SF·SIX / PROVIDER PRICING
Google API pricing
Live prices for every model Google serves: its own per-1M-token prices, or per image, second or character, next to the cheapest price elsewhere.
Google serves 43 models with live API prices on SF·SIX, 43 models priced per 1M tokens. The cheapest is gpt-oss-20b at $0.07 per 1M input and $0.25 per 1M output tokens. The most used on OpenRouter is Claude Opus 5.5 (933.37B tokens on 2026-10-16).
- Models with live prices
- 43
- Cheapest language model
- gpt-oss-20b$0.07 / $0.25 per 1M tokens
- Most used on OpenRouter (2026-10-16)
- Claude Opus 5.5933.37B tokens
- Newest model
- Gemini 4 Argon2026-10-13
- Cheapest standard host for
- 3 models of 43
Google token prices (USD per 1M tokens)
| Model | Input / 1M | Output / 1M | Terms | Cheapest standard price anywhere | Context (tokens) | OpenRouter tokens / day |
|---|---|---|---|---|---|---|
| DeepSeek V3.2 | $0.56 | $1.68 | Standard | $0.2088 / $0.3096GMI Cloud (fp8) | 163,840 | Not in named rows |
| gpt-oss-20b | $0.07 | $0.25 | us-central1 region | $0.018 / $0.09Darkbloom (fp8) | 131,072 | Not in named rows |
| Llama 3.3 70B Instruct | $0.72 | $0.72 | Standard | $0.135 / $0.40Novita AI (bf16) | 131,072 | Not in named rows |
| GLM 4.7 | $0.60 | $2.20 | Standard | $0.40 / $1.75DeepInfra (fp4) | 204,800 | Not in named rows |
| Qwen3 235B A22B Instruct 2507 | $0.22 | $0.88 | us-south1 region | $0.0875 / $0.35GMI Cloud (fp8) | 262,144 | Not in named rows |
| Claude Haiku 5.5 | $0.10 | $0.50 | Global endpoint | $0.10 / $0.50Anthropic | 1,000,000 | 302.61B |
| Claude Sonnet 5.5 | $2.00 | $10.00 | Global endpoint | $2.00 / $10.00Anthropic | 1,000,000 | 396.5B |
| Claude Opus 5.5 | $4.00 | $20.00 | Global endpoint | $4.00 / $20.00Anthropic | 1,000,000 | 933.37B |
| Claude Opus 5 | $5.00 | $25.00 | Global endpoint | $5.00 / $25.00Anthropic | 1,000,000 | 82.77B |
| Claude Sonnet 5 | $2.00 | $10.00 | Global endpoint | $2.00 / $10.00Anthropic | 1,000,000 | 87.16B |
| Claude Fable 5 | $10.00 | $50.00 | Global endpoint | $10.00 / $50.00Anthropic | 1,000,000 | Not in named rows |
| Claude Opus 4.8 | $5.00 | $25.00 | Global endpoint | $5.00 / $25.00Anthropic | 1,000,000 | Not in named rows |
| Claude Opus 4.7 | $5.00 | $25.00 | Global endpoint | $5.00 / $25.00Anthropic | 1,000,000 | Not in named rows |
| Claude Sonnet 4.6 | $3.00 | $15.00 | Global endpoint | $3.00 / $15.00Anthropic | 1,000,000 | Not in named rows |
| Claude Opus 4.6 | $5.00 | $25.00 | Global endpoint | $5.00 / $25.00Anthropic | 1,000,000 | Not in named rows |
| Claude Opus 4.5 | $5.00 | $25.00 | Global endpoint | $5.00 / $25.00Anthropic | 200,000 | Not in named rows |
| Claude Sonnet 4.5 | $3.00 | $15.00 | Global endpoint | $3.00 / $15.00Anthropic | 1,000,000 | Not in named rows |
| Claude Fable 5.1 | $10.00 | $50.00 | Global endpoint | $10.00 / $50.00Anthropic | 1,000,000 | Not in named rows |
| Claude Haiku 4.5 | $1.00 | $5.00 | Global endpoint | $1.00 / $5.00Anthropic | 200,000 | Not in named rows |
| Llama 4 Maverick | $0.35 | $1.15 | us-east5 region | $0.1875 / $0.6525DigitalOcean | 1,048,576 | Not in named rows |
| Qwen3 Next 80B A3B Instruct | $0.15 | $1.20 | Global endpoint | $0.09 / $1.10DeepInfra (fp8) | 262,144 | Not in named rows |
| Qwen3 Coder 480B A35B | $0.22 | $1.80 | us-south1 region | $0.35 / $1.50Venice AI (fp8) | 262,144 | Not in named rows |
