ModelRig

Models & pricing

Provider list prices for every model in the registry — input, output and cached-input per million tokens (Mtok). Generated from the pinned pricing map with the leaderboard, never hand-authored.

List prices as of 2026-08-19, from the pinned pricing map.

The public face of conformance & cost monitoring: the same probes that rank models in the open watch your own traffic in the console. Conformance & cost monitoring.

List price is not your price. These are provider list prices. Our fee is a flat 2% of usage valued at them; a discount you have negotiated with a provider is yours to keep.

Host lanes are distinct. The same open weights served by two hosts are two entries with two prices — the leading segment of a model's name is the host serving it.

Anthropic

The Claude model family, first-party API.

modelhostinput $/Mtokoutput $/Mtokcached input $/Mtokas oflinks
claude-fable-5Anthropic$10.000$50.000$1.0002026-08-19leaderboard · registry
claude-haiku-4-5Anthropic$1.000$5.000$0.1002026-08-19leaderboard · registry
claude-opus-5Anthropic$5.000$25.000$0.5002026-08-19leaderboard · registry
claude-sonnet-5Anthropic$2.000$10.000$0.2002026-08-19leaderboard · registry

Pricing source: litellm-pricing-map(pinned)+adapter-static

DeepInfra

A GPU host serving open-weight models from several creators.

modelhostinput $/Mtokoutput $/Mtokcached input $/Mtokas oflinks
MiniMaxAI/MiniMax-M3DeepInfra$0.280$1.1002026-08-19leaderboard · registry
Qwen/Qwen3-30B-A3BDeepInfra$0.080$0.2902026-08-19leaderboard · registry
Qwen/Qwen3-Coder-480B-A35B-Instruct-TurboDeepInfra$0.290$1.2002026-08-19leaderboard · registry
google/gemma-4-31B-itDeepInfra$0.130$0.3802026-08-19leaderboard · registry
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8DeepInfra$0.150$0.6002026-08-19leaderboard · registry
meta-llama/Llama-4-Scout-17B-16E-InstructDeepInfra$0.080$0.3002026-08-19leaderboard · registry
mistralai/Mistral-Small-3.2-24B-Instruct-2506DeepInfra$0.075$0.2002026-08-19leaderboard · registry
moonshotai/Kimi-K2.6DeepInfra$0.750$3.5002026-08-19leaderboard · registry
moonshotai/Kimi-K2.7-CodeDeepInfra$0.680$3.4002026-08-19leaderboard · registry
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55BDeepInfra$0.500$2.2002026-08-19leaderboard · registry
openai/gpt-oss-120bDeepInfra$0.050$0.4502026-08-19leaderboard · registry
zai-org/GLM-5.2DeepInfra$0.750$2.4002026-08-19leaderboard · registry

Pricing source: litellm-pricing-map(pinned)+adapter-static

DeepSeek

The DeepSeek model family, first-party API.

modelhostinput $/Mtokoutput $/Mtokcached input $/Mtokas oflinks
deepseek-chatDeepSeek$0.280$0.420$0.0282026-08-19leaderboard · registry
deepseek-reasonerDeepSeek$0.280$0.420$0.0282026-08-19leaderboard · registry
deepseek-v4-flashDeepSeek$0.140$0.280$0.0032026-08-19leaderboard · registry
deepseek-v4-proDeepSeek$0.435$0.870$0.0042026-08-19leaderboard · registry

Pricing source: litellm-pricing-map(pinned)+adapter-static

Fireworks AI

A GPU host serving open-weight models from several creators.

modelhostinput $/Mtokoutput $/Mtokcached input $/Mtokas oflinks
glm-5p2Fireworks AI$1.400$4.400$0.1402026-08-19leaderboard · registry
gpt-oss-120bFireworks AI$0.150$0.600$0.0152026-08-19leaderboard · registry
kimi-k3Fireworks AI$3.000$15.000$0.3002026-08-19leaderboard · registry

Pricing source: litellm-pricing-map(pinned)+adapter-static

Google

The Gemini model family, via the Gemini API.

modelhostinput $/Mtokoutput $/Mtokcached input $/Mtokas oflinks
gemini-2.5-flashGoogle$0.300$2.500$0.0302026-08-19leaderboard · registry
gemini-3-flash-previewGoogle$0.500$3.000$0.0502026-08-19leaderboard · registry
gemini-3.1-flash-liteGoogle$0.250$1.500$0.0252026-08-19leaderboard · registry
gemini-3.1-pro-previewGoogle$2.000$12.000$0.2002026-08-19leaderboard · registry

Pricing source: litellm-pricing-map(pinned)+adapter-static

OpenAI

The GPT model family, first-party API.

modelhostinput $/Mtokoutput $/Mtokcached input $/Mtokas oflinks
gpt-5-miniOpenAI$0.250$2.000$0.0252026-08-19leaderboard · registry
gpt-5.2OpenAI$1.750$14.000$0.1752026-08-19leaderboard · registry
gpt-5.4OpenAI$2.500$15.000$0.2502026-08-19leaderboard · registry
gpt-5.4-miniOpenAI$0.750$4.500$0.0752026-08-19leaderboard · registry
gpt-5.4-nanoOpenAI$0.200$1.250$0.0202026-08-19leaderboard · registry
gpt-5.5OpenAI$5.000$30.000$0.5002026-08-19leaderboard · registry
gpt-5.5-proOpenAI$30.000$180.000$3.0002026-08-19leaderboard · registry

Pricing source: litellm-pricing-map(pinned)+adapter-static

xAI

The Grok model family, first-party API.

modelhostinput $/Mtokoutput $/Mtokcached input $/Mtokas oflinks
grok-4-1-fastxAI$0.200$0.500$0.0502026-08-19leaderboard · registry
grok-4.3xAI$1.250$2.500$0.2002026-08-19leaderboard · registry
grok-4.5xAI$2.000$6.000$0.5002026-08-19leaderboard · registry

Pricing source: litellm-pricing-map(pinned)+adapter-static

data as of 2026-08-19 · vintage 2026-08-19T14:18:42.501Z · live @ 41d1634