canonical id | Context | Input $/1M | Output $/1M | Surface |
|---|---|---|---|---|---|
| GPT-4.1 | gpt-4.1 | 1,047,576 | $2.00 | $8.00 | OpenAI-compatible |
| GPT-4.1 mini | gpt-4.1-mini | 1,047,576 | $0.40 | $1.60 | OpenAI-compatible |
| GPT-4.1 nano | gpt-4.1-nano | 1,047,576 | $0.10 | $0.40 | OpenAI-compatible |
| GPT-4o | gpt-4o | 128,000 | $2.50 | $10.00 | OpenAI-compatible |
| GPT-4o mini | gpt-4o-mini | 128,000 | $0.15 | $0.60 | OpenAI-compatible |
| o3 | o3 | 200,000 | $2.00 | $8.00 | OpenAI-compatible |
| o4-mini | o4-mini | 200,000 | $1.10 | $4.40 | OpenAI-compatible |
| GPT-5.5 | gpt-5.5 | 1,000,000 | $5.00 | $30.00 | OpenAI-compatible |
| GPT-5.5 Pro | gpt-5.5-pro | see provider | $30.00 | $180.00 | OpenAI-compatible |
| GPT-5.4 | gpt-5.4 | 1,000,000 | $2.50 | $15.00 | OpenAI-compatible |
| GPT-5.4 mini | gpt-5.4-mini | 400,000 | $0.75 | $4.50 | OpenAI-compatible |
| GPT-5.4 nano | gpt-5.4-nano | 400,000 | $0.20 | $1.25 | OpenAI-compatible |
| GPT-5.4 Pro | gpt-5.4-pro | see provider | $30.00 | $180.00 | OpenAI-compatible |
| GPT-5.3 Codex | gpt-5.3-codex | 400,000 | $1.75 | $14.00 | OpenAI-compatible |
| o3 Deep Research | o3-deep-research | 200,000 | $10.00 | $40.00 | OpenAI-compatible |
| o4-mini Deep Research | o4-mini-deep-research | 200,000 | $2.00 | $8.00 | OpenAI-compatible |
Google8 models
| Model | Canonical id | Context | Input $/1M | Output $/1M | Surface |
|---|---|---|---|---|---|
| Gemini 2.5 Pro | gemini-2.5-pro | 1,048,576 | $1.25 | $10.00 | Native |
| Gemini 2.5 Flash | gemini-2.5-flash | 1,048,576 | $0.30 | $2.50 | Native |
| Gemini 2.0 Flash | gemini-2.0-flash | 1,048,576 | $0.10 | $0.40 | Native |
| Gemini 3.5 Flash | gemini-3.5-flash | 1,048,576 | $1.50 | $9.00 | Native |
| Gemini 3.1 Pro Preview | gemini-3.1-pro-preview | 1,048,576 | $2.00 | $12.00 | Native |
| Gemini 3.1 Flash-Lite | gemini-3.1-flash-lite | 1,048,576 | $0.25 | $1.50 | Native |
| Gemini 3 Flash Preview | gemini-3-flash-preview | 1,048,576 | $0.50 | $3.00 | Native |
| Gemini 2.5 Flash-Lite | gemini-2.5-flash-lite | 1,048,576 | $0.10 | $0.40 | Native |
Groq11 models
| Model | Canonical id | Context | Input $/1M | Output $/1M | Surface |
|---|---|---|---|---|---|
| Llama 3.3 70B Versatile | llama-3.3-70b-versatile | 131,072 | $0.59 | $0.79 | OpenAI-compatible |
| Llama 3.1 8B Instant | llama-3.1-8b-instant | 131,072 | $0.05 | $0.08 | OpenAI-compatible |
| Llama 4 Scout 17Bx16E | llama-4-scout-17b-16e-instruct | 131,072 | $0.11 | $0.34 | OpenAI-compatible |
| GPT-OSS 120B | gpt-oss-120b | 131,072 | $0.15 | $0.60 | OpenAI-compatible |
| GPT-OSS 20B | gpt-oss-20b | 131,072 | $0.07 | $0.30 | OpenAI-compatible |
