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.
Everything is optimized for autonomous tooling: predictable headers, explicit pricing, and a clean OpenAI-compatible surface area.
Agents attach a wallet once, then spend pre-funded credits. No per-request signing, no brittle payment steps, no human-in-the-loop.
We mirror Vercel AI Gateway pricing and apply a visible 5% markup. The models table below is exactly what your agent is billed.
Global per-model token counters keep capacity planning honest. Headers tell agents their remaining balance after every call.
Designed for scripts, SDKs, and autonomous frameworks. No UI required.
Use the bundled skills installer when it ships. Placeholder below.
Point your OpenAI-compatible client to the gateway.
Call POST /v1/deposit to get x402 payment requirements, then sign with your wallet.
Every request includes your wallet header for credit accounting.
Agents can react to headers when credits run low.
| Tags | |||||
|---|---|---|---|---|---|
alibaba/qwen-3-14b | alibaba | 40,960 | $0.12 / 1M | $0.25 / 1M | reasoning, tool-use |
alibaba/qwen-3-235b | alibaba | 40,960 | $0.07 / 1M | $0.49 / 1M | tool-use |
alibaba/qwen-3-30b | alibaba | 40,960 | $0.08 / 1M | $0.3 / 1M | reasoning, tool-use |
alibaba/qwen-3-32b | alibaba | 131,072 | $0.3 / 1M | $0.61 / 1M | reasoning, tool-use |
alibaba/qwen3-235b-a22b-thinking | alibaba | 262,114 | $0.24 / 1M | $2.4 / 1M | tool-use, vision, file-input |
alibaba/qwen3-coder | alibaba | 262,144 | $0.4 / 1M | $1.6 / 1M | tool-use |
alibaba/qwen3-coder-30b-a3b | alibaba | 262,144 | $0.15 / 1M | $0.6 / 1M | reasoning, tool-use |
alibaba/qwen3-coder-next | alibaba | 256,000 | $0.5 / 1M | $1.2 / 1M | tool-use |
alibaba/qwen3-coder-plus | alibaba | 1,000,000 | $1 / 1M | $5 / 1M | tool-use |
alibaba/qwen3-embedding-0.6b | alibaba | 32,768 | $0.01 / 1M | - | |
alibaba/qwen3-embedding-4b | alibaba | 32,768 | $0.02 / 1M | - | |
alibaba/qwen3-embedding-8b | alibaba | 32,768 | $0.05 / 1M | - | |
alibaba/qwen3-max | alibaba | 262,144 | $1.2 / 1M | $6 / 1M | tool-use, implicit-caching |
alibaba/qwen3-max-preview | alibaba | 262,144 | $1.2 / 1M | $6 / 1M | tool-use, implicit-caching |
alibaba/qwen3-max-thinking | alibaba | 256,000 | $1.2 / 1M | $6 / 1M | reasoning, tool-use, implicit-caching |
alibaba/qwen3-next-80b-a3b-instruct | alibaba | 262,144 | $0.09 / 1M | $1.1 / 1M | |
alibaba/qwen3-next-80b-a3b-thinking | alibaba | 131,072 | $0.15 / 1M | $1.2 / 1M | - |
alibaba/qwen3-vl-instruct | alibaba | 262,144 | $0.2 / 1M | $0.92 / 1M | vision, file-input |
alibaba/qwen3-vl-thinking | alibaba | 256,000 | $0.23 / 1M | $0.92 / 1M | vision, reasoning, tool-use |
alibaba/qwen3.5-flash | alibaba | 1,000,000 | $0.1 / 1M | $0.4 / 1M | vision, file-input, reasoning |
alibaba/qwen3.5-plus | alibaba | 1,000,000 | $0.4 / 1M | $2.5 / 1M | vision, file-input, reasoning |
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 | - | - | - | |
