ModelBench
Google logo
Models/Google

Gemini 3 Pro Preview

Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts

Source-linked gemini-pro Closed weights Released 2025-11-18
API data Report
Input modalitiesT
Output modalitiesT
Input price$2/1M tokens
Output price$12/1M tokens
Context window1.04858M
Max output65.536K
Overview

Capabilities and specifications

✓ Reasoning Yes
✓ Tool calling Yes
✓ Structured output Yes
✓ Attachments Yes
✓ Vision input Yes
× Open weights No
Creator
Google
Model family
gemini-pro
Knowledge cutoff
2025-01
License
Not documented
Release date
2025-11-18
Model ID
google/gemini-3-pro-preview
Inference availability

Provider pricing and availability

Provider-specific identifiers, limits, and prices per million tokens.

Report a price
Providers offering Gemini 3 Pro Preview
ProviderProvider model IDContextInputOutputCache readCapabilitiesSource
AnyAPI google/gemini-3-pro-preview 1.04858M Not listed Not listed - ReasoningToolsJSON Docs
QiHang gemini-3-pro-preview 1M $0.57 $3.43 - ReasoningTools Docs
NEAR AI Cloud google/gemini-3-pro 1.04858M $1.25 $15 - ReasoningToolsJSON Docs
Requesty google/gemini-3-pro-preview 1.04858M $2 $12 $0.2 ReasoningTools Docs
Vercel AI Gateway google/gemini-3-pro-preview 1M $2 $12 $0.2 ReasoningToolsJSON Docs
Google gemini-3-pro-preview 1.04858M $2 $12 $0.2 ReasoningToolsJSON Docs
Merge Gateway google/gemini-3-pro-preview 1.04858M $2 $12 $0.2 ReasoningToolsJSON Docs
Databricks databricks-gemini-3-pro 1.04858M $2 $12 $0.2 ReasoningToolsJSON Docs
Neon gemini-3-pro 1.04858M $2 $12 $0.2 ReasoningToolsJSON Docs
OrcaRouter google/gemini-3-pro-preview 1.04858M $4 $18 $0.2 ReasoningToolsJSON Docs

Capability badges appear only when the provider catalog explicitly lists support.

Serving quality

Performance and reliability

Observed serving measurements stay separate from model specifications and are never estimated from price or model size.

Throughput Not reported

Generation speed; higher is faster.

Latency / TTFT Not reported

Time until the first output token arrives.

Uptime Not reported

Successful requests over a measured period.

Performance varies by inference provider, region, and load. Provider-level measurements appear only when a source reports them.

Published evaluations

Benchmarks

Raw results remain attached to their original source and version.

Benchmark registry
SWE-Bench Pro - Unversioned - resolve rateTop 8 reported models
Claude Fable 5
80.3
Claude Opus 4.8
69.2
Grok 4.5
64.7
GPT-5.6 Sol
64.6
Claude Opus 4.7
64.3
GPT-5.6 Terra
63.4
Claude Sonnet 5
63.2
Gemini 3 Pro Preview
43.3
Catalog activity

Recent record changes

Detected changes from successful source imports.

Full change log
No recent changes detected

This record has not changed in the retained import history.

Public API

Use this record

Fetch the complete source-linked model record without an API key.

API documentation
Endpoint
GET https://www.modelbench.lol/api/v1/models/google/gemini-3-pro-preview
curl
curl "https://www.modelbench.lol/api/v1/models/google/gemini-3-pro-preview"