USDC-backed inference on Base for autonomous agents

Agent AI Gateway

A drop-in, OpenAI-compatible gateway that lets agents pay with USDC on Base for long-running inference. Built for OpenClaw, OpenCode, Claude Code, and any SDK that already speaks OpenAI.

OpenAI-compatible+5% price transparencyx402 funding flowLLM-friendly docs
Get startedllm.txt
Fetch skills for your agent:
curl -fsSL https://agentaigateway.com/skill.md

Why agents choose this gateway

Everything is optimized for autonomous tooling: predictable headers, explicit pricing, and a clean OpenAI-compatible surface area.

Wallet-first billing

Agents attach a wallet once, then spend pre-funded credits. No per-request signing, no brittle payment steps, no human-in-the-loop.

Transparent pricing

We mirror Vercel AI Gateway pricing and apply a visible 5% markup. The models table below is exactly what your agent is billed.

Usage telemetry

Global per-model token counters keep capacity planning honest. Headers tell agents their remaining balance after every call.

Agent setup

Designed for scripts, SDKs, and autonomous frameworks. No UI required.

1. Install gateway skills

Use the bundled skills installer when it ships. Placeholder below.

curl -fsSL https://agentaigateway.com/skill.md

2. Configure SDK base URL

Point your OpenAI-compatible client to the gateway.

export OPENAI_BASE_URL="https://api.agentaigateway.com/v1"

3. Fund via x402 deposit

Call POST /v1/deposit to get x402 payment requirements, then sign with your wallet.

POST /v1/deposit {"amount_usdc": 20}
→ 402 + X-Payment-Required header
→ Sign & resend with X-Payment header

4. Attach wallet context

Every request includes your wallet header for credit accounting.

-H "X-Wallet-Address: 0xYOUR_WALLET"

5. Read low-balance hints

Agents can react to headers when credits run low.