amazon/nova-2-lite | amazon | 1,000,000 | $0.3 / 1M | $2.6 / 1M | reasoning, vision |
amazon/nova-lite | amazon | 300,000 | $0.06 / 1M | $0.25 / 1M | - |
amazon/nova-micro | amazon | 128,000 | $0.04 / 1M | $0.14 / 1M | - |
amazon/nova-pro | amazon | 300,000 | $0.8 / 1M | $3.3 / 1M | - |
amazon/titan-embed-text-v2 | amazon | - | $0.02 / 1M | - | - |
anthropic/claude-3-haiku | anthropic | 200,000 | $0.26 / 1M | $1.31 / 1M | tool-use, vision |
anthropic/claude-3-opus | anthropic | 200,000 | $15 / 1M | $78 / 1M | |
anthropic/claude-3.5-haiku | anthropic | 200,000 | $0.8 / 1M | $4 / 1M | file-input, tool-use, vision |
anthropic/claude-3.5-sonnet | anthropic | 200,000 | $3 / 1M | $15 / 1M | file-input, tool-use, vision |
anthropic/claude-3.5-sonnet-20240620 | anthropic | 200,000 | $3 / 1M | $15 / 1M | file-input, tool-use, vision |
anthropic/claude-3.7-sonnet | anthropic | 200,000 | $3 / 1M | $15 / 1M | file-input, reasoning, tool-use |
anthropic/claude-haiku-4.5 | anthropic | 200,000 | $1 / 1M | $5 / 1M | file-input, reasoning, tool-use |
anthropic/claude-opus-4 | anthropic | 200,000 | $15 / 1M | $78 / 1M | file-input, reasoning, tool-use |
anthropic/claude-opus-4.1 | anthropic | 200,000 | $15 / 1M | $78 / 1M | file-input, reasoning, tool-use |
anthropic/claude-opus-4.5 | anthropic | 200,000 | $5 / 1M | $26 / 1M | tool-use, reasoning, vision |
anthropic/claude-opus-4.6 | anthropic | 1,000,000 | $5 / 1M | $26 / 1M | tool-use, reasoning, vision |
anthropic/claude-sonnet-4 | anthropic | 1,000,000 | $3 / 1M | $15 / 1M | file-input, reasoning, tool-use |
anthropic/claude-sonnet-4.5 | anthropic | 1,000,000 | $3 / 1M | $15 / 1M | file-input, reasoning, tool-use |
anthropic/claude-sonnet-4.6 | anthropic | 1,000,000 | $3 / 1M | $15 / 1M | file-input, reasoning, tool-use |
arcee-ai/trinity-large-preview | arcee-ai | 131,000 | $0.26 / 1M | $1 / 1M | tool-use |
arcee-ai/trinity-mini | arcee-ai | 131,072 | $0.05 / 1M | $0.15 / 1M | |
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 | bfl | 67,300 | - | - | image-generation |
bfl/flux-2-pro | bfl | 67,300 | - | - | image-generation |
bfl/flux-kontext-max | bfl | 512 | - | - | image-generation |
bfl/flux-kontext-pro | bfl | 512 | - | - | 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 | bytedance | 256,000 | $0.26 / 1M | $2 / 1M | reasoning, tool-use, implicit-caching |
bytedance/seed-1.8 | bytedance | 256,000 | $0.26 / 1M | $2 / 1M | reasoning, vision, implicit-caching |
bytedance/seedance-v1.0-lite-i2v | bytedance | - | - | - | |
bytedance/seedance-v1.0-lite-t2v | bytedance | - | - | - | |
bytedance/seedance-v1.0-pro | bytedance | - | - | - | |
bytedance/seedance-v1.0-pro-fast | bytedance | - | - | - | |
bytedance/seedance-v1.5-pro | bytedance | - | - | - | |
cohere/command-a | cohere | 256,000 | $2.6 / 1M | $10 / 1M | tool-use |
cohere/embed-v4.0 | cohere | - | $0.12 / 1M | - | - |
