Gemma 4: API pricing, providers and specs
Gemma 4 is a text model by Google. 19 providers serve it, from $0.30 to $1.58 /1M; the lowest price is at FastRouter.
How Gemma 4 compares
Against the 737 text models on the site priced the same way.
- Cheap for its class: at $0.30 /1M, its lowest price undercuts 76% of comparable models (median $1.10).
- Its 262K-token context window is larger than 45% of them (median 262K), about 390 pages of text.
- 19 providers serve it; 87% of comparable models have fewer.
- Its weights are open under the Apache 2.0 license: commercial use allowed.
Gemma 4 prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
 Nvidia | Free/1M | Free/1M | — | — |
 FastRouter | $0.10/1M | $0.30/1M | — | 262K |
 Venice AI | $0.12/1M | $0.36/1M | $0.09/1M | — |
 OrcaRouter | $0.13/1M | $0.38/1M | $0.02/1M | — |
 Requesty | $0.13/1M | From$0.38/1M | — | 262K |
 Cortecs | $0.224/1M | $0.392/1M | — | — |
 Kenari | $0.099/1M | $0.392/1M | $0.04/1M | — |
 Novita AI | $0.14/1M | $0.40/1M | — | — |
 Hugging Face | $0.14/1M | From$0.40/1M | — | — |
| Vercel AI Gateway | $0.14/1M | $0.40/1M | — | 262K |
 Deep Infra | $0.20/1M | From$0.40/1M | — | — |
 Amazon Bedrock | $0.14/1M | From$0.40/1M | — | — |
| OpenRouter | $0.20/1M | From$0.40/1M | — | 262K |
| DevPass (LLM Gateway) | $0.20/1M | From$0.40/1M | — | — |
 AIHubMix | $0.20/1M | $0.40/1M | — | 262K |
| ZenMux | $0.14/1M | $0.40/1M | — | 262K |
 Neuralwatt | $0.14/1M | $0.42/1M | $0.01/1M | — |
 SiliconFlow | $0.75/1M | $1/1M | $0.25/1M | — |
| AI/ML API | $1.05/1M | $1.58/1M | $1.05/1M | — |
- FastRouter$0.30
- Venice AI$0.36
- OrcaRouter$0.38
- RequestyFrom$0.38
- Cortecs$0.392
- Kenari$0.392
- Novita AI$0.40
- Vercel AI Gateway$0.40
- AIHubMix$0.40
- ZenMux$0.40
- Hugging FaceFrom$0.40
- Deep InfraFrom$0.40
Specs
- Type
- Text
- Maker
- Inputs
- Image, Text, Video
- Outputs
- Text
- Context
- 262K≈ 390 pages of text
- Max output
- 131K
- Capabilities
- JSON, Reasoning, Tool calling, Vision
- Released
- Mar 11, 2026
- License
- Apache 2.0commercial use allowed
- Open weights
- Yes, downloadable
- Parameters
- 31B
- Monthly searches
- 6K
3 uncensored versions · See them
Alternatives to Gemma 4
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| Gemma 4this model | $0.30/1M | 262K | — | 19 |
 GLM-5.3-Flash | $0.20/1M | 1.05M | 1608 | 45 |
 Qwen3.8 27B | $0.50/1M | 262K | 1591 | 33 |
| GPT-6 Luna | $0.40/1M | 1.05M | 1578 | 28 |
| Claude Haiku 5.5 | $0.30/1M | 1M | 1585 | 27 |
 MiMo-V2.6-Pro | $0.696/1M | 1.05M | 1625 | 21 |
| Qwen3.8 Flash Next | $0.376/1M | 262K | 1628 | 5 |
 DeepSeek V4 Flash | $0.17/1M | 1.05M | — | 26 |
| DeepSeek V4 Flash Vision Exp | $0.294/1M | 1.05M | — | 26 |
More from Google
Gemini 4 ArgonGoogle$8/1MNano Banana 2Google$0.067/imgVeo-3Google$2.50/runNano Banana Pro PreviewGoogle$0.09/runGemini Omni 1.1Google$0.05/secNano Banana 2.1Google$6/1MGemini 3 FlashGoogle$2.40/1MVeo 3.1Google$0.16/secGemma 4 FAQ
The lowest price for Gemma 4 is $0.30 /1M, at FastRouter.
FastRouter, at $0.30 /1M. 19 providers serve Gemma 4; the table above lists every one with its price.
Gemma 4 reads up to 262K tokens per request and writes up to 131K.
Yes. Gemma 4's weights can be downloaded from its maker's Hugging Face page, under the Apache 2.0 license.
About 31B, as the safetensors metadata of its official Hugging Face repo states.
19 API providers serve Gemma 4. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us