Gemini 4 Hydrogen
Google · released 2026-11-12
The official API price of Gemini 4 Hydrogen is $1.5 per 1M input tokens and $7.5 per 1M output tokens (as of 2026-11-13). Context window: 1.05M tokens, up to 65.5K output tokens per request. 11 providers sell it. The lowest is Kilo Gateway: $0.75 input, $3.75 output.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| $1.5 | $7.5 | $0.075 | Official | Official docs | |
KKilo GatewayLowestgoogle/ | $0.75 | $3.75 | $0.0375 | Lowest | Official docs |
EEden AIgoogle/ | $1.5 | $7.5 | $0.075 | Official docs | |
EEden AIvertex/ | $1.5 | $7.5 | $0.075 | Official docs | |
| $1.5 | $7.5 | $0.075 | Official docs | ||
| $1.5 | $7.5 | $0.075 | Official docs | ||
LLLM Gatewaygoogle-ai-studio/ | $1.5 | $7.5 | $0.075 | Official docs | |
LLLM Gatewaygoogle-vertex/ | $1.5 | $7.5 | $0.075 | Official docs | |
MMerge Gatewaygoogle/ | $1.5 | $7.5 | $0.075 | Official docs | |
NNanoGPTgoogle/ | $1.5 | $7.5 | $0.075 | Official docs | |
| $1.5 | $7.5 | $0.075 | Official docs | ||
| $1.5 | $7.5 | $0.075 | Official docs |
3 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| $1.5 | $7.5 | $0.075 | Official docs | ||
EEden AIvertex/ | $1.65 | $8.25 | $0.0825 | Official docs | |
EEden AIvertex/ | $1.65 | $8.25 | $0.0825 | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Google's Gemini 4 model for everyday coding and agentic workflows, with four thinking levels and a 1M-token context window
Description from models.dev.
Specs
- Type
- Text
- Context
- 1.05M
- Max output
- 65.5K
- Input
- Text, Image, Video, Audio, PDF
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2026-03
- Open weights
- No
- Released
- 2026-11-12
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-13. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.