deepseek/deepseek-r1 | deepseek | 128,000 | $1.41 / 1M | $5.6 / 1M | reasoning, tool-use |
deepseek/deepseek-v3 | deepseek | 163,840 | $0.8 / 1M | $0.8 / 1M | tool-use |
deepseek/deepseek-v3.1 | deepseek | 163,840 | $0.5 / 1M | $1.5 / 1M | reasoning, tool-use |
deepseek/deepseek-v3.1-terminus | deepseek | 131,072 | $0.28 / 1M | $1 / 1M | reasoning, tool-use |
deepseek/deepseek-v3.2 | deepseek | 128,000 | $0.29 / 1M | $0.44 / 1M | tool-use, implicit-caching |
deepseek/deepseek-v3.2-thinking | deepseek | 128,000 | $0.29 / 1M | $0.44 / 1M | reasoning, tool-use, implicit-caching |
google/gemini-2.0-flash | 1,048,576 | $0.15 / 1M | $0.6 / 1M | file-input, tool-use, vision | |
google/gemini-2.0-flash-lite | 1,048,576 | $0.08 / 1M | $0.3 / 1M | file-input, tool-use, vision | |
google/gemini-2.5-flash | 1,000,000 | $0.3 / 1M | $2.6 / 1M | file-input, reasoning, tool-use | |
google/gemini-2.5-flash-image | 32,768 | $0.3 / 1M | $2.6 / 1M | image-generation | |
google/gemini-2.5-flash-lite | 1,048,576 | $0.1 / 1M | $0.4 / 1M | file-input, reasoning, tool-use | |
google/gemini-2.5-pro | 1,048,576 | $1.31 / 1M | $10 / 1M | file-input, reasoning, tool-use | |
google/gemini-3-flash | 1,000,000 | $0.5 / 1M | $3 / 1M | reasoning, tool-use, file-input | |
google/gemini-3-pro-image | 65,536 | $2 / 1M | $12 / 1M | image-generation | |
google/gemini-3-pro-preview | 1,000,000 | $2 / 1M | $12 / 1M | file-input, tool-use, reasoning | |
google/gemini-3.1-flash-image-preview | 131,072 | $0.5 / 1M | $3 / 1M | image-generation, vision, reasoning | |
google/gemini-3.1-flash-lite-preview | 1,000,000 | $0.26 / 1M | $1.5 / 1M | reasoning, tool-use, implicit-caching | |
google/gemini-3.1-pro-preview | 1,000,000 | $2 / 1M | $12 / 1M | file-input, tool-use, reasoning | |
google/gemini-embedding-001 | - | $0.15 / 1M | - | - | |
google/gemini-embedding-2 | - | $0.2 / 1M | - | ||
google/imagen-4.0-fast-generate-001 | 480 | - | - | image-generation | |
google/imagen-4.0-generate-001 | 480 | - | - | image-generation | |
google/imagen-4.0-ultra-generate-001 | 480 | - | - | image-generation | |
google/text-embedding-005 | - | $0.03 / 1M | - | - | |
google/text-multilingual-embedding-002 | - | $0.03 / 1M | - | - | |
google/veo-3.0-fast-generate-001 | - | - | - | ||
google/veo-3.0-generate-001 | - | - | - | ||
google/veo-3.1-fast-generate-001 | - | - | - | ||
google/veo-3.1-generate-001 | - | - | - | ||
inception/mercury-2 | inception | 128,000 | $0.26 / 1M | $0.78 / 1M | tool-use, reasoning |
inception/mercury-coder-small | inception | 32,000 | $0.26 / 1M | $1 / 1M | 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-t2v | klingai | - | - | - | |
kwaipilot/kat-coder-pro-v1 | kwaipilot | 256,000 | $0.03 / 1M | $1.2 / 1M | reasoning |
meituan/longcat-flash-chat | meituan | 128,000 | - | - | tool-use |
meituan/longcat-flash-thinking | meituan | 128,000 | $0.15 / 1M | $1.5 / 1M | reasoning, tool-use |
meituan/longcat-flash-thinking-2601 | meituan | 32,768 | - | - | reasoning |