X-Low-Balance: true
Check balance
Model pricing (gateway billed)
Auto-refreshed daily from Vercel AI Gateway + 5% markup
407 models
⌕
Tags
alibaba/qwen-3-14b
alibaba40,960$0.12 / 1M$0.25 / 1Mreasoning, tool-use, structured-output
alibaba/qwen-3-235b
alibaba262,144$0.23 / 1M$0.92 / 1Mtool-use, structured-output, reasoning
alibaba/qwen-3-30b
alibaba40,960$0.12 / 1M$0.5 / 1Mreasoning, tool-use, structured-output
alibaba/qwen-3-32b
alibaba128,000$0.16 / 1M$0.67 / 1Mreasoning, tool-use, structured-output
alibaba/qwen-3.6-max-preview
alibaba240,000$1.3 / 1M$8.1 / 1Mreasoning, tool-use, explicit-caching
alibaba/qwen3-235b-a22b-thinking
alibaba131,072$0.4 / 1M$4 / 1Mvision, reasoning, tool-use
alibaba/qwen3-coder
alibaba262,144$1.5 / 1M$7.8 / 1Mtool-use, structured-output, implicit-caching
alibaba/qwen3-coder-30b-a3b
alibaba262,144$0.15 / 1M$0.6 / 1Mtool-use, structured-output
alibaba/qwen3-coder-next
alibaba256,000$0.5 / 1M$1.2 / 1Mtool-use, structured-output
alibaba/qwen3-coder-plus
alibaba1,000,000$1 / 1M$5 / 1Mimplicit-caching, tool-use
alibaba/qwen3-embedding-0.6b
alibaba32,768$0.01 / 1M--
alibaba/qwen3-embedding-4b
alibaba32,768$0.02 / 1M--
alibaba/qwen3-embedding-8b
alibaba32,768$0.01 / 1M--
alibaba/qwen3-max
alibaba262,144$1.2 / 1M$6 / 1Mtool-use, implicit-caching, structured-output
alibaba/qwen3-max-preview
alibaba262,144$1.2 / 1M$6 / 1Mtool-use, implicit-caching, structured-output
alibaba/qwen3-max-thinking
alibaba256,000$1.2 / 1M$6 / 1Mreasoning, tool-use, structured-output
alibaba/qwen3-next-80b-a3b-instruct
alibaba262,114$0.15 / 1M$1.2 / 1Mtool-use, structured-output
alibaba/qwen3-next-80b-a3b-thinking
alibaba262,144$0.15 / 1M$1.2 / 1Mreasoning, tool-use, structured-output
alibaba/qwen3-vl-235b-a22b-instruct
alibaba131,072$0.4 / 1M$1.6 / 1Mtool-use, vision, implicit-caching
alibaba/qwen3-vl-instruct
alibaba131,072$0.4 / 1M$1.6 / 1Mtool-use, vision, implicit-caching
alibaba/qwen3-vl-thinking
alibaba131,072$0.4 / 1M$4 / 1Mvision, reasoning, tool-use
alibaba/qwen3.5-flash
alibaba1,000,000$0.1 / 1M$0.4 / 1Mvision, file-input, reasoning
alibaba/qwen3.5-plus
alibaba1,000,000$0.4 / 1M$2.5 / 1Mvision, file-input, reasoning
alibaba/qwen3.6-27b
alibaba256,000$0.6 / 1M$3.7 / 1Mreasoning, tool-use, file-input
alibaba/qwen3.6-plus
alibaba1,000,000$0.5 / 1M$3 / 1Mreasoning, tool-use, vision
alibaba/qwen3.7-flash
alibaba991,000$0.03 / 1M$0.13 / 1Mreasoning, tool-use, implicit-caching
alibaba/qwen3.7-max
alibaba991,000$2.6 / 1M$7.8 / 1Mimplicit-caching, reasoning, tool-use
alibaba/qwen3.7-plus
alibaba1,000,000$0.4 / 1M$1.6 / 1Mreasoning, tool-use, implicit-caching
alibaba/qwen3.8-2.4t-a95b
alibaba262,144$2 / 1M$6 / 1Mreasoning, tool-use, implicit-caching
alibaba/qwen3.8-27b
alibaba1,000,000$0.5 / 1M$3 / 1Mreasoning, tool-use, vision
alibaba/qwen3.8-flash
alibaba991,000$0.15 / 1M$0.49 / 1Mreasoning, tool-use, implicit-caching
alibaba/qwen3.8-max
alibaba262,144$2 / 1M$6 / 1Mreasoning, tool-use, implicit-caching
alibaba/qwen3.8-max-0902
alibaba991,000$2 / 1M$6 / 1Mreasoning, tool-use, vision
alibaba/qwen3.8-max-prime
alibaba1,000,000$4 / 1M$12 / 1Mimplicit-caching, reasoning, structured-output
alibaba/qwen3.8-omni-flash
alibaba1,000,000$0.15 / 1M$0.49 / 1Mimplicit-caching, reasoning, structured-output
alibaba/wan-v2.5-t2v-preview
alibaba----
alibaba/wan-v2.6-i2v
alibaba----
alibaba/wan-v2.6-i2v-flash
alibaba----
alibaba/wan-v2.6-r2v
alibaba----
alibaba/wan-v2.6-r2v-flash
alibaba----
alibaba/wan-v2.6-t2v
alibaba----
alibaba/wan-v2.7-r2v
alibaba----
alibaba/wan-v2.7-t2v
alibaba----
alibaba/wan-v3.0-video
alibaba---vision, video-input, audio-input
alibaba/wan-v3.0-video-prime
alibaba---vision, video-input, audio-input
amazon/nova-2-lite
amazon1,000,000$0.3 / 1M$2.6 / 1Mfile-input, reasoning, tool-use
amazon/nova-lite
amazon300,000$0.06 / 1M$0.25 / 1Mfile-input, tool-use, vision
amazon/nova-micro
amazon128,000$0.04 / 1M$0.14 / 1Mtool-use, structured-output
amazon/nova-pro
amazon300,000$0.8 / 1M$3.3 / 1Mfile-input, tool-use, vision
amazon/titan-embed-text-v2
amazon-$0.02 / 1M--
anthropic/claude-3-haiku
anthropic200,000$0.26 / 1M$1.31 / 1Mtool-use, vision, explicit-caching
anthropic/claude-fable-5
anthropic1,000,000$10 / 1M$50 / 1Mreasoning, tool-use, explicit-caching
anthropic/claude-fable-5.1
anthropic1,000,000$10 / 1M$50 / 1Mreasoning, tool-use, explicit-caching
anthropic/claude-haiku-4.5
anthropic200,000$1 / 1M$5 / 1Mexplicit-caching, file-input, reasoning
anthropic/claude-opus-4
anthropic200,000$15 / 1M$78 / 1Mfile-input, reasoning, tool-use
