Abacus
Gemini 3.1 Pro Preview
Reasoning-first Gemini preview for agentic coding and complex problem solving
Cheapest input
$2
$/MTok · models.dev
Cheapest output
$12
$/MTok
Context
1.0M
tokens
Offers
11
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.devcheapestgemini-3.1-pro-preview | Abacus | $2 | $12 | $0.2 | 1.0M |
| models.devgemini-3.1-pro-preview | AIHubMix | $2 | $12 | $0.2 | 1.0M |
| models.devgemini-3.1-pro-preview | Auriko | $2 | $12 | $0.2 | 1.0M |
| models.devgemini-3.1-pro-preview | DaoXE | $2 | $12 | $0.2 | 1.0M |
| models.devgemini-3-1-pro-preview | FrogBot | $2 | $12 | $0.2 | 1M |
| models.devgemini-3.1-pro-preview | GitHub Copilot | $2 | $12 | $0.2 | 1M |
| models.devgemini-3.1-pro-preview | Google Vertex AI | $2 | $12 | $0.2 | 1.0M |
| models.devgemini-3.1-pro-preview | LLM Gateway | $2 | $12 | $0.2 | 1.0M |
| models.devgemini-3.1-pro-preview | Vivgrid | $2 | $12 | $0.2 | 1.0M |
| LiteLLMgemini-3.1-pro-preview | — | $2 | $12 | $0.2 | — |
| models.devgemini-3-1-pro-preview | Venice AI | $2.50 | $15 | $0.5 | 1M |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- In: text
- In: image
- In: audio
- In: video
- In: pdf
- Out: text
Knowledge cutoff: 2025-01Released: 2026-02-19Family: 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 Elo1485
- AA intelligence46.5
- AA coding68.8
- AA agentic21.4
Sources: Arena AI, Artificial Analysis. See /benchmarks.