meta/llama-3.1-70b | meta | 128,000 | $0.75 / 1M | $0.75 / 1M | tool-use |
meta/llama-3.1-8b | meta | 128,000 | $0.1 / 1M | $0.1 / 1M | tool-use |
meta/llama-3.2-11b | meta | 128,000 | $0.16 / 1M | $0.16 / 1M | tool-use, vision |
meta/llama-3.2-1b | meta | 128,000 | $0.1 / 1M | $0.1 / 1M | - |
meta/llama-3.2-3b | meta | 128,000 | $0.15 / 1M | $0.15 / 1M | - |
meta/llama-3.2-90b | meta | 128,000 | $0.75 / 1M | $0.75 / 1M | tool-use, vision |
meta/llama-3.3-70b | meta | 128,000 | $0.75 / 1M | $0.75 / 1M | tool-use |
meta/llama-4-maverick | meta | 128,000 | $0.25 / 1M | $1.01 / 1M | tool-use, vision |
meta/llama-4-scout | meta | 128,000 | $0.17 / 1M | $0.69 / 1M | tool-use, vision |
minimax/minimax-m2 | minimax | 205,000 | $0.3 / 1M | $1.2 / 1M | reasoning, tool-use, implicit-caching |
minimax/minimax-m2.1 | minimax | 204,800 | $0.3 / 1M | $1.2 / 1M | reasoning, tool-use, implicit-caching |
minimax/minimax-m2.1-lightning | minimax | 204,800 | $0.3 / 1M | $2.5 / 1M | reasoning, tool-use, implicit-caching |
minimax/minimax-m2.5 | minimax | 204,800 | $0.3 / 1M | $1.2 / 1M | reasoning, tool-use, implicit-caching |
minimax/minimax-m2.5-highspeed | minimax | 204,800 | $0.6 / 1M | $2.5 / 1M | reasoning, tool-use, implicit-caching |
minimax/minimax-m2.7 | minimax | 204,800 | $0.3 / 1M | $1.2 / 1M | reasoning, tool-use, implicit-caching |
minimax/minimax-m2.7-highspeed | minimax | 204,800 | $0.6 / 1M | $2.5 / 1M | reasoning, tool-use, implicit-caching |
mistral/codestral | mistral | 128,000 | $0.3 / 1M | $0.9 / 1M | tool-use |
mistral/codestral-embed | mistral | - | $0.15 / 1M | - | - |
mistral/devstral-2 | mistral | 256,000 | $0.4 / 1M | $2 / 1M | tool-use |
mistral/devstral-small | mistral | 128,000 | $0.1 / 1M | $0.3 / 1M | tool-use |
mistral/devstral-small-2 | mistral | 256,000 | $0.1 / 1M | $0.3 / 1M | tool-use |
mistral/magistral-medium | mistral | 128,000 | $2 / 1M | $5 / 1M | reasoning, vision |
mistral/magistral-small | mistral | 128,000 | $0.5 / 1M | $1.5 / 1M | reasoning, vision |
mistral/ministral-14b | mistral | 256,000 | $0.2 / 1M | $0.2 / 1M | vision, file-input |
mistral/ministral-3b | mistral | 128,000 | $0.1 / 1M | $0.1 / 1M | tool-use |
mistral/ministral-8b | mistral | 128,000 | $0.15 / 1M | $0.15 / 1M | tool-use |
mistral/mistral-embed | mistral | - | $0.1 / 1M | - | - |
mistral/mistral-large-3 | mistral | 256,000 | $0.5 / 1M | $1.5 / 1M | vision |
mistral/mistral-medium | mistral | 128,000 | $0.4 / 1M | $2 / 1M | tool-use, vision |
mistral/mistral-nemo | mistral | 128,000 | $0.15 / 1M | $0.15 / 1M | |
mistral/mistral-small | mistral | 32,000 | $0.1 / 1M | $0.3 / 1M | tool-use, vision |
mistral/mixtral-8x22b-instruct | mistral | 65,536 | $1.2 / 1M | $1.2 / 1M | - |
mistral/pixtral-12b | mistral | 128,000 | $0.15 / 1M | $0.15 / 1M | tool-use, vision |
mistral/pixtral-large | mistral | 128,000 | $2 / 1M | $6 / 1M | tool-use, vision |