anthropic/claude-opus-4.5
anthropic200,000$5 / 1M$26 / 1Mexplicit-caching, file-input, reasoning
anthropic/claude-opus-4.6
anthropic1,000,000$5 / 1M$26 / 1Mtool-use, reasoning, vision
anthropic/claude-opus-4.7
anthropic1,000,000$5 / 1M$26 / 1Mtool-use, reasoning, vision
anthropic/claude-opus-4.8
anthropic1,000,000$5 / 1M$26 / 1Mtool-use, reasoning, vision
anthropic/claude-opus-4.8-fast
anthropic1,000,000$10 / 1M$50 / 1Mtool-use, reasoning, vision
anthropic/claude-opus-5
anthropic1,000,000$5 / 1M$26 / 1Mtool-use, reasoning, vision
anthropic/claude-opus-5-fast
anthropic1,000,000$10 / 1M$50 / 1Mtool-use, reasoning, vision
anthropic/claude-opus-5.5
anthropic1,000,000$4 / 1M$20 / 1Mexplicit-caching, fast, file-input
anthropic/claude-opus-5.5-fast
anthropic1,000,000$8 / 1M$40 / 1Mexplicit-caching, fast, file-input
anthropic/claude-sonnet-4
anthropic1,000,000$3 / 1M$15 / 1Mfile-input, reasoning, tool-use
anthropic/claude-sonnet-4.5
anthropic1,000,000$3 / 1M$15 / 1Mexplicit-caching, file-input, reasoning
anthropic/claude-sonnet-4.6
anthropic1,000,000$3 / 1M$15 / 1Mfile-input, reasoning, tool-use
anthropic/claude-sonnet-5
anthropic1,000,000$2 / 1M$10 / 1Mreasoning, tool-use, explicit-caching
anthropic/claude-sonnet-5.5
anthropic1,000,000$2 / 1M$10 / 1Mexplicit-caching, file-input, reasoning
arcee-ai/trinity-large-thinking
arcee-ai262,100$0.26 / 1M$0.9 / 1Mreasoning, tool-use, structured-output
bfl/flux-2-flex
bfl---image-generation
bfl/flux-2-klein-4b
bfl---image-generation
bfl/flux-2-klein-9b
bfl---image-generation
bfl/flux-2-max
bfl67,300--image-generation
bfl/flux-2-pro
bfl67,300--image-generation
bfl/flux-3-video
bfl---video-generation
bfl/flux-kontext-max
bfl512--image-generation
bfl/flux-kontext-pro
bfl512--image-generation
bfl/flux-pro-1.0-fill
bfl---image-generation
bfl/flux-pro-1.1
bfl---image-generation
bfl/flux-pro-1.1-ultra
bfl---image-generation
bytedance/seed-1.6
bytedance256,000$0.26 / 1M$2 / 1Mreasoning, tool-use, vision
bytedance/seed-1.8
bytedance256,000$0.26 / 1M$2 / 1Mreasoning, tool-use, vision
bytedance/seed-2.1-turbo
bytedance262,144$0.5 / 1M$2.6 / 1Mreasoning, tool-use, video-input
bytedance/seedance-2.0
bytedance---video-generation, vision
bytedance/seedance-2.0-fast
bytedance---vision, video-generation
bytedance/seedance-2.0-mini
bytedance---vision, video-generation
bytedance/seedance-2.5
bytedance----
bytedance/seedance-v1.0-pro
bytedance---video-generation
bytedance/seedance-v1.0-pro-fast
bytedance---video-generation
bytedance/seedance-v1.5-pro
bytedance---video-generation
bytedance/seedream-4.0
bytedance---image-generation
bytedance/seedream-4.5
bytedance---image-generation
bytedance/seedream-5.0-lite
bytedance---image-generation
bytedance/seedream-5.0-pro
bytedance-$0 / 1M-image-generation
cohere/command-a
cohere256,000$2.6 / 1M$10 / 1Mtool-use, structured-output
cohere/embed-v4.0
cohere128,000$0.12 / 1M--
cohere/rerank-v3.5
cohere4,096---
cohere/rerank-v4-fast
cohere32,000---
cohere/rerank-v4-pro
cohere32,000---
convaiinnovations/laya
convaiinnovations8,192$0 / 1M$0 / 1Mfree
convaiinnovations/laya-free
convaiinnovations8,192$0 / 1M$0 / 1Mfree
deepseek/deepseek-r1
deepseek128,000$1.41 / 1M$5.6 / 1Mreasoning, tool-use, implicit-caching
deepseek/deepseek-v3.1
deepseek163,840$0.26 / 1M$0.99 / 1Mimplicit-caching, reasoning, tool-use
deepseek/deepseek-v3.1-terminus
deepseek131,072$0.28 / 1M$1 / 1Mimplicit-caching, reasoning, tool-use
deepseek/deepseek-v3.2
deepseek128,000$0.65 / 1M$1.94 / 1Mtool-use, implicit-caching
deepseek/deepseek-v3.2-thinking
deepseek128,000$0.65 / 1M$1.94 / 1Mtool-use, implicit-caching
deepseek/deepseek-v4-flash
deepseek1,000,000$0.13 / 1M$0.27 / 1Mreasoning, tool-use, implicit-caching
deepseek/deepseek-v4-flash-0731
deepseek1,000,000$0.08 / 1M$0.16 / 1Mreasoning, tool-use, implicit-caching
deepseek/deepseek-v4-flash-vision-exp
deepseek1,048,576$0.23 / 1M$0.68 / 1Mreasoning, tool-use, implicit-caching
deepseek/deepseek-v4-pro
deepseek1,000,000$0.69 / 1M$2.07 / 1Mimplicit-caching, reasoning, tool-use
deepseek/deepseek-v4-pro-0813
deepseek1,000,000$0.69 / 1M$2.07 / 1Mreasoning, tool-use, implicit-caching
deepseek/deepseek-v4.1-flash
deepseek1,048,576$0.3 / 1M$1.2 / 1Mreasoning, tool-use, implicit-caching
deepseek/deepseek-v4.1-flash-fast
deepseek1,048,576$0.3 / 1M$1.2 / 1Mimplicit-caching, reasoning, structured-output
fireworks/ember-1
fireworks1,048,576$3 / 1M$15 / 1Mimplicit-caching, reasoning, tool-use
fish-audio/s1
fish-audio-$15 / 1M--
fish-audio/s2-pro
fish-audio-$15 / 1M--
