The Orchestrator › Models › Google
Google: Gemini 3 Flash
Google's most intelligent model built for speed, combining frontier intelligence with superior search and grounding.
Specifications
| Provider | |
| Model ID | google/gemini-3-flash |
| Context window | 1M tokens (1,000,000) |
| Modalities | text + image + pdf → text |
| Tokenizer | — |
| Router sources | Vercel AI Gateway |
| Released | 2025-12-17 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | Vercel AI Gateway | google/gemini-3-flash | $0.5 | $3.00 | 1M |
| batch | Vercel AI Gateway | google/gemini-3-flash:batch | $0.25 | $1.50 | 1M |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.5 | $3.00 | 1M |
Capabilities
Vision (image input)Agentic tool useStructured outputs1M+ context windowControllable reasoningNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
max_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoning, response_format, structured_outputs