Last refreshed 2026-06-30. Next refresh: weekly.
Why use Gemma 4 31B IT on Open Inference?
Open Inference offers Gemma 4 31B IT with free input token pricing. Open Inference provides an OpenAI-compatible API for hosted text-generation model inference.
Compare Gemma 4 31B IT across 6 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: gemma-4-31b-itgemma-4-31b-itRequest example
Gotchas
No curated gotchas have been sourced for this exact provider/model route yet.
Compare Gemma 4 31B IT Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Google AI Studio | — | — |
| GCP Vertex AI | $0.15 | $0.60 |
| OpenRouter | $0.13 | $0.38 |
| Together AI | $0.39 | $0.97 |
| Novita AI | $0.14 | $0.40 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | Free |
| Output tokens | Free |
Capabilities
About Gemma 4 31B IT
Instruction-tuned variant of the 31B model with enhanced instruction-following. Maintains #3 Arena leaderboard performance with multimodal capabilities.
FAQ
What does Gemma 4 31B IT cost on Open Inference?
On Open Inference, Gemma 4 31B IT costs $0 per 1M input tokens and $0 per 1M output tokens.
What is the context window for Gemma 4 31B IT on Open Inference?
Gemma 4 31B IT supports a 256k token context window on Open Inference.
How does Open Inference compare to other Gemma 4 31B IT providers?
Gemma 4 31B IT is available from 6 providers. The cheapest input pricing is $0/1M tokens from Open Inference.
Who created Gemma 4 31B IT?
Gemma 4 31B IT was created by Google DeepMind as part of the Gemma 4 model family.
Is Gemma 4 31B IT open source?
Gemma 4 31B IT is open source under Apache 2.0 according to the seed data.