fish-audio/s2.1-pro
fish-audio-$15 / 1M--
fish-audio/transcribe-1
fish-audio-$0 / 1M--
google/gemini-2.5-flash
google1,000,000$0.3 / 1M$2.6 / 1Mfile-input, reasoning, tool-use
google/gemini-2.5-flash-image
google32,768$0.3 / 1M$2.6 / 1Mimage-generation, web-search, vision
google/gemini-2.5-flash-lite
google1,048,576$0.1 / 1M$0.4 / 1Mfile-input, reasoning, tool-use
google/gemini-2.5-pro
google1,048,576$1.31 / 1M$10 / 1Mfile-input, reasoning, tool-use
google/gemini-3-flash
google1,000,000$0.5 / 1M$3 / 1Mreasoning, file-input, vision
google/gemini-3-pro-image
google65,536$2 / 1M$12 / 1Mimage-generation, web-search, implicit-caching
google/gemini-3.1-flash-image
google131,072$0.5 / 1M$3 / 1Mimage-generation, implicit-caching, reasoning
google/gemini-3.1-flash-image-preview
google131,072$0.5 / 1M$3 / 1Mimage-generation, implicit-caching, reasoning
google/gemini-3.1-flash-lite
google1,000,000$0.26 / 1M$1.5 / 1Mreasoning, tool-use, implicit-caching
google/gemini-3.1-flash-lite-image
google65,536$0.26 / 1M$1.5 / 1Mimage-generation, implicit-caching, reasoning
google/gemini-3.1-pro-preview
google1,000,000$2 / 1M$12 / 1Mfile-input, tool-use, reasoning
google/gemini-3.5-flash
google1,000,000$1.5 / 1M$9 / 1Mreasoning, file-input, vision
google/gemini-3.5-flash-lite
google1,000,000$0.3 / 1M$2.6 / 1Mreasoning, tool-use, implicit-caching
google/gemini-3.5-transcribe
google-$2 / 1M$12 / 1M-
google/gemini-3.5-transcribe-live
google-$0 / 1M-websocket-transcription
google/gemini-3.6-flash
google1,000,000$0.78 / 1M$3.93 / 1Mreasoning, file-input, tool-use
google/gemini-3.7-flash
google1,000,000$0.78 / 1M$3.93 / 1Mreasoning, file-input, vision
google/gemini-3.8-flash
google1,000,000$0.78 / 1M$3.93 / 1Mreasoning, file-input, vision
google/gemini-3.8-flash-lite-tts
google-$0.5 / 1M$6 / 1M-
google/gemini-3.8-flash-tts
google-$0.5 / 1M$9 / 1M-
google/gemini-3.8-live
google-$0.78 / 1M$4.7 / 1Mwebsocket-realtime
google/gemini-3.8-live-extended-thinking
google-$0.78 / 1M$4.7 / 1Mwebsocket-realtime
google/gemini-embedding-001
google-$0.15 / 1M--
google/gemini-embedding-2
google-$0.2 / 1M--
google/gemini-omni-flash-preview
google1,000,000$1.5 / 1M$9 / 1Mfile-input, reasoning, vision
google/gemma-4-26b-a4b-it
google262,144$0.15 / 1M$0.6 / 1Mfile-input, reasoning, tool-use
google/gemma-4-31b-it
google262,144$0.14 / 1M$0.4 / 1Mtool-use, vision, file-input
google/text-embedding-005
google-$0.03 / 1M--
google/text-multilingual-embedding-002
google-$0.03 / 1M--
google/veo-3.0-fast-generate-001
google----
google/veo-3.0-generate-001
google----
google/veo-3.1-fast-generate-001
google----
google/veo-3.1-generate-001
google----
google/veo-3.1-lite-generate-001
google----
inception/mercury-2
inception128,000$0.26 / 1M$0.78 / 1Mreasoning, tool-use, structured-output
inception/mercury-2.5
inception260,000$0.04 / 1M$0.15 / 1Mimplicit-caching, reasoning, tool-use
inception/mercury-coder-small
inception32,000$0.26 / 1M$1 / 1Mtool-use, structured-output
inclusionai/ling-3.0-flash
inclusionai256,000$0.02 / 1M$0.07 / 1Mreasoning, tool-use, implicit-caching
inclusionai/ling-3.0-flash-fin
inclusionai256,000$0.08 / 1M$0.23 / 1Mimplicit-caching, reasoning, tool-use
inclusionai/ling-3.0-flash-sante
inclusionai256,000$0 / 1M$0 / 1Mfree, reasoning, tool-use
inclusionai/ling-3.0-flash-sante-free
inclusionai256,000$0 / 1M$0 / 1Mfree, reasoning, tool-use
inclusionai/ling-3.0-flash-vl
inclusionai256,000$0.08 / 1M$0.23 / 1Mreasoning, tool-use, video-input
inclusionai/ling-3.1-flash
inclusionai262,144$0 / 1M$0 / 1Mfree, reasoning, tool-use
inclusionai/ling-3.1-flash-free
inclusionai262,144$0 / 1M$0 / 1Mfree, reasoning, tool-use
inference-net/schematron-v2-small
inference-net128,000$0.05 / 1M$0.24 / 1Mstructured-output
inference-net/schematron-v2-turbo
inference-net128,000$0.03 / 1M$0.15 / 1Mstructured-output
interfaze/interfaze-beta
interfaze1,000,000$1.5 / 1M$3.6 / 1Mfile-input, reasoning, tool-use
klingai/kling-v2.5-turbo-i2v
klingai----
klingai/kling-v2.5-turbo-t2v
klingai----
klingai/kling-v2.6-i2v
klingai----
klingai/kling-v2.6-motion-control
klingai----
klingai/kling-v2.6-t2v
klingai----
klingai/kling-v3.0-i2v
klingai----
klingai/kling-v3.0-motion-control
klingai---video-generation
klingai/kling-v3.0-t2v
klingai----
liquid/d1
liquid65,536$0.04 / 1M$0 / 1M-
meituan/longcat-2.5-preview
meituan1,048,576$0.3 / 1M$1.2 / 1Mimplicit-caching, reasoning, tool-use
meta/llama-3.1-70b
meta128,000$0.75 / 1M$0.75 / 1Mtool-use, structured-output
meta/llama-3.1-8b
