Google: Gemini-3-Flash
Fast Gemini model balancing multimodal reasoning, tool use, and cost
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestgoogle/gemini-3-flash | Poe | $0.4 | $2.40 | $0.04 | 1.0M |
| models.devgoogle/gemini-3-flash | Vercel AI Gateway | $0.5 | $3 | $0.05 | 1M |
| models.devdatabricks-gemini-3-flash | Databricks | $0.5 | $3 | $0.05 | 1.0M |
| models.devgemini-3-flash | Neon | $0.5 | $3 | $0.05 | 1.0M |
| models.devgemini-3-flash | OpenCode Zen | $0.5 | $3 | $0.05 | 1.0M |
| models.devgemini-3-flash | Pioneer | $0.5 | $3 | $0.05 | 1M |
| LiteLLMdatabricks-gemini-3-flash | N/A | $0.625 | $3.75 | $0.0625 | N/A |
| LiteLLMdatabricks/databricks-gemini-3-flash | N/A | $0.625 | $3.75 | $0.0625 | N/A |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- In: text
- In: image
- In: video
- In: audio
- In: pdf
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence26.3i
- AA coding0i
- AA agentic0i
- HLE (without tools)33.7i
- GPQA Diamond90.4i
- SWE-Bench Verified78i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.