Inference providerUS Centralprices checked Oct 23, 06:00 UTC
Google serves 28 models at a verified price. On the 19 it shares with other hosts, it is the cheapest on 6 and charges a median 54% above the cheapest.
Models served2815 with open weights
Cheapest input, per M$0.07gpt-oss-20b
Uptime, last 24 h61.3%average of its 14 OpenRouter endpoints
Sign-upNo card neededno free credits stated
| Model | Precision | Context | Tools | Input | Output | Cache |
|---|---|---|---|---|---|---|
| Gemini 4 Argon | — | 1M | — | $2.00 | $10.00 | $0.10 |
| DeepSeek V4.1 Flash | not checked yet | 1M | ✓ | $0.30 | $1.20 | $0.03 |
| Gemini 3.8 Flash | — | 1M | — | $0.75 | $3.75 | $0.075 |
| Claude Fable 5.1cheapest | — | 1M | — | $10.00 | $50.00 | $0.25 |
| Gemini 3.7 Flash | — | 1M | — | $0.75 | $3.75 | $0.075 |
| Claude Opus 5cheapest | — | 1M | ✓ | $5.00 | $25.00 | $0.50 |
| Gemini 3.5 Flash-Lite | — | 1M | — | $0.30 | $2.50 | $0.03 |
| Gemini 3.6 Flash | — | 1M | — | $0.75 | $3.75 | $0.075 |
| Claude Sonnet 5cheapest | — | 1M | ✓ | $2.00 | $10.00 | $0.20 |
| Claude Fable 5cheapest | — | 1M | ✓ | $10.00 | $50.00 | $1.00 |
| Gemma 4 26B A4B | not stated by the host | 256K | ✓ | $0.15 | $0.60 | — |
| Gemini 3.1 Pro Preview | — | 1M | — | $2.00 | $12.00 | $0.20 |
| GLM 4.7 | not stated by the host | 200K | ✓ | $0.60 | $2.20 | — |
| Gemini 3 Flash Preview | — | 1M | — | $0.50 | $3.00 | $0.05 |
| Kimi K2 Thinkingcheapest | not stated by the host | 256K | ✓ | $0.60 | $2.50 | — |
| MiniMax M2 | not stated by the host | 192K | ✓ | $0.30 | $1.20 | — |
| DeepSeek V3.2 | not stated by the host | 160K | ✓ | $0.56 | $1.68 | — |
| Qwen3 Next 80B A3B Thinkingcheapest | not stated by the host | 256K | ✓ | $0.15 | $1.20 | — |
| gpt-oss-120b | not stated by the host | 128K | — | $0.09 | $0.36 | — |
| gpt-oss-20b | not stated by the host | 128K | — | $0.07 | $0.25 | — |
| Qwen3 Coder | not stated by the host | 256K | ✓ | $0.22 | $1.80 | — |
| Qwen3 235B A22B Instruct 2507 | not stated by the host | 256K | ✓ | $0.22 | $0.88 | — |
| Gemini 2.5 Flash | — | 1M | — | $0.30 | $2.50 | $0.03 |
| Gemini 2.5 Pro | — | 1M | — | $1.25 | $10.00 | $0.13 |
| Llama 4 Maverick | not stated by the host | 512K | ✓ | $0.35 | $1.15 | — |
| Llama 4 Scout | not stated by the host | under review | ✓ | $0.25 | $0.70 | — |
| Llama 3.3 70B | not stated by the host | 125K | ✓ | $0.72 | $0.72 | — |
| Qwen3 Next 80B A3B | not stated by the host | 256K | ✓ | $0.15 | $1.20 | — |
10 of 28 models · prices per million tokens · precision and context: read at Google's own catalogue or docs where its terms allow, otherwise as declared to OpenRouter (hover a cell for its source) · tools as Google declares them to OpenRouter
| Condition | What it says | Source |
|---|---|---|
| Sign-up | No credit card needed to start | ai.google.dev |
| Free credits | None stated | — |
| Headquarters region | US Central | — |
| Price list | Where its per-token prices are published | ai.google.dev |
| API documentation | Its own docs | ai.google.dev |
| Terms of service | Its terms | ai.google.dev |
| Discount | Gemini 3.8 Flash and 3.6 Flash at half price: $0.75 / $3.75 per 1M tokens, until Dec 31 | ai.google.dev |
| Free tier | Gemini API free tier on Gemini 3.8 Flash and 3.6 Flash | ai.google.dev |
| Discount | Gemini 4 Argon at half price: $2 / $10 per 1M tokens, until Nov 30 | ai.google.dev |
Links checked Oct 8.