Gemma 4 31B It:thinking API
Google's Gemma 4 31B It:thinking costs $0.1 per million input tokens and $0.34 per million output tokens from 1 supplier. Each request through the OpenAI-compatible API goes to the offer with the lowest estimated charge that meets your rules.
- Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
- The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send gemma-4-31b-it:thinking as the model.
- Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.
About Gemma 4 31B It:thinking
Gemma 4 31B It:thinking is a language model from Google. Its release date is 2 April 2026. Largest Gemma 4 instruction model for open, self-hosted chat and reasoning. Its weights are open. Its training data ends in January 2025. It takes text and images and gives text. The largest offer takes 262,144 input tokens. It has 1 supplier on this exchange now.
Description, release date and licence: models.dev (https://models.dev/)
Facts
- Model name
- gemma-4-31b-it:thinking
- Maker
- Context window
- 262.1K tokens
- Input price
- $0.1 per million tokens
- Output price
- $0.34 per million tokens
- Suppliers
- 1 supplier
- Regions
- us
Providers
- Architect: us, declared precision provider-managed, $0.1 input and $0.34 output per million tokens, $0.1 cache read per million tokens, 262.1K tokens of context
Scores
- SimpleQA Verified: 10.4, #159 of 172
Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)
Request
curl https://router.inference.ai.exchange/v1/chat/completions \
-H "Authorization: Bearer $LIQUID_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemma-4-31b-it:thinking",
"messages": [{"role":"user","content":"Say hello."}]
}'Questions
- What is Gemma 4 31B It:thinking?
- Gemma 4 31B It:thinking is a language model from Google. Its release date is 2 April 2026. Largest Gemma 4 instruction model for open, self-hosted chat and reasoning. Its weights are open. Its training data ends in January 2025.
- How much does Gemma 4 31B It:thinking cost?
- Offers now ask $0.1 per million input tokens and $0.34 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
- What is the context length of Gemma 4 31B It:thinking?
- The largest offer takes 262,144 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
- What can Gemma 4 31B It:thinking do?
- Its providers list Vision, Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
- What inputs and outputs does Gemma 4 31B It:thinking support?
- Text · Images → Text.
- Which providers serve Gemma 4 31B It:thinking?
- It has 1 supplier now, with 1 offer. The table above ranks them by the cost of one agent-mix job.
- How do I call Gemma 4 31B It:thinking?
- Send "gemma-4-31b-it:thinking" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
- When was Gemma 4 31B It:thinking released?
- Its creator released it on 2 April 2026.
- When was Gemma 4 31B It:thinking listed?
- The exchange first listed it on 10/10/2026. This is not its release date.
Related pages
- Diffusiongemma
- Gemma 4 26B a4b It:thinking
- Gemma 3 27B It
- Gemma 3 4B It
- Gemma 4 12B It Starry Ocean
- Gemma 4 12B It
- Popular open weights
- Reasoning models
- Set up a client
- All models
- Providers
- Discover the best model for your budget
- Quickstart
- llms.txt: the index of every page, as Markdown
- llms-full.txt: every page in one file
- This page as Markdown