meta128,000$0.23 / 1M$0.23 / 1Mtool-use, structured-output
meta/llama-3.3-70b
meta128,000$0.75 / 1M$0.75 / 1Mtool-use
meta/llama-4-maverick
meta128,000$0.25 / 1M$1.01 / 1Mtool-use, vision, structured-output
meta/llama-4-scout
meta128,000$0.17 / 1M$0.69 / 1Mtool-use, vision, structured-output
meta/muse-glimmer-30b
meta131,072$0.36 / 1M$1.5 / 1Mvision, implicit-caching, reasoning
meta/muse-image-1.0
meta---image-generation, vision
meta/muse-spark-1.1
meta1,048,576$1.31 / 1M$4.46 / 1Mreasoning, tool-use, implicit-caching
meta/muse-spark-1.2
meta1,048,576$1.31 / 1M$4.46 / 1Mreasoning, tool-use, implicit-caching
meta/muse-spark-1.2-contributor
meta1,048,576$0.1 / 1M$0.2 / 1Mreasoning, tool-use, implicit-caching
meta/muse-spark-1.3
meta1,048,576$1.31 / 1M$4.46 / 1Mreasoning, tool-use, implicit-caching
meta/muse-spark-1.3-contributor
meta1,048,576$0.1 / 1M$0.2 / 1Mreasoning, tool-use, implicit-caching
microsoft/mai-transcribe-1.5
microsoft-$0 / 1M--
microsoft/mai-transcribe-2
microsoft-$0 / 1M--
microsoft/mai-transcribe-2-streaming
microsoft---websocket-transcription
microsoft/mai-voice-2
microsoft-$23 / 1M--
microsoft/mai-voice-2-flash
microsoft-$15 / 1M--
microsoft/mai-voice-2.1
microsoft-$23 / 1M--
microsoft/mai-voice-2.1-flash
microsoft-$15 / 1M--
minimax/minimax-h3
minimax---video-generation, vision
minimax/minimax-h3-max
minimax---video-generation, vision
minimax/minimax-m2
minimax205,000$0.3 / 1M$1.2 / 1Mreasoning, tool-use, explicit-caching
minimax/minimax-m2.1
minimax204,800$0.3 / 1M$1.2 / 1Mreasoning, tool-use, structured-output
minimax/minimax-m2.1-lightning
minimax204,800$0.3 / 1M$2.5 / 1Mreasoning, tool-use, implicit-caching
minimax/minimax-m2.5
minimax204,800$0.3 / 1M$1.2 / 1Mreasoning, tool-use, structured-output
minimax/minimax-m2.5-highspeed
minimax204,800$0.6 / 1M$2.5 / 1Mreasoning, tool-use, implicit-caching
minimax/minimax-m2.7
minimax204,800$0.3 / 1M$1.2 / 1Mreasoning, tool-use, implicit-caching
minimax/minimax-m2.7-highspeed
minimax204,800$0.6 / 1M$2.5 / 1Mreasoning, tool-use, implicit-caching
minimax/minimax-m3
minimax512,000$0.3 / 1M$1.2 / 1Mreasoning, tool-use, vision
mistral/codestral
mistral128,000$0.3 / 1M$0.9 / 1Mtool-use, structured-output
mistral/codestral-embed
mistral-$0.15 / 1M--
mistral/ministral-14b
mistral262,144$0.2 / 1M$0.2 / 1Mfile-input, tool-use, vision
mistral/ministral-3b
mistral131,072$0.1 / 1M$0.1 / 1Mtool-use, vision
mistral/ministral-8b
mistral262,144$0.15 / 1M$0.15 / 1Mtool-use, vision, structured-output
mistral/mistral-embed
mistral-$0.1 / 1M--
mistral/mistral-large-3
mistral262,144$0.5 / 1M$1.5 / 1Mtool-use, vision, structured-output
mistral/mistral-medium-3.5
mistral262,144$1.5 / 1M$7.8 / 1Mreasoning, tool-use, vision
mistral/mistral-nemo
mistral60,288$0.04 / 1M$0.17 / 1Mtool-use, structured-output
mistral/mistral-small
mistral262,144$0.15 / 1M$0.6 / 1Mtool-use, vision, structured-output
mixedbread/toast-1
mixedbread131,000$0.3 / 1M$0.75 / 1Mimplicit-caching, tool-use, structured-output
moonshotai/kimi-k2
moonshotai131,072$0.59 / 1M$2.4 / 1Mtool-use
moonshotai/kimi-k2-thinking
moonshotai216,144$0.49 / 1M$2 / 1Mreasoning, tool-use, implicit-caching
moonshotai/kimi-k2.5
moonshotai256,000$0.6 / 1M$3 / 1Mreasoning, vision, tool-use
moonshotai/kimi-k2.6
moonshotai262,000$0.99 / 1M$4 / 1Mimplicit-caching, reasoning, tool-use
moonshotai/kimi-k2.7-code
moonshotai256,000$0.99 / 1M$4 / 1Mreasoning, tool-use, implicit-caching
moonshotai/kimi-k2.7-code-highspeed
moonshotai262,144$1.9 / 1M$8 / 1Mreasoning, tool-use, vision
moonshotai/kimi-k3
moonshotai1,000,000$3 / 1M$15 / 1Mreasoning, tool-use, implicit-caching
moonshotai/kimi-k3-fast
moonshotai1,000,000$4.7 / 1M$23.6 / 1Mreasoning, tool-use, implicit-caching
morph/morph-v3-fast
morph81,920$0.8 / 1M$1.2 / 1Mstructured-output
morph/morph-v3-large
morph81,920$0.9 / 1M$1.9 / 1Mstructured-output
nvidia/nemotron-3-nano-30b-a3b
nvidia262,144$0.05 / 1M$0.2 / 1Mreasoning, tool-use
nvidia/nemotron-3-super-120b-a12b
nvidia256,000$0.15 / 1M$0.68 / 1Mreasoning, tool-use, structured-output
nvidia/nemotron-3-ultra-550b-a55b
nvidia1,000,000$0.6 / 1M$2.5 / 1Mreasoning, tool-use, structured-output
nvidia/nemotron-3.5-lightning
nvidia262,144$0.05 / 1M$0.2 / 1Mreasoning, tool-use, implicit-caching
nvidia/nemotron-nano-12b-v2-vl
nvidia131,072$0.2 / 1M$0.6 / 1Mvision, reasoning, tool-use
nvidia/nemotron-nano-9b-v2
nvidia131,072$0.06 / 1M$0.24 / 1Mreasoning, tool-use
openai/gpt-3.5-turbo
openai16,385$0.5 / 1M$1.5 / 1Mtool-use
openai/gpt-4-turbo
openai128,000$10 / 1M$30 / 1Mtool-use, vision
