Gemma 4 31B It Turbo
deepinfra/google/gemma-4-31B-it-turboGemma 4 31B It Turbo is a reasoning model by Google with vision, function calling, structured output — designed for complex, multi-step problem solving where accuracy matters more than speed. It features an extended 262K token context window, suitable for processing long documents and complex conversations. Priced at $0.09 per million input tokens and $0.34 per million output tokens, it is one of the most cost-efficient options in its class. Access Gemma 4 31B It Turbo through Inworld LLM Inference with OpenAI SDK compatibility, built-in failover, and intelligent routing across providers.
- Input
- $0.09
- Output
- $0.34
- Cache read
- $0.05
- Context
- 262.1K
- Max output
- —
curl --fail-with-body https://api.inworld.ai/v1/chat/completions \
-H "Authorization: Basic $INWORLD_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "deepinfra/google/gemma-4-31B-it-turbo",
"messages": [{"role": "user", "content": "Hello"}],
"stream": true
}'Pricing and providers
Access Gemma 4 31B It Turbo through Inworld LLM Inference or speech to speech via DeepInfra. By using the providers below you agree to their terms, listed under each provider's name in the Legal section.
| Modalities | |||||||
|---|---|---|---|---|---|---|---|
DeepInfraThis pagedeepinfra/google/gemma-4-31B-it-turbo | $0.09 | $0.34 | $0.05 | — | 262.1K | — | TextImage→Text |
Start building with Gemma 4 31B It Turbo
Access Gemma 4 31B It Turbo and every other model through LLM Inference or speech to speech. Create a free account and start in minutes.