| GPT-OSS Safeguard 20B | gpt-oss-safeguard-20b | 131,072 | $0.07 | $0.30 | OpenAI-compatible |
| Qwen3 32B | qwen3-32b | 131,072 | $0.29 | $0.59 | OpenAI-compatible |
| Qwen3.6 27B | qwen3.6-27b | 131,072 | $0.60 | $3.00 | OpenAI-compatible |
| Kimi K2 Instruct 0905 | kimi-k2-instruct-0905 | see provider | $1.00 | $3.00 | OpenAI-compatible |
| Groq Compound | compound | 131,072 | see provider | see provider | OpenAI-compatible |
| Groq Compound Mini | compound-mini | 131,072 | see provider | see provider | OpenAI-compatible |
Together AI16 models
| Model | Canonical id | Context | Input $/1M | Output $/1M | Surface |
|---|---|---|---|---|---|
| Kimi K2.7 Code | kimi-k2.7-code | 262,144 | $0.95 | $4.00 | OpenAI-compatible |
| Kimi K2.6 | kimi-k2.6 | 262,144 | $1.20 | $4.50 | OpenAI-compatible |
| GLM-5.2 | glm-5.2 | 262,144 | $1.40 | $4.40 | OpenAI-compatible |
| GLM-5.1 | glm-5.1 | 202,752 | $1.40 | $4.40 | OpenAI-compatible |
| MiniMax M3 | minimax-m3 | 524,288 | $0.30 | $1.20 | OpenAI-compatible |
| MiniMax M2.7 | minimax-m2.7 | 202,752 | $0.30 | $1.20 | OpenAI-compatible |
| Qwen3.7 Max | qwen3.7-max | see provider | $1.25 | $3.75 | OpenAI-compatible |
| Qwen3.7 Plus | qwen3.7-plus | 1,000,000 | $0.32 | $1.28 | OpenAI-compatible |
| Qwen3.6 Plus | qwen3.6-plus | 1,000,000 | $0.50 | $3.00 | OpenAI-compatible |
| Qwen3.5 9B | qwen3.5-9b | 262,144 | $0.17 | $0.25 | OpenAI-compatible |
| Qwen3 235B A22B 2507 | qwen3-235b-a22b-instruct-2507-tput | 262,144 | $0.20 | $0.60 | OpenAI-compatible |
| Qwen 2.5 7B Turbo | qwen2.5-7b-instruct-turbo | 32,768 | $0.30 | $0.30 | OpenAI-compatible |
| Llama 3.3 70B Turbo | llama-3.3-70b-instruct-turbo | 131,072 | see provider | see provider | OpenAI-compatible |
| Llama 3 8B Lite | meta-llama-3-8b-instruct-lite | 8,192 | $0.14 | $0.14 | OpenAI-compatible |
| Nemotron 3 Ultra 550B | nemotron-3-ultra-550b-a55b | 512,300 | $0.60 | $3.60 | OpenAI-compatible |
| LFM2 24B A2B | lfm2-24b-a2b | 32,768 | $0.03 | $0.12 | OpenAI-compatible |
Fireworks AI7 models
| Model | Canonical id | Context | Input $/1M | Output $/1M | Surface |
|---|---|---|---|---|---|
| GLM 5.2 | glm-5p2 | see provider | $1.40 | $4.40 | OpenAI-compatible |
| GLM 5.1 | glm-5p1 | see provider | $1.40 | $4.40 | OpenAI-compatible |
| Kimi K2.7 Code | kimi-k2p7-code | see provider | $0.95 | $4.00 | OpenAI-compatible |
| Kimi K2.6 | kimi-k2p6 | see provider | $0.95 | $4.00 | OpenAI-compatible |
| Qwen3.7 Plus | qwen3p7-plus | see provider | $0.40 | $1.60 | OpenAI-compatible |
| Llama 3.3 70B Instruct | llama-v3p3-70b-instruct | see provider | $0.90 | $0.90 | OpenAI-compatible |
