The Orchestrator › Models › Google
Google: Gemma 3 12B
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
Specifications
| Provider | |
| Model ID | google/gemma-3-12b-it |
| Context window | 131K tokens (131,072) |
| Modalities | text + image → text |
| Tokenizer | Gemini |
| Router sources | OpenRouter, TrustedRouter |
| Released | 2025-03-13 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | google/gemma-3-12b-it | $0.05 | $0.15 | 131K |
| standard | TrustedRouter | google/gemma-3-12b-it | $0.053 | $0.105 | 131K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.053 | $0.105 | 131K |
| 2026-11-14 | $0.05 | $0.15 | 131K |
Capabilities
Vision (image input)Agentic tool useStructured outputsNo content storage (attested)Zero data retention
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p