openai/gpt-4.1
openai1,047,576$2 / 1M$8 / 1Mfile-input, implicit-caching, tool-use
openai/gpt-4.1-fast
openai1,047,576$3.6 / 1M$14 / 1Mfile-input, implicit-caching, tool-use
openai/gpt-4.1-mini
openai1,047,576$0.4 / 1M$1.6 / 1Mfile-input, implicit-caching, tool-use
openai/gpt-4.1-mini-fast
openai1,047,576$0.7 / 1M$2.9 / 1Mfile-input, implicit-caching, tool-use
openai/gpt-4.1-nano
openai1,047,576$0.1 / 1M$0.4 / 1Mfile-input, implicit-caching, tool-use
openai/gpt-4.1-nano-fast
openai1,047,576$0.2 / 1M$0.8 / 1Mfile-input, implicit-caching, tool-use
openai/gpt-4o
openai128,000$2.6 / 1M$10 / 1Mfile-input, implicit-caching, tool-use
openai/gpt-4o-fast
openai128,000$4.46 / 1M$17 / 1Mfile-input, implicit-caching, tool-use
openai/gpt-4o-mini
openai128,000$0.15 / 1M$0.6 / 1Mfile-input, implicit-caching, tool-use
openai/gpt-4o-mini-fast
openai128,000$0.26 / 1M$1 / 1Mfile-input, implicit-caching, tool-use
openai/gpt-4o-mini-transcribe
openai-$1.31 / 1M$5 / 1M-
openai/gpt-4o-transcribe
openai-$2.6 / 1M$10 / 1M-
openai/gpt-5
openai400,000$1.31 / 1M$10 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5-codex
openai400,000$1.31 / 1M$10 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5-fast
openai400,000$2.6 / 1M$20 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5-mini
openai400,000$0.26 / 1M$2 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5-mini-fast
openai400,000$0.47 / 1M$3.7 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5-nano
openai400,000$0.05 / 1M$0.4 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5-pro
openai400,000$15 / 1M$120 / 1Mfile-input, reasoning, tool-use
openai/gpt-5.1-codex
openai400,000$1.31 / 1M$10 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5.1-codex-max
openai400,000$1.31 / 1M$10 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5.1-codex-mini
openai400,000$0.26 / 1M$2 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5.1-thinking
openai400,000$1.31 / 1M$10 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5.1-thinking-fast
openai400,000$2.6 / 1M$20 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5.2
openai400,000$1.83 / 1M$14 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5.2-codex
openai400,000$1.83 / 1M$14 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5.2-fast
openai400,000$3.6 / 1M$29 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5.2-pro
openai400,000$22 / 1M$176 / 1Mtool-use, vision, reasoning
openai/gpt-5.3-codex
openai400,000$1.83 / 1M$14 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5.3-codex-fast
openai400,000$3.6 / 1M$29 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5.4
openai1,050,000$2.6 / 1M$15 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5.4-fast
openai1,050,000$5 / 1M$30 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5.4-mini
openai400,000$0.78 / 1M$4.7 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5.4-mini-fast
openai400,000$1.5 / 1M$9 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5.4-nano
openai400,000$0.2 / 1M$1.31 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5.4-pro
openai1,050,000$30 / 1M$180 / 1Mfile-input, reasoning, tool-use
openai/gpt-5.5
openai1,000,000$5 / 1M$30 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5.5-fast
openai1,000,000$13.1 / 1M$78 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-5.5-pro
openai1,000,000$30 / 1M$180 / 1Mreasoning, tool-use, file-input
openai/gpt-5.6-luna
openai1,050,000$0.2 / 1M$1.2 / 1Mreasoning, file-input, tool-use
openai/gpt-5.6-luna-fast
openai1,050,000$0.4 / 1M$2.5 / 1Mreasoning, file-input, tool-use
openai/gpt-5.6-sol
openai1,050,000$4 / 1M$20 / 1Mreasoning, tool-use, implicit-caching
openai/gpt-5.6-sol-fast
openai1,050,000$8 / 1M$40 / 1Mreasoning, tool-use, implicit-caching
openai/gpt-5.6-terra
openai1,050,000$2 / 1M$12 / 1Mreasoning, web-search, file-input
openai/gpt-5.6-terra-fast
openai1,050,000$4 / 1M$25 / 1Mreasoning, web-search, file-input
openai/gpt-6-astra
openai1,050,000$10 / 1M$50 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-6-astra-fast
openai1,050,000$20 / 1M$100 / 1Mfile-input, implicit-caching, reasoning
openai/gpt-6-luna
openai1,050,000$0.1 / 1M$0.5 / 1Mexplicit-caching, file-input, implicit-caching
openai/gpt-6-luna-fast
openai1,050,000$0.2 / 1M$1 / 1Mexplicit-caching, file-input, implicit-caching
openai/gpt-6-sol
openai1,050,000$2 / 1M$10 / 1Mexplicit-caching, file-input, implicit-caching
openai/gpt-6-sol-fast
openai1,050,000$4 / 1M$20 / 1Mexplicit-caching, file-input, implicit-caching
