Google: Gemini 3 Pro Preview✓ Catalog verified
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, see our docs here: https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks. 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.
Overview
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, see our docs here: https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks. 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.
Access: available through the official Google API. Context window: 1.0M.
Specifications
| API identifier | google/gemini-3-pro-preview |
| Provider | |
| Model type | Multimodal LLM |
| Context window | 1.0M catalog |
| Input modalities | text · image · file · audio · video |
| Output modalities | text |
| Released | Nov 18, 2025 |
| Tokenizer | Gemini |
| Moderated | No |
| Architecture modality | text+image+file+audio+video->text |
| Scheduled expiry | 2026-03-26 |
API defaults
{
"top_p": null,
"temperature": null,
"frequency_penalty": null
}Pricing
Live pricing components for google/gemini-3-pro-preview as published in the catalog.
| Pricing component | Raw unit price | Normalized | Unit |
|---|---|---|---|
| Prompt tokens | $0.000002 | $2.00 / 1M | Per input token |
| Completion tokens | $0.000012 | $12.00 / 1M | Per output token |
| Request fee | N/A | N/A | Per request |
| Image fee | $0.000002 | $0.000002 | Per image unit |
| Web search fee | N/A | N/A | Per search request |
Cost calculator
Estimate monthly spend from your own token volumes.
Estimated Total Cost
$3.4Calculated from current list pricing in the ModelsAtlas catalog.Capabilities
| Capability | Status | What it means |
|---|---|---|
| Visual Understanding | ✓ Supported | Image and document analysis support |
| Audio Processing | ✓ Supported | Speech and voice aligned flows |
| Tool Calling | ✓ Supported | Supports tools / function calling |
| Self-Hosting | Not advertised | Deploy outside managed APIs |
Capability signals
Directional signals derived from model metadata and capability tags — not official benchmark submissions.
Quick start
Call Google: Gemini 3 Pro Preview through an OpenAI-compatible client.
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key="YOUR_API_KEY"
)
response = client.chat.completions.create(
model="google/gemini-3-pro-preview",
messages=[{"role": "user", "content": "Explain quantum physics."}]
)
print(response.choices[0].message.content)Alternatives
Closest models by context window from a different provider.
| Model | Provider | Context | Input /1M | Actions |
|---|---|---|---|---|
| Meta: Llama 4 Maverick | Meta | 1.0M | $0.15 | View → |
| Xiaomi: MiMo-V2-Pro | Xiaomi | 1.0M | $1.00 | View → |
Head-to-head comparisons
Side-by-side breakdowns of Google: Gemini 3 Pro Preview against other frontier models.
Sources & attribution
Pricing and metadata are maintained in the ModelsAtlas catalog.
Frequently asked questions
How much does Google: Gemini 3 Pro Preview cost?
$2.00 per 1M input tokens and $12.00 per 1M output tokens on the official Google API.
What is the context window of Google: Gemini 3 Pro Preview?
Google: Gemini 3 Pro Preview supports up to 1.0M tokens of context.
Does Google: Gemini 3 Pro Preview support tool / function calling?
Yes, Google: Gemini 3 Pro Preview supports tool / function calling — you can register tools and the model will emit structured tool calls.
How do I access Google: Gemini 3 Pro Preview?
Use the official Google API with the model id `google/gemini-3-pro-preview`. See the Quick start section above for code examples.