Google: Gemini 3.6 Flash
Fast Gemini model balancing multimodal reasoning, tool use, and cost
Cheapest input
$1.50
$/MTok · models.dev
Cheapest output
$7.50
$/MTok
Context
1.0M
tokens
Offers
15
3 sources
Offers
Same model, different listings. First-party, 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.devcheapestgemini/gemini-3.6-flash | CrossModel | $1.50 | $7.50 | $0.15 | 1.0M |
| models.devgemini-3.6-flash | GitHub Copilot | $1.50 | $7.50 | $0.15 | 1M |
| models.devgemini-3.6-flash | Google Vertex AI | $1.50 | $7.50 | $0.15 | 1.0M |
| models.devgemini-3.6-flash | $1.50 | $7.50 | $0.15 | 1.0M | |
| models.devgoogle/gemini-3.6-flash | Impossibl | $1.50 | $7.50 | $0.15 | 1.0M |
| models.devgoogle/gemini-3.6-flash | Kilo Gateway | $1.50 | $7.50 | $0.15 | 1.0M |
| models.devgemini-3.6-flash | LLM Gateway | $1.50 | $7.50 | $0.15 | 1.0M |
| models.devgoogle/gemini-3.6-flash | Merge Gateway | $1.50 | $7.50 | $0.15 | 1.0M |
| models.devgemini-3.6-flash | OpenCode Zen | $1.50 | $7.50 | $0.15 | 1.0M |
| OpenRoutergoogle/gemini-3.6-flash | OpenRouter | $1.50 | $7.50 | $0.15 | 1.0M |
| models.devgoogle/gemini-3.6-flash | Vercel AI Gateway | $1.50 | $7.50 | $0.15 | 1M |
| LiteLLMgemini/gemini-3.6-flash | — | $1.50 | $7.50 | $0.15 | — |
| LiteLLMgemini-3.6-flash | — | $1.50 | $7.50 | $0.15 | — |
| LiteLLMvertex_ai/gemini-3.6-flash | — | $1.50 | $7.50 | $0.15 | — |
| models.devgemini-3-6-flash | Venice AI | $1.88 | $9.38 | $0.1875 | 1M |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- In: text
- In: image
- In: audio
- In: video
- In: pdf
- In: file
- Out: text
Knowledge cutoff: 2026-03Released: 2026-07-21Family: gemini-flash
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- Arena code Elo1533
- Arena text Elo1483
- Arena vision Elo1290
- AA intelligence50.1
- AA coding69.2
- AA agentic38.7
Sources: Arena AI, Artificial Analysis. See /benchmarks.