| Llama 3.1 70B Instruct | llama-v3p1-70b-instruct | see provider | $0.90 | $0.90 | OpenAI-compatible |
Mistral AI11 models
| Model | Canonical id | Context | Input $/1M | Output $/1M | Surface |
|---|---|---|---|---|---|
| Mistral Large 3 | mistral-large-latest | 262,144 | $0.50 | $1.50 | OpenAI-compatible |
| Mistral Medium 3.5 | mistral-medium-latest | 262,144 | $1.50 | $7.50 | OpenAI-compatible |
| Mistral Small 4 | mistral-small-latest | 262,144 | $0.15 | $0.60 | OpenAI-compatible |
| Codestral | codestral-latest | 256,000 | $0.30 | $0.90 | OpenAI-compatible |
| Magistral Medium | magistral-medium-latest | see provider | $2.00 | $5.00 | OpenAI-compatible |
| Magistral Small | magistral-small-latest | see provider | $0.50 | $1.50 | OpenAI-compatible |
| Ministral 3 3B | ministral-3b-latest | 131,072 | $0.10 | $0.10 | OpenAI-compatible |
| Ministral 3 8B | ministral-8b-latest | 262,144 | $0.15 | $0.15 | OpenAI-compatible |
| Ministral 3 14B | ministral-14b-latest | 262,144 | $0.20 | $0.20 | OpenAI-compatible |
| Devstral 2 | devstral-2512 | 262,144 | $0.40 | $2.00 | OpenAI-compatible |
| Devstral Small 2 | devstral-small-latest | see provider | $0.10 | $0.30 | OpenAI-compatible |
DeepSeek4 models
| Model | Canonical id | Context | Input $/1M | Output $/1M | Surface |
|---|---|---|---|---|---|
| DeepSeek V4 Flash | deepseek-v4-flash | 1,048,576 | $0.14 | $0.28 | OpenAI-compatible |
| DeepSeek V4 Pro | deepseek-v4-pro | 1,048,576 | $0.43 | $0.87 | OpenAI-compatible |
| DeepSeek Chat | deepseek-chat | see provider | $0.14 | $0.28 | OpenAI-compatible |
| DeepSeek Reasoner | deepseek-reasoner | see provider | $0.14 | $0.28 | OpenAI-compatible |
xAI5 models
| Model | Canonical id | Context | Input $/1M | Output $/1M | Surface |
|---|---|---|---|---|---|
| Grok 4.3 | grok-4.3 | 1,000,000 | $1.25 | $2.50 | OpenAI-compatible |
| Grok 4.20 Reasoning | grok-4.20-0309-reasoning | see provider | $1.25 | $2.50 | OpenAI-compatible |
| Grok 4.20 Non-Reasoning | grok-4.20-0309-non-reasoning | see provider | $1.25 | $2.50 | OpenAI-compatible |
| Grok 4.20 Multi-Agent | grok-4.20-multi-agent-0309 | see provider | $1.25 | $2.50 | OpenAI-compatible |
| Grok Build 0.1 | grok-build-0.1 | 256,000 | $1.00 | $2.00 | OpenAI-compatible |
Perplexity4 models
| Model | Canonical id | Context | Input $/1M | Output $/1M | Surface |
|---|---|---|---|---|---|
| Sonar | sonar | 127,072 | $1.00 | $1.00 | OpenAI-compatible |
| Sonar Pro | sonar-pro | 200,000 | $3.00 | $15.00 | OpenAI-compatible |
| Sonar Reasoning Pro | sonar-reasoning-pro | 128,000 | $2.00 | $8.00 | OpenAI-compatible |
| Sonar Deep Research | sonar-deep-research | 128,000 | $2.00 | $8.00 | OpenAI-compatible |
