The Orchestrator › Models › Google
Google: Gemma 4 31B
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Specifications
| Provider | |
| Model ID | google/gemma-4-31b-it |
| Context window | 262K tokens (262,144) |
| Modalities | text + image + video → text |
| Tokenizer | Gemma |
| Router sources | OpenRouter, TrustedRouter, Vercel AI Gateway |
| Released | 2026-04-02 |
| Tracked since | 2026-11-14 |
| Popularity | #34 by usage · peak 3.7% spend share in an OpenRouter category |
| Reasoning | Supported |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | google/gemma-4-31b-it | $0.2 | $0.4 | 262K |
| free | OpenRouter | google/gemma-4-31b-it:free | Free | Free | 262K |
| standard | TrustedRouter | google/gemma-4-31b-it | $0.105 | $0.359 | 262K |
| standard | Vercel AI Gateway | google/gemma-4-31b-it | $0.14 | $0.4 | 262K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.14 | $0.4 | 262K |
| 2026-11-14 | $0.105 | $0.359 | 262K |
| 2026-11-14 | $0.2 | $0.4 | 262K |
Capabilities
Vision (image input)Video inputAgentic tool useStructured outputs256K+ context windowControllable reasoningNo content storage (attested)Zero data retention
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, logit_bias, logprobs, max_completion_tokens, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p