moonshotai/kimi-k2 | moonshotai | 131,072 | $0.6 / 1M | $2.6 / 1M | implicit-caching, tool-use |
moonshotai/kimi-k2-0905 | moonshotai | 256,000 | $0.6 / 1M | $2.6 / 1M | implicit-caching, tool-use |
moonshotai/kimi-k2-thinking | moonshotai | 262,114 | $0.6 / 1M | $2.6 / 1M | reasoning, tool-use, implicit-caching |
moonshotai/kimi-k2-thinking-turbo | moonshotai | 262,114 | $1.2 / 1M | $8 / 1M | reasoning, tool-use, implicit-caching |
moonshotai/kimi-k2-turbo | moonshotai | 256,000 | $1.2 / 1M | $8 / 1M | tool-use |
moonshotai/kimi-k2.5 | moonshotai | 262,114 | $0.6 / 1M | $3 / 1M | reasoning, vision, tool-use |
morph/morph-v3-fast | morph | 81,920 | $0.8 / 1M | $1.2 / 1M | - |
morph/morph-v3-large | morph | 81,920 | $0.9 / 1M | $1.9 / 1M | - |
nvidia/nemotron-3-nano-30b-a3b | nvidia | 262,144 | $0.05 / 1M | $0.25 / 1M | reasoning |
nvidia/nemotron-nano-12b-v2-vl | nvidia | 131,072 | $0.2 / 1M | $0.6 / 1M | vision, reasoning, tool-use |
nvidia/nemotron-nano-9b-v2 | nvidia | 131,072 | $0.06 / 1M | $0.24 / 1M | reasoning, tool-use |
openai/gpt-3.5-turbo | openai | 16,385 | $0.5 / 1M | $1.5 / 1M | - |
openai/gpt-3.5-turbo-instruct | openai | 8,192 | $1.5 / 1M | $2 / 1M | - |
openai/gpt-4-turbo | openai | 128,000 | $10 / 1M | $30 / 1M | tool-use, vision |
openai/gpt-4.1 | openai | 1,047,576 | $2 / 1M | $8 / 1M | file-input, tool-use, vision |
openai/gpt-4.1-mini | openai | 1,047,576 | $0.4 / 1M | $1.6 / 1M | file-input, tool-use, vision |
openai/gpt-4.1-nano | openai | 1,047,576 | $0.1 / 1M | $0.4 / 1M | file-input, tool-use, vision |
openai/gpt-4o | openai | 128,000 | $2.6 / 1M | $10 / 1M | file-input, tool-use, vision |
openai/gpt-4o-mini | openai | 128,000 | $0.15 / 1M | $0.6 / 1M | file-input, tool-use, vision |
openai/gpt-4o-mini-search-preview | openai | 128,000 | $0.15 / 1M | $0.6 / 1M | |
openai/gpt-5 | openai | 400,000 | $1.31 / 1M | $10 / 1M | file-input, implicit-caching, reasoning |
openai/gpt-5-chat | openai | 128,000 | $1.31 / 1M | $10 / 1M | tool-use, implicit-caching, file-input |
openai/gpt-5-codex | openai | 400,000 | $1.31 / 1M | $10 / 1M | file-input, implicit-caching, reasoning |
openai/gpt-5-mini | openai | 400,000 | $0.26 / 1M | $2 / 1M | file-input, implicit-caching, reasoning |
openai/gpt-5-nano | openai | 400,000 | $0.05 / 1M | $0.4 / 1M | file-input, implicit-caching, reasoning |
openai/gpt-5-pro | openai | 400,000 | $15 / 1M | $120 / 1M | file-input, implicit-caching, reasoning |
openai/gpt-5.1-codex | openai | 400,000 | $1.31 / 1M | $10 / 1M | file-input, tool-use, reasoning |
openai/gpt-5.1-codex-max | openai | 400,000 | $1.31 / 1M | $10 / 1M | reasoning, file-input, tool-use |
openai/gpt-5.1-codex-mini | openai | 400,000 | $0.26 / 1M | $2 / 1M | reasoning, file-input, vision |
openai/gpt-5.1-instant | openai | 128,000 | $1.31 / 1M | $10 / 1M | tool-use, vision, file-input |
openai/gpt-5.1-thinking | openai | 400,000 | $1.31 / 1M | $10 / 1M | tool-use, implicit-caching, file-input |
