Skip to content

Model detail

Gemini 3 Pro preview

Provided by Google
Pay-as-you-go

Gemini 3 Pro is Google’s flagship frontier model for high-precision multimodal reasoning, combining strong performance across text, image, video, audio, and code with a 1M-token context window. Reasoning Details must be preserved when using multi-turn tool calling. It delivers state-of-the-art benchmark results in general reasoning, STEM problem solving, factual QA, and multimodal understanding, including leading scores on LMArena, GPQA Diamond, MathArena Apex, MMMU-Pro, and Video-MMMU. Interactions emphasize depth and interpretability: the model is designed to infer intent with minimal prompting and produce direct, insight-focused responses. Built for advanced development and agentic workflows, Gemini 3 Pro provides robust tool-calling, long-horizon planning stability, and strong zero-shot generation for complex UI, visualization, and coding tasks. It excels at agentic coding (SWE-Bench Verified, Terminal-Bench 2.0), multimodal analysis, and structured long-form tasks such as research synthesis, planning, and interactive learning experiences. Suitable applications include autonomous agents, coding assistants, multimodal analytics, scientific reasoning, and high-context information processing.

Model specs

Model ID
gemini-3-pro-preview
Context length
1.048576M
Max output
65.536K
I/O modalities
Released
2025-11

02

API endpoints

One MixRoute gateway, OpenAI-compatible

  • Gemini /v1beta/models/{model}:generateContent POST
  • OpenAI-compatible /v1/chat/completions POST

03

Pricing

Flat rate, unit: /1M Tokens

Input

$2.0000 /1M Tokens

Completion

$12.0000 /1M Tokens

Cache read

$0.2000 /1M Tokens

05

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

Coding

Gemini 3 Pro preview is built for writing and reviewing code, and it reads images alongside text. It accepts input such as text, image and video, and returns text. Its capabilities are broken down in the section just below. Run it on one file from your own repository and check the patch before you commit.

What should you check before using it?

1,048,576 context, 65,536 output tokens

Gemini 3 Pro preview accepts up to 1,048,576 tokens of context and returns up to 65,536 output tokens per request. Check that your longest prompt and its expected answer fit inside both limits before you size production traffic.

Why use it through MixRoute?

Swap the base URL, keep the Gemini 3 Pro preview client

Keep your existing OpenAI client and swap only the base URL. MixRoute supports calling Gemini 3 Pro preview through its OpenAI-compatible endpoint; point your client at https://api.mixroute.ai/v1 with the model ID gemini-3-pro-preview and re-run your integration tests.

07

Capabilities & compatibility

Unconfirmed capabilities stay "Unknown," no guesses

Available:

Tool calling

Gemini 3 Pro preview supports function and tool calls.

EX Send a tools definition; the response returns tool_calls to execute and feed results back.
Available:

Structured output

Gemini 3 Pro preview can produce JSON-formatted output on demand.

EX response_format: { type: "json_schema" } forces valid JSON output.
Available:

Streaming

Gemini 3 Pro preview supports streamed responses.

EX stream: true streams tokens incrementally, so chat UIs render as they arrive.
Available:

Prompt caching

Gemini 3 Pro preview supports prompt caching under supported routing conditions.

EX Keep the system prompt and tool definitions at the start of the request; repeated prefixes are automatically billed at the cache-read rate.
Available:

Vision input

Gemini 3 Pro preview can process image inputs alongside text.

EX Pass a base64-encoded image in a image_url content part alongside text messages.
Available:

OpenAI SDK

Call Gemini 3 Pro preview through MixRoute's OpenAI-compatible endpoint.

EX Change base_url to https://api.mixroute.ai/v1; everything else follows the OpenAI style.

08

Token cost estimator

Live estimate from this page's pricing, not an actual bill

Share of the same prefix read repeatedly, up to 100%

09

FAQ

Gemini 3 Pro preview was released on 2025-11-18. Its catalog status is stable. Check the model page for deprecation notices before you build a long-lived integration on it.

More from Google

All Google models
gemini-3.8-flash-lite-tts Google In $0.50 · Out $6.00 /1M View model gemini-3.8-flash-tts Google In $0.50 · Out $9.00 /1M View model Gemini 4 Argon Google In $2.00 · Out $10.00 · Cached $0.10 /1M View model Gemini Nano Banana 2.1 Google In $1.50 · Out $7.50 /1M View model

One endpoint, a testable decision

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.

Create an API key View integration docs