| Gemini 4 Argon | $2.20 | $11.00 | US region | $2.00 / $10.00Google AI Studio | 1,048,576 | 169.13B |
| Gemini 3.8 Flash | $0.75 | $3.75 | Global endpoint | $0.75 / $3.75Google AI Studio | 1,048,576 | 261.28B |
| Gemini 3.7 Flash | $0.75 | $3.75 | Global endpoint | $0.75 / $3.75Google AI Studio | 1,048,576 | 60.27B |
| Gemini 3.6 Flash | $0.75 | $3.75 | Global endpoint | $0.75 / $3.75Google AI Studio | 1,048,576 | Not in named rows |
| Gemini 3.5 Flash Lite | $0.30 | $2.50 | Global endpoint | $0.30 / $2.50Google AI Studio | 1,048,576 | Not in named rows |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | $0.25 | $1.50 | Global endpoint | $0.25 / $1.50Google AI Studio | 65,536 | Not in named rows |
| Nano Banana 2 (Gemini 3.1 Flash Image) | $0.50 | $3.00 | Global endpoint | $0.50 / $3.00Google AI Studio | 131,072 | Not in named rows |
| Nano Banana Pro (Gemini 3 Pro Image) | $2.00 | $12.00 | Global endpoint | $2.00 / $12.00Google AI Studio (Global endpoint) | 131,072 | Not in named rows |
| Gemini 3.5 Flash | $1.50 | $9.00 | Global endpoint | $1.50 / $9.00Google AI Studio | 1,048,576 | Not in named rows |
| Gemini 3.1 Flash Lite | $0.25 | $1.50 | Global endpoint | $0.25 / $1.50Google AI Studio | 1,048,576 | 73.07B |
| Gemini 3.1 Pro Preview | $2.00 | $12.00 | Global endpoint | $2.00 / $12.00Google AI Studio | 1,048,576 | Not in named rows |
| Gemini 3 Flash Preview | $0.50 | $3.00 | Global endpoint | $0.50 / $3.00Google AI Studio | 1,048,576 | 97.9B |
| Kimi K2 Thinking | $0.60 | $2.50 | Standard | Googlecheapest standard host | 262,144 | Not in named rows |
| MiniMax M2 | $0.30 | $1.20 | Standard | $0.255 / $1.02MiniMax (fp8) | 204,800 | Not in named rows |
| Gemini 2.5 Flash Lite | $0.10 | $0.40 | Standard | $0.10 / $0.40Google AI Studio | 1,048,576 | 102.54B |
| Gemini 2.5 Flash | $0.30 | $2.50 | Global endpoint | $0.30 / $2.50Google AI Studio | 1,048,576 | Not in named rows |
| Gemini 2.5 Pro | $2.25 | $18.00 | Priority tier · Global endpoint | $0.625 / $5.00Google AI Studio (Flex tier) | 1,048,576 | Not in named rows |
| Gemini 2.5 Pro Preview 06-05 | $2.25 | $18.00 | Priority tier · Global endpoint | $0.625 / $5.00Google AI Studio (Flex tier) | 1,048,576 | Not in named rows |
| Llama 4 Scout | $0.25 | $0.70 | us-east5 region | $0.10 / $0.30DeepInfra (fp8) | 1,310,720 | Not in named rows |
| Nano Banana (Gemini 2.5 Flash Image) | $0.30 | $2.50 | Global endpoint | Googlecheapest standard host | 32,768 | Not in named rows |
| Qwen3 Next 80B A3B Thinking | $0.15 | $1.20 | Global endpoint | Googlecheapest standard host | 262,144 | Not in named rows |
Google’s own endpoint for each model (standard tier and default region first), next to the cheapest standard price from any provider. Most widely served first.
Method
Prices are USD per 1M tokens at the standard service tier in the default region: the cheapest qualifying provider per model, with flex, batch, priority and fast endpoints and unusually low outliers never used as the headline. “Blended” weights input and output 3:1. Missing prices are unknown, not free. OpenRouter tokens per day are the latest full UTC day of OpenRouter’s public rankings (named rows only). Prices move: see AI API price changes for recent cuts and increases.