How much does Gemini 3 Pro Preview cost?

On the Respan gateway, Gemini 3 Pro Preview costs $2.00 per 1M input tokens and $12.00 per 1M output tokens on Google Vertex AI, after gateway discounts.

Which providers serve Gemini 3 Pro Preview on Respan?

Gemini 3 Pro Preview is served by Google Vertex AI through 2 routes. Google Vertex AI requires your own provider API key (BYOK).

What is Gemini 3 Pro Preview's context window?

Gemini 3 Pro Preview accepts up to 1M tokens of context on its largest provider route.

How do I use Gemini 3 Pro Preview with the Respan gateway?

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "gemini-3-pro-preview". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Where does Gemini 3 Pro Preview rank on the Respan Index?

Gemini 3 Pro Preview scores 37.3 out of 100 on the Respan Index v1.1, ranking #55 of 143 models. By category: Coding 17.9, Agents 47.0, Reasoning 34.0, Knowledge & language 48.3, and Human preference 51.5. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

How does Gemini 3 Pro Preview score on benchmarks?

Gemini 3 Pro Preview has 32 published benchmark scores, including AIME 2025 (with code execution) 100%, tau2-bench Telecom 91%, and GPQA Diamond 92.6%. Each score links to where it was published; the data is collected by llmmetric.com.

Gemini 3 Pro Preview

Q: What is Gemini 3 Pro Preview?

Gemini 3 Pro Preview is a model from Google Gemini AI, released on Nov 18, 2025. Gemini 3 Pro Preview is a Google Gemini model built for multimodal understanding, long context, and tool use across chat and agent workflows. Gemini 3 Pro Preview is a Google Gemini model built for multimodal understanding, long context, and tool use across chat and agent workflows. Supports tool use. Up to 1M context window.

Gemini 3 Pro Preview is a Google Gemini model built for multimodal understanding, long context, and tool use across chat and agent workflows. Gemini 3 Pro Preview is a Google Gemini model built for multimodal understanding, long context, and tool use across chat and agent workflows. Supports tool use. Up to 1M context window.

Input / output price: $2.00 / $12.00 per 1M
Context: 1M tokens
Released: Nov 18, 2025

Try Respan for free

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "gemini-3-pro-preview".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="gemini-3-pro-preview",

    messages=[{"role": "user", "content": "Hello!"}],

)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

const response = await client.chat.completions.create({

  model: "gemini-3-pro-preview",

  messages: [{ role: "user", content: "Hello!" }],

});

console.log(response.choices[0].message.content);

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "gemini-3-pro-preview",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

2 routes from 1 provider, cheapest first, priced per 1M tokens after gateway discounts. BYOK routes use your own key.

Provider	Context	Input	Output	Cache read	Capabilities
Google Vertex AIBYOK only`vertex_ai_beta/gemini-3-pro-preview`	1M	$2.00/M	$12.00/M	—
Google Vertex AIBYOK only`vertex_ai/gemini-3-pro-preview`	1M	$2.00/M	$12.00/M	—

Is a provider down? Google AI status

Pricing

Averaged across 2 routes from 1 provider, in USD per 1M tokens after gateway discounts.

Average input: $2.00 per 1M
Average output: $12.00 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$2.00/MGoogle Vertex AI

Benchmarks

The Respan Index plus 32 published scores from 10 sources, each linked to where it was published.

37.3/ 100

Respan Index#55 of 143

143 ranked models. The shaded band is this model's 95% interval, 29.1 to 47.2. Claude Opus 4.5 and GPT-5 fall inside it, so the gap is within the margin of error.

55Gemini 3 Pro Preview37.3
54Claude Opus 4.537.4
56GPT-537.2

Published scores

Benchmark	Score	Source	Published
AIME 2025 (with code execution)storage.googleapis.com	100%	storage.googleapis.com	Nov 18, 2025
SWE-bench Verifiedstorage.googleapis.com	76.2%	storage.googleapis.com	Nov 18, 2025
SWE-bench VerifiedEpoch AI	72.9%	Epoch AI	Oct 5, 2026
WeirdMLHåvard Tveit Ihle	69.9%	Håvard Tveit Ihle	Oct 5, 2026
Humanity's Last Exam (with search and code execution)storage.googleapis.com	45.8%	storage.googleapis.com	Nov 18, 2025
GSO Opt@1GSO	17.7%	GSO	Nov 28, 2025

Benchmark	Score	Source	Published
tau2-bench TelecomSierra	91%	Sierra	Mar 2, 2026
τ2-benchstorage.googleapis.com	85.4%	storage.googleapis.com	Nov 18, 2025
tau2-bench AirlineSierra	80.5%	Sierra	Mar 2, 2026
tau2-bench RetailSierra	75.9%	Sierra	Mar 2, 2026
BALROGBALROG	58.1%	BALROG	Feb 3, 2026
Terminal-Bench 2.0 (Terminus-2 agent)storage.googleapis.com	54.2%	storage.googleapis.com	Nov 18, 2025
tau2-bench Banking KnowledgeSierra	18%	Sierra	Mar 2, 2026
Vending-Bench 2Andon Labs	5478.16 · #24 of 59	Andon Labs	Oct 5, 2026

Benchmark	Score	Source	Published
GPQA DiamondEpoch AI	92.6%	Epoch AI	Oct 5, 2026
GPQA Diamondstorage.googleapis.com	91.9%	storage.googleapis.com	Nov 18, 2025
SimpleBenchSimpleBench	76.4%	SimpleBench	Nov 18, 2025
Humanity's Last Exam (no tools)storage.googleapis.com	37.5%	storage.googleapis.com	Nov 18, 2025
ARC-AGI-2 (ARC Prize Verified)storage.googleapis.com	31.1%	storage.googleapis.com	Nov 18, 2025
Chess PuzzlesEpoch AI	31%	Epoch AI	Oct 5, 2026

Benchmark	Score	Source	Published
AIME 2025storage.googleapis.com	95%	storage.googleapis.com	Nov 18, 2025
OTIS Mock AIME 2024-2025Epoch AI	91.4%	Epoch AI	Oct 5, 2026
MathArena Apexstorage.googleapis.com	23.4%	storage.googleapis.com	Nov 18, 2025

Benchmark	Score	Source	Published
MMMLUstorage.googleapis.com	91.8%	storage.googleapis.com	Nov 18, 2025
SimpleQA Verifiedstorage.googleapis.com	72.1%	storage.googleapis.com	Nov 18, 2025

Benchmark	Score	Source	Published
Video-MMMUstorage.googleapis.com	87.6%	storage.googleapis.com	Nov 18, 2025
CharXiv Reasoningstorage.googleapis.com	81.4%	storage.googleapis.com	Nov 18, 2025
MMMU-Prostorage.googleapis.com	81%	storage.googleapis.com	Nov 18, 2025

Benchmark	Score	Source	Published
LMArena EloLMArena	1486 Elo · #16 of 147	LMArena	Oct 8, 2026
LMArena WebDevLMArena	1440 Elo · #54 of 99	LMArena	Oct 8, 2026
LMArena VisionLMArena	1289 Elo · #11 of 85	LMArena	Oct 9, 2026