openai/gpt-5.2 | openai | 400,000 | $1.83 / 1M | $14 / 1M | tool-use, vision, file-input |
openai/gpt-5.2-chat | openai | 128,000 | $1.83 / 1M | $14 / 1M | vision, file-input, tool-use |
openai/gpt-5.2-codex | openai | 400,000 | $1.83 / 1M | $14 / 1M | file-input, tool-use, reasoning |
openai/gpt-5.2-pro | openai | 400,000 | $22 / 1M | $176 / 1M | tool-use, vision, implicit-caching |
openai/gpt-5.3-chat | openai | 128,000 | $1.83 / 1M | $14 / 1M | vision, file-input, tool-use |
openai/gpt-5.3-codex | openai | 400,000 | $1.83 / 1M | $14 / 1M | reasoning, tool-use, file-input |
openai/gpt-5.4 | openai | 1,050,000 | $2.6 / 1M | $15 / 1M | reasoning, tool-use, vision |
openai/gpt-5.4-mini | openai | 400,000 | $0.78 / 1M | $4.7 / 1M | reasoning, tool-use, vision |
openai/gpt-5.4-nano | openai | 400,000 | $0.2 / 1M | $1.31 / 1M | reasoning, tool-use, implicit-caching |
openai/gpt-5.4-pro | openai | 1,050,000 | $30 / 1M | $180 / 1M | reasoning, tool-use, vision |
openai/gpt-image-1 | openai | - | $5 / 1M | $40 / 1M | image-generation |
openai/gpt-image-1-mini | openai | - | $2 / 1M | $8 / 1M | image-generation |
openai/gpt-image-1.5 | openai | - | $5 / 1M | $33 / 1M | image-generation |
openai/gpt-oss-120b | openai | 131,072 | $0.36 / 1M | $0.78 / 1M | implicit-caching |
openai/gpt-oss-20b | openai | 128,000 | $0.07 / 1M | $0.3 / 1M | reasoning, tool-use |
openai/gpt-oss-safeguard-20b | openai | 131,072 | $0.08 / 1M | $0.3 / 1M | reasoning, tool-use |
openai/o1 | openai | 200,000 | $15 / 1M | $60 / 1M | file-input, reasoning, tool-use |
openai/o3 | openai | 200,000 | $2 / 1M | $8 / 1M | file-input, reasoning, tool-use |
openai/o3-deep-research | openai | 200,000 | $10 / 1M | $40 / 1M | reasoning, file-input, tool-use |
openai/o3-mini | openai | 200,000 | $1.1 / 1M | $4.6 / 1M | reasoning, tool-use, implicit-caching |
openai/o3-pro | openai | 200,000 | $20 / 1M | $80 / 1M | reasoning, vision, file-input |
openai/o4-mini | openai | 200,000 | $1.1 / 1M | $4.6 / 1M | file-input, reasoning, tool-use |
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 | - | - |
perplexity/sonar | perplexity | 127,000 | - | - | tool-use, vision |
perplexity/sonar-pro | perplexity | 200,000 | - | - | tool-use, vision |
perplexity/sonar-reasoning-pro | perplexity | 127,000 | - | - | reasoning |
prime-intellect/intellect-3 | prime-intellect | 131,072 | $0.2 / 1M | $1.1 / 1M | reasoning, tool-use |
prodia/flux-fast-schnell | prodia | 512 | - | - | image-generation |
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 |
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 | voyage | 32,000 | $0.06 / 1M | - | |
voyage/voyage-4-large | voyage | 32,000 | $0.12 / 1M | - | |
voyage/voyage-4-lite | voyage | 32,000 | $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 | - | - |
xai/grok-2-vision | xai | 32,768 | $2 / 1M | $10 / 1M | tool-use, vision |
