Gemini 3.1 Pro Preview

google/gemini-3.1-pro-preview

Maker: Google, United States
Released: 2026-02-19
Knowledge cutoff: 2025-01
Family: gemini-pro
Weights: closed
Tasks: text.chat, text.reasoning, code, vision.understand, vision.extract
Cheapest offering: Google Gemini API, about $0.0056 for a typical text.chat call

Try it in the sandbox Use it from the API

Offerings

Provider	Model id at the provider	Status	Price per 1M tokens	Per-unit prices	Limits	Capabilities (level)
Google Gemini API	`gemini-3.1-pro-preview`	ga	Input: $2 Output: $12 Cache read: $0.20 Input, prompts over 200,000 tokens: $4 Output, prompts over 200,000 tokens: $18 Cache read, prompts over 200,000 tokens: $0.40 Input, flex tier: $1 Output, flex tier: $6 Cache read, flex tier: $0.20 Input, priority tier: $3.60 Output, priority tier: $21.60 Cache read, priority tier: $0.36 Since 2026-11-03 · Curated by Nanner Tech	none	Context: 1,048,576 tokens Max input: 1,048,576 tokens Max output: 65,536 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `input.audio` claimed `input.video` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` native `tool_choice` claimed `prompt_caching` claimed `web_search` claimed
Google Gemini API	`gemini-pro-latest`	ga	Input: $2 Output: $12 Cache read: $0.2 Input, prompts over 200,000 tokens: $4 Output, prompts over 200,000 tokens: $18 Cache read, prompts over 200,000 tokens: $0.4 Since 2026-11-03 · models.dev, MIT	none	Context: 1,048,576 tokens Max input: 1,048,576 tokens Max output: 65,536 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `input.audio` claimed `input.video` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` native `tool_choice` claimed `prompt_caching` claimed `web_search` claimed
OpenRouter	`google/gemini-3.1-pro-preview`	ga	Input: $2 Output: $12 Cache read: $0.2 Cache write (5 min): $0.375 Reasoning: $12 Audio input: $2 Input, prompts over 200,000 tokens: $4 Output, prompts over 200,000 tokens: $18 Cache read, prompts over 200,000 tokens: $0.4 Since 2026-11-03 · models.dev, MIT	none	Context: 1,048,576 tokens Max output: 65,536 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `input.audio` claimed `input.video` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed
Google Vertex AI	`gemini-3.1-pro-preview`	preview	Input: $2 Output: $12 Cache read: $0.2 Input, prompts over 200,000 tokens: $4 Output, prompts over 200,000 tokens: $18 Cache read, prompts over 200,000 tokens: $0.4 Since 2026-11-03 · models.dev, MIT	none	Context: 1,048,576 tokens Max output: 65,536 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `input.audio` claimed `input.video` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed `prompt_caching` claimed `web_search` claimed

Quality scores

Basis	Score (0–1)	Raw	Measured	Source
`epoch:gpqa_diamond`	0.980	0.9444	2026-08-06	Epoch AI, CC-BY-4.0, normalized by Nanner Tech
`epoch:terminal_bench`	0.947	0.8022	2026-02-19	Epoch AI, CC-BY-4.0, normalized by Nanner Tech
`lmarena:vision_style_control`	0.941	1279.5484	2026-10-19	LMArena, CC-BY-4.0, normalized by Nanner Tech
`lmarena:document_style_control`	0.885	1458.8644	2026-09-13	LMArena, CC-BY-4.0, normalized by Nanner Tech
`epoch:hle`	0.847	0.4644	2026-02-19	Epoch AI, CC-BY-4.0, normalized by Nanner Tech
`epoch:frontiermath`	0.637	0.5965	2026-06-11	Epoch AI, CC-BY-4.0, normalized by Nanner Tech
`lmarena:webdev`	0.220	1446.6498	2026-10-28	LMArena, CC-BY-4.0, normalized by Nanner Tech
`lmarena:agent`	0.000	-0.0461	2026-11-02	LMArena, CC-BY-4.0, normalized by Nanner Tech

Aliases

Other names the API accepts for this model.

gemini-3.1-pro-preview
gemini-pro-latest

Use it from the API

Look this model up, or ask for the best model for its task on the providers that offer it. See the quickstart and the API reference.

Look up this model

curl 'https://rhumbdata.com/v1/models/google/gemini-3.1-pro-preview' \
  -H "Authorization: Bearer $RHUMB_KEY"

Resolve text.chat on its providers

curl 'https://rhumbdata.com/v1/resolve?task=text.chat&providers=gemini,openrouter,vertex' \
  -H "Authorization: Bearer $RHUMB_KEY"

Built from catalog version 2026-11-04.3 of 2026-11-04. Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).