openai/gpt-6.1-sol
openai1,050,000$2 / 1M$10 / 1Mexplicit-caching, file-input, implicit-caching
openai/gpt-6.1-sol-fast
openai1,050,000$4 / 1M$20 / 1Mexplicit-caching, file-input, implicit-caching
openai/gpt-image-1
openai-$5 / 1M$40 / 1Mimage-generation, implicit-caching
openai/gpt-image-1-mini
openai-$2 / 1M$8 / 1Mimage-generation, implicit-caching
openai/gpt-image-1.5
openai-$5 / 1M$33 / 1Mimage-generation, implicit-caching
openai/gpt-image-2
openai-$5 / 1M$30 / 1Mimage-generation, implicit-caching
openai/gpt-image-2.5-flare
openai-$5 / 1M$30 / 1Mimage-generation, implicit-caching
openai/gpt-image-2.5-sunburst
openai-$5 / 1M$30 / 1Mimage-generation, implicit-caching
openai/gpt-live-1
openai---audio-input
openai/gpt-oss-120b
openai131,072$0.1 / 1M$0.5 / 1Mreasoning, tool-use, structured-output
openai/gpt-oss-20b
openai131,072$0.03 / 1M$0.14 / 1Mreasoning, tool-use, structured-output
openai/gpt-oss-safeguard-120b
openai128,000$0.15 / 1M$0.6 / 1Mreasoning, tool-use, structured-output
openai/gpt-oss-safeguard-20b
openai128,000$0.07 / 1M$0.2 / 1Mreasoning, tool-use, structured-output
openai/gpt-realtime-1.5
openai-$4 / 1M$16 / 1M-
openai/gpt-realtime-2
openai-$4 / 1M$25 / 1Mwebsocket-realtime
openai/gpt-realtime-2.1
openai128,000$4 / 1M$25 / 1M-
openai/gpt-realtime-mini
openai-$0.6 / 1M$2.5 / 1M-
openai/gpt-realtime-whisper
openai-$0 / 1M-websocket-realtime, websocket-transcription
openai/o1
openai200,000$15 / 1M$60 / 1Mfile-input, reasoning, tool-use
openai/o3
openai200,000$2 / 1M$8 / 1Mfile-input, implicit-caching, reasoning
openai/o3-fast
openai200,000$3.6 / 1M$14 / 1Mfile-input, implicit-caching, reasoning
openai/o3-mini
openai200,000$1.1 / 1M$4.6 / 1Mimplicit-caching, reasoning, tool-use
openai/o3-pro
openai200,000$20 / 1M$80 / 1Mreasoning, vision, file-input
openai/o4-mini
openai200,000$1.1 / 1M$4.6 / 1Mfile-input, implicit-caching, reasoning
openai/o4-mini-fast
openai200,000$2 / 1M$8 / 1Mfile-input, implicit-caching, reasoning
openai/text-embedding-3-large
openai-$0.13 / 1M--
openai/text-embedding-3-small
openai-$0.02 / 1M--
openai/text-embedding-ada-002
openai-$0.1 / 1M--
openai/tts-1
openai-$15 / 1M--
openai/tts-1-hd
openai-$30 / 1M--
openai/whisper-1
openai-$0 / 1M--
perplexity/pplx-embed-v1-0.6b
perplexity32,000$0 / 1M--
perplexity/pplx-embed-v1-4b
perplexity32,000$0.03 / 1M--
perplexity/sonar
perplexity127,000$0.26 / 1M$2.6 / 1Mvision, web-search, structured-output
poolside/laguna-s-2.1
poolside1,000,000$0.1 / 1M$0.2 / 1Mreasoning, tool-use
poolside/laguna-s-2.1-free
poolside256,000$0 / 1M$0 / 1Mreasoning, tool-use, free
prodia/flux-fast-schnell
prodia512--image-generation
quiverai/arrow-1.1
quiverai131,072--image-generation
quiverai/arrow-2
quiverai131,072$4 / 1M$20 / 1Mtool-use, reasoning, vision
quiverai/arrow-2-telos
quiverai131,072$6 / 1M$30 / 1Mtool-use, reasoning, vision
recraft/recraft-v2
recraft---image-generation
recraft/recraft-v3
recraft---image-generation
recraft/recraft-v4
recraft---image-generation
recraft/recraft-v4-pro
recraft---image-generation
recraft/recraft-v4.1
recraft---image-generation
recraft/recraft-v4.1-flash
recraft---image-generation
recraft/recraft-v4.1-pro
recraft---image-generation
recraft/recraft-v4.1-utility
recraft---image-generation
recraft/recraft-v4.1-utility-pro
recraft---image-generation
sakana/fugu-max
sakana1,000,000$2 / 1M$6 / 1Mreasoning, tool-use, vision
sakana/fugu-ultra
sakana1,000,000$5 / 1M$30 / 1Mvision, tool-use, reasoning
sakana/fugu-ultra-v2
sakana1,000,000$5 / 1M$30 / 1Mreasoning, tool-use, vision
sakana/namazu
sakana256,000$0.99 / 1M$4 / 1Mvision, file-input, implicit-caching
spacexai/grok-4.1-fast-non-reasoning
spacexai1,000,000$0.2 / 1M$0.5 / 1Mtool-use, file-input, vision
spacexai/grok-4.1-fast-reasoning
spacexai1,000,000$0.2 / 1M$0.5 / 1Mreasoning, file-input, vision
spacexai/grok-4.20-multi-agent
spacexai2,000,000$1.31 / 1M$2.6 / 1Mreasoning, tool-use, implicit-caching
spacexai/grok-4.20-multi-agent-beta
spacexai2,000,000$1.31 / 1M$2.6 / 1Mreasoning, tool-use, implicit-caching
spacexai/grok-4.20-non-reasoning
spacexai2,000,000$1.31 / 1M$2.6 / 1Mtool-use, implicit-caching, file-input
spacexai/grok-4.20-non-reasoning-beta
spacexai2,000,000$1.31 / 1M$2.6 / 1Mtool-use, implicit-caching, vision
spacexai/grok-4.20-reasoning
spacexai2,000,000$1.31 / 1M$2.6 / 1Mreasoning, tool-use, implicit-caching
spacexai/grok-4.20-reasoning-beta
spacexai2,000,000$1.31 / 1M$2.6 / 1Mreasoning, tool-use, vision
spacexai/grok-4.3
spacexai1,000,000$1.31 / 1M$2.6 / 1Mreasoning, tool-use, implicit-caching
