Google: Gemini 3 Pro Preview
Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts
Cheapest input
$1.25
$/MTok · models.dev
Cheapest output
$15
$/MTok
Context
1.0M
tokens
Offers
7
2 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.devcheapestgoogle/gemini-3-pro | NEAR AI Cloud | $1.25 | $15 | $0 | 1.0M |
| models.devgoogle/gemini-3-pro | Poe | $1.60 | $9.60 | $0.16 | 1.0M |
| models.devgemini-3-pro | Neon | $2 | $12 | $0.2 | 1.0M |
| models.devgemini-3-pro | OpenCode Zen | $2 | $12 | $0.2 | 1.0M |
| LiteLLMgoogle/gemini-3-pro | — | $2 | $12 | $0.2 | — |
| LiteLLMgemini-3-pro | — | $2 | $12 | $0.2 | — |
| LiteLLMreplicate/google/gemini-3-pro | — | $2 | $12 | $0.2 | — |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- In: text
- In: image
- In: video
- In: audio
- In: pdf
- Out: text
Knowledge cutoff: 2025-01Released: 2025-11-18Family: gemini-pro
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 text Elo1486
- Arena vision Elo1289
Sources: Arena AI, Artificial Analysis. See /benchmarks.