OpenRouter28 models
| Model | Canonical id | Context | Input $/1M | Output $/1M | Surface |
|---|---|---|---|---|---|
| Llama 4 Maverick | llama-4-maverick | 1,048,576 | $0.15 | $0.60 | OpenAI-compatible |
| Llama 4 Scout | llama-4-scout | 10,000,000 | $0.10 | $0.30 | OpenAI-compatible |
| Llama 3.3 70B Instruct | llama-3.3-70b-instruct | 131,072 | $0.10 | $0.32 | OpenAI-compatible |
| Llama 3.1 8B Instruct | llama-3.1-8b-instruct | 131,072 | $0.02 | $0.03 | OpenAI-compatible |
| Llama Guard 4 12B | llama-guard-4-12b | 163,840 | $0.18 | $0.18 | OpenAI-compatible |
| DeepSeek R1 | deepseek-r1 | 163,840 | $0.70 | $2.50 | OpenAI-compatible |
| DeepSeek V3.2 | deepseek-v3.2 | 131,072 | $0.23 | $0.34 | OpenAI-compatible |
| Qwen3 Coder | qwen3-coder | 1,048,576 | $0.22 | $1.80 | OpenAI-compatible |
| Qwen3 Max | qwen3-max | 262,144 | $0.78 | $3.90 | OpenAI-compatible |
| Qwen3 Next 80B A3B | qwen3-next-80b-a3b-instruct | 262,144 | $0.09 | $1.10 | OpenAI-compatible |
| Kimi K2 Thinking | kimi-k2-thinking | 262,144 | $0.60 | $2.50 | OpenAI-compatible |
| Kimi K2.5 | kimi-k2.5 | 262,144 | $0.38 | $2.02 | OpenAI-compatible |
| GLM-5 | glm-5 | 202,752 | $0.60 | $1.92 | OpenAI-compatible |
| GLM-4.7 | glm-4.7 | 202,752 | $0.40 | $1.75 | OpenAI-compatible |
| GLM-4.7 Flash | glm-4.7-flash | 202,752 | $0.06 | $0.40 | OpenAI-compatible |
| MiniMax M2.5 | minimax-m2.5 | 204,800 | $0.12 | $0.48 | OpenAI-compatible |
| Nemotron 3 Super 120B | nemotron-3-super-120b-a12b | 1,000,000 | $0.08 | $0.45 | OpenAI-compatible |
| Nemotron 3 Nano 30B | nemotron-3-nano-30b-a3b | 262,144 | $0.05 | $0.20 | OpenAI-compatible |
| Phi-4 | phi-4 | 16,384 | $0.07 | $0.14 | OpenAI-compatible |
| Gemma 4 31B | gemma-4-31b-it | 262,144 | $0.12 | $0.35 | OpenAI-compatible |
| Gemma 3 27B | gemma-3-27b-it | 131,072 | $0.08 | $0.16 | OpenAI-compatible |
| Command A | command-a | 256,000 | $2.50 | $10.00 | OpenAI-compatible |
| Jamba Large 1.7 | jamba-large-1.7 | 256,000 | $2.00 | $8.00 | OpenAI-compatible |
| Nova 2 Lite | nova-2-lite-v1 | 1,000,000 | $0.30 | $2.50 | OpenAI-compatible |
| Mercury 2 | mercury-2 | 128,000 | $0.25 | $0.75 | OpenAI-compatible |
| Hermes 4 405B | hermes-4-405b | 131,072 | $1.00 | $3.00 | OpenAI-compatible |
| Olmo 3 32B Think | olmo-3-32b-think | 65,536 | $0.15 | $0.50 | OpenAI-compatible |
| Hunyuan A13B | hunyuan-a13b-instruct | 131,072 | $0.14 | $0.57 | OpenAI-compatible |
Not listed? Route it through OpenRouter with the X-AxioRank-Upstream header, or point the gateway at any OpenAI-compatible endpoint. The same guardrails and signed receipts apply. See the AI Gateway docs.