Gemini 3.1 Pro: AI Large Language Models

Gemini 3.1 Pro is Google's next-generation multimodal model, optimized for complex reasoning, planning, coding, and multi-turn conversation. Supports text and image inputs. Token-based pricing: $4.00/M input tokens, $24.00/M output tokens. Two endpoints: standard async (/gemini-3-1-pro) and live streaming (/gemini-3-1-pro/stream) via SSE.

📝

Overview

About this model

Gemini 3.1 Pro is Google's next-generation multimodal model, optimized for complex reasoning, planning, coding, and multi-turn conversation. It delivers high-quality text and multimodal generations. Pricing: $4.00 per million input tokens and $24.00 per million output tokens.

1Logical Reasoning: Solve complex logical puzzles, mathematical problems, and multi-step tasks.
2Advanced Coding: Refactoring, debugging, code generation, and multi-file code editing.
3Multimodal Processing: Analyze images, diagrams, charts, and text together in a single request.
4Structured Outputs: Generate highly precise JSON schemas, tables, and structured data formats.
💰

Pricing & Value

Cost analysis

muapiapp$4.00/M input tokens, $24.00/M output tokens

Token-based billing. Minimum $0.0006 per call. Highly competitive pricing.

Fal.ai$5.00/M input tokens, $30.00/M output tokens

muapiapp remains more cost-effective.

Replicate$5.20/M input tokens, $31.00/M output tokens

muapiapp remains more cost-effective.

** Competitor pricing is estimated based on similar model architectures and usage tiers.

⚙️

Technical Details

Configuration schema

Promptstring

The user message or instruction for the model.

Default ValueSolve this complex coding problem step by step.
Image URLstring

Optional image URL to include as multimodal input.

Default Valueundefined
System Promptstring

Optional system-level instruction to guide model behavior.

Default ValueYou are a helpful software engineering assistant.
📖

Implementation Guide

Developer documentation

Standard (Async)

POST /api/v1/gemini-3-1-pro — returns request_id, poll for result via /api/v1/predictions/{id}/result.

Streaming (SSE)

POST /api/v1/gemini-3-1-pro/stream — returns a live SSE stream. Each chunk: data: {"choices":[{"delta":{"content":"text"}}]}, ending with data: [DONE].

See Streaming Documentation for full code examples.

Common Questions

Frequently asked

How is pricing calculated?

Pricing is token-based: $4.00 per million input tokens and $24.00 per million output tokens. The minimum charge per call is $0.0006. Actual cost is deducted after each call based on token counts returned by the model.

Does Gemini 3.1 Pro support images?

Yes. Pass an image_url in the request body to include an image as part of the user message.

Does Gemini 3.1 Pro support system prompts?

Yes. You can supply an optional system_prompt field to guide the model's behavior and tone.