spacexai/grok-4.5
spacexai500,000$2 / 1M$6 / 1Mreasoning, tool-use, implicit-caching
spacexai/grok-4.6
spacexai500,000$2 / 1M$6 / 1Mreasoning, tool-use, implicit-caching
spacexai/grok-4.7
spacexai500,000$2 / 1M$6 / 1Mreasoning, tool-use, implicit-caching
spacexai/grok-build-0.1
spacexai256,000$1 / 1M$2 / 1Mreasoning, implicit-caching, vision
spacexai/grok-imagine-image
spacexai---image-generation
spacexai/grok-imagine-image-2.0
spacexai---image-generation
spacexai/grok-imagine-video
spacexai----
spacexai/grok-imagine-video-1.5
spacexai----
spacexai/grok-imagine-video-1.5-lite
spacexai----
spacexai/grok-stt
spacexai-$0 / 1M-websocket-transcription
spacexai/grok-tts
spacexai-$15 / 1M--
spacexai/grok-voice-think-fast-1.0
spacexai----
spacexai/grok-voice-think-fast-2.0
spacexai----
stepfun/step-3.5-flash
stepfun262,114$0.09 / 1M$0.3 / 1Mreasoning, tool-use, implicit-caching
stepfun/step-3.7-flash
stepfun256,000$0.2 / 1M$1.2 / 1Mimplicit-caching, reasoning, tool-use
stepfun/step-5-preview
stepfun1,000,000$1 / 1M$2.8 / 1Mimplicit-caching, vision, structured-output
tencent/hy-mt2-lite
tencent8,000$0.05 / 1M$0.18 / 1M-
tencent/hy-mt2-plus
tencent8,000$0.08 / 1M$0.31 / 1Mstructured-output
tencent/hy-mt2-pro
tencent8,000$0.08 / 1M$0.31 / 1Mstructured-output
tencent/hy3
tencent262,144$0.14 / 1M$0.6 / 1Mimplicit-caching, reasoning, tool-use
tencent/hy4-preview
tencent1,024,000$0.88 / 1M$2.63 / 1Mreasoning, tool-use, implicit-caching
thinkingmachines/inkling
thinkingmachines256,000$1 / 1M$4.25 / 1Mimplicit-caching, reasoning, structured-output
thinkingmachines/inkling-small
thinkingmachines1,000,000$0.47 / 1M$1.2 / 1Mreasoning, tool-use, vision
typesafe-ai/jev
typesafe-ai32,000$0.04 / 1M$0 / 1M-
voyage/rerank-2.5
voyage32,000$0.05 / 1M--
voyage/rerank-2.5-lite
voyage32,000$0.02 / 1M--
voyage/rerank-3
voyage32,000$0.05 / 1M--
voyage/rerank-3-lite
voyage32,000$0.02 / 1M--
voyage/voyage-3-large
voyage-$0.18 / 1M--
voyage/voyage-3.5
voyage-$0.06 / 1M--
voyage/voyage-3.5-lite
voyage-$0.02 / 1M--
voyage/voyage-4
voyage32,000$0.06 / 1M--
voyage/voyage-4-large
voyage32,000$0.12 / 1M--
voyage/voyage-4-lite
voyage32,000$0.02 / 1M--
voyage/voyage-code-2
voyage-$0.12 / 1M--
voyage/voyage-code-3
voyage-$0.18 / 1M--
voyage/voyage-finance-2
voyage-$0.12 / 1M--
voyage/voyage-law-2
voyage-$0.12 / 1M--
xiaomi/mimo-v2.5
xiaomi1,050,000$0.14 / 1M$0.29 / 1Mreasoning, tool-use, implicit-caching
xiaomi/mimo-v2.5-pro
xiaomi1,050,000$0.46 / 1M$0.91 / 1Mreasoning, tool-use, implicit-caching
xiaomi/mimo-v2.6-flash
xiaomi1,048,576$0.04 / 1M$1.34 / 1Maudio-input, implicit-caching, reasoning
xiaomi/mimo-v2.6-pro
xiaomi1,048,576$0.46 / 1M$0.91 / 1Maudio-input, implicit-caching, reasoning
xiaomi/mimo-v2.6-pro-ultraspeed
xiaomi1,048,576$4.56 / 1M$9.1 / 1Maudio-input, implicit-caching, reasoning
zai/glm-4.5
zai128,000$0.6 / 1M$2.3 / 1Mreasoning, tool-use, implicit-caching
zai/glm-4.5-air
zai128,000$0.2 / 1M$1.1 / 1Mreasoning, tool-use, implicit-caching
zai/glm-4.5v
zai66,000$0.6 / 1M$1.8 / 1Mimplicit-caching, reasoning, tool-use
zai/glm-4.6
zai200,000$0.6 / 1M$2.3 / 1Mimplicit-caching, reasoning, tool-use
zai/glm-4.7
zai200,000$0.6 / 1M$2.3 / 1Mreasoning, tool-use, structured-output
zai/glm-4.7-flash
zai200,000$0.07 / 1M$0.4 / 1Mreasoning, tool-use, structured-output
zai/glm-4.7-flashx
zai200,000$0.06 / 1M$0.4 / 1Mreasoning, tool-use, implicit-caching
zai/glm-5
zai202,800$1 / 1M$3.3 / 1Mreasoning, tool-use, structured-output
zai/glm-5-turbo
zai202,800$1.2 / 1M$4 / 1Mreasoning, tool-use, implicit-caching
zai/glm-5.1
zai202,800$1.4 / 1M$4.6 / 1Mimplicit-caching, reasoning, tool-use
zai/glm-5.2
zai1,000,000$0.8 / 1M$2.67 / 1Mreasoning, tool-use, implicit-caching
zai/glm-5.2-fast
zai1,000,000$2.9 / 1M$9.2 / 1Mreasoning, tool-use, implicit-caching
zai/glm-5.3
zai1,000,000$1.4 / 1M$4.6 / 1Mimplicit-caching, reasoning, tool-use
zai/glm-5.3-fast
zai1,048,576$2.2 / 1M$6.9 / 1Mreasoning, tool-use, implicit-caching
zai/glm-5.3-flash
zai1,000,000$0.15 / 1M$0.5 / 1Mreasoning, tool-use, implicit-caching
zai/glm-5.3-flashx
zai1,000,000$0.38 / 1M$1.31 / 1Mreasoning, tool-use, implicit-caching
zai/glm-5v-turbo
zai200,000$1.2 / 1M$4 / 1Mreasoning, tool-use, implicit-caching

LLM-friendly endpoints

LLMs can read structured documentation at /llm.txt. Use it for agent discovery and machine-readable setup instructions.

Quick endpoints
OpenAI-compatible surface
GET /llm.txt GET /v1/models POST /v1/chat/completions GET /v1/balance/:wallet POST /v1/deposit (x402)