API provider

FastRouter

What this provider sells and at what price. A price belongs to the offer, not the model: at another provider the same model may cost several times more or less.

37 models with a price
resold models
aggregate databases price source

Models & prices

Model Developer Input, $/1M Output, $/1M Blended, $/1M
Claude Opus 4.8 Anthropic $5 $25 $10
Gemini 3.5 Flash Google DeepMind $1.5 $9 $3.38
Sarvam 105B Sarvam AI $0.04 $0.16 $0.07
Sarvam 30B Sarvam AI $0.02 $0.1 $0.04
DeepSeek V4 Pro DeepSeek $1.74 $3.48 $2.18
GPT 5.5 OpenAI $5 $30 $11.25
GPT-5.5 Pro OpenAI $30 $180 $67.5
Kimi K2.6 Moonshot AI (Kimi) $0.75 $3.5 $1.44
Grok 4.3 xAI $1.25 $2.5 $1.56
Grok Build 0.1 xAI $1 $2 $1.25
Gemma 4 31B Google DeepMind $0.13 $0.38 $0.19
GLM 5.1 Zhipu AI / Z.ai $1.05 $3.5 $1.66
MiniMax M2.7 MiniMax $0.3 $1.2 $0.53
MiniMax M2.7 Highspeed MiniMax $0.6 $2.4 $1.05
GPT-5.4 mini OpenAI $0.75 $4.5 $1.69
GPT-5.4 nano OpenAI $0.2 $1.25 $0.46
Qwen 3 Coder 480B Alibaba (Qwen) $0.3 $1.2 $0.53
Nano Banana 2 Google DeepMind $0.5 $3 $1.13
Gemini 3.1 Pro Preview Google DeepMind $2 $12 $4.5
Claude Sonnet 4.6 Anthropic $3 $15 $6
GLM 5 Zhipu AI / Z.ai $0.95 $3.15 $1.5
GPT 5.3 Codex OpenAI $1.75 $14 $4.81
Nano Banana Pro Google DeepMind $2 $12 $4.5
GPT 5 OpenAI $1.25 $10 $3.44
GPT-5 Mini OpenAI $0.25 $2 $0.69
Claude Opus 4.1 Anthropic $15 $75 $30
GPT 5 Nano OpenAI $0.05 $0.4 $0.14
GPT OSS 120B OpenAI $0.15 $0.6 $0.26
GPT OSS 20B OpenAI $0.05 $0.2 $0.09
Kimi K2 Moonshot AI (Kimi) $0.55 $2.2 $0.96
Grok 4 xAI $3 $15 $6
Gemini 2.5 Flash Google DeepMind $0.3 $2.5 $0.85
Gemini 2.5 Pro Google DeepMind $1.25 $10 $3.44
GPT Realtime 1.5 OpenAI $4 $16 $7
Claude Sonnet 4 Anthropic $3 $15 $6
GPT 4.1 OpenAI $2 $8 $3.5
DeepSeek R1 Distill Llama 70B DeepSeek $0.03 $0.14 $0.06

These are this provider’s prices, not the market’s best: the same model may cost differently at another provider. The blended price uses a three-input-tokens-to-one-output scheme — the way to compare models whose output costs several times more than input. Only the base per-token rate counts, without batch or discounted tiers; input and output come from one price list, not two minimums from different ones.