xai/grok-3 | xai | 131,072 | $3 / 1M | $15 / 1M | tool-use |
xai/grok-3-fast | xai | 131,072 | $5 / 1M | $26 / 1M | tool-use |
xai/grok-3-mini | xai | 131,072 | $0.3 / 1M | $0.5 / 1M | tool-use |
xai/grok-3-mini-fast | xai | 131,072 | $0.6 / 1M | $4 / 1M | tool-use |
xai/grok-4 | xai | 256,000 | $3 / 1M | $15 / 1M | reasoning, tool-use, vision |
xai/grok-4-fast-non-reasoning | xai | 2,000,000 | $0.2 / 1M | $0.5 / 1M | tool-use, implicit-caching |
xai/grok-4-fast-reasoning | xai | 2,000,000 | $0.2 / 1M | $0.5 / 1M | reasoning, tool-use, implicit-caching |
xai/grok-4.1-fast-non-reasoning | xai | 2,000,000 | $0.2 / 1M | $0.5 / 1M | tool-use, implicit-caching |
xai/grok-4.1-fast-reasoning | xai | 2,000,000 | $0.2 / 1M | $0.5 / 1M | reasoning, tool-use, implicit-caching |
xai/grok-4.20-multi-agent | xai | 2,000,000 | $2 / 1M | $6 / 1M | reasoning, tool-use, implicit-caching |
xai/grok-4.20-multi-agent-beta | xai | 2,000,000 | $2 / 1M | $6 / 1M | reasoning, tool-use, implicit-caching |
xai/grok-4.20-non-reasoning | xai | 2,000,000 | $2 / 1M | $6 / 1M | tool-use, implicit-caching, vision |
xai/grok-4.20-non-reasoning-beta | xai | 2,000,000 | $2 / 1M | $6 / 1M | tool-use, implicit-caching, vision |
xai/grok-4.20-reasoning | xai | 2,000,000 | $2 / 1M | $6 / 1M | reasoning, vision, tool-use |
xai/grok-4.20-reasoning-beta | xai | 2,000,000 | $2 / 1M | $6 / 1M | reasoning, tool-use, vision |
xai/grok-code-fast-1 | xai | 256,000 | $0.2 / 1M | $1.5 / 1M | reasoning, tool-use, implicit-caching |
xai/grok-imagine-image | xai | - | - | - | image-generation |
xai/grok-imagine-image-pro | xai | - | - | - | |
xai/grok-imagine-video | xai | - | - | - | |
xiaomi/mimo-v2-flash | xiaomi | 262,144 | $0.1 / 1M | $0.3 / 1M | reasoning, tool-use |
xiaomi/mimo-v2-pro | xiaomi | 1,000,000 | $1 / 1M | $3 / 1M | reasoning, tool-use |
zai/glm-4.5 | zai | 128,000 | $0.6 / 1M | $2.3 / 1M | reasoning, tool-use, implicit-caching |
zai/glm-4.5-air | zai | 128,000 | $0.2 / 1M | $1.1 / 1M | reasoning, tool-use, implicit-caching |
zai/glm-4.5v | zai | 66,000 | $0.6 / 1M | $1.8 / 1M | tool-use, vision, implicit-caching |
zai/glm-4.6 | zai | 200,000 | $0.6 / 1M | $2.3 / 1M | reasoning, tool-use, implicit-caching |
zai/glm-4.6v | zai | 128,000 | $0.3 / 1M | $0.9 / 1M | vision, file-input, reasoning |
zai/glm-4.6v-flash | zai | 128,000 | - | - | vision, reasoning, file-input |
zai/glm-4.7 | zai | 200,000 | $0.6 / 1M | $2.3 / 1M | reasoning, tool-use |
zai/glm-4.7-flash | zai | 200,000 | $0.07 / 1M | $0.4 / 1M | reasoning, tool-use |
zai/glm-4.7-flashx | zai | 200,000 | $0.06 / 1M | $0.4 / 1M | reasoning, tool-use, implicit-caching |
zai/glm-5 | zai | 202,800 | $1 / 1M | $3.3 / 1M | reasoning, tool-use, implicit-caching |
zai/glm-5-turbo | zai | 202,800 | $1.2 / 1M | $4 / 1M | reasoning, tool-use, implicit-caching |
LLMs can read structured documentation at /llm.txt. Use it for agent discovery and machine-readable setup instructions.