Gemini 2.5 Pro Preview 05-06
VerifiedGoogle's multimodal model processes text, images, audio, video and files over 1M tokens.
About Gemini 2.5 Pro Preview 05-06
The architecture supports simultaneous handling of text, images, files, audio and video. A context window of 1,048,576 tokens allows the model to ingest and reason over very long combined inputs. Access remains restricted to Google's hosted API since the weights are not released.
Its primary strength lies in unifying diverse modalities inside one forward pass without external tool chaining. Users typically apply it to long-form video understanding, multi-hour audio analysis, or document collections that mix text and visual elements. The preview designation indicates ongoing updates to capabilities and stability.
Capabilities
How Gemini 2.5 Pro Preview 05-06 compares
Gemini 2.5 Pro Preview 05-06 (striped bar) vs other multimodal on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · Gemini 2.5 Pro Preview 05-06 ranks #93 of 139
Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Large-scale Document Analysis
Processes and reasons over documents up to 1048576 tokens, making it suitable for summarizing extensive reports or reviewing full code repositories in one pass.
Multimedia Content Review
Handles audio and video analysis alongside text for tasks such as extracting insights from recorded meetings or moderating video content.
Complex Instruction Execution
Follows detailed multi-step instructions while generating code or processing files, ideal for building applications that require precise adherence to specifications.
Strengths & limitations
Strengths
- +Very large context window
- +Native support for multiple modalities
- +Strong cross-modal reasoning
- +Flexible file handling
Limitations
- –Preview version may show variability
- –High resource use with maximum context
- –Occasional modality-specific inconsistencies
Cost calculator
Estimate what Gemini 2.5 Pro Preview 05-06 would cost for your usage.
Based on Gemini 2.5 Pro Preview 05-06's $1.25/1M input · $10.00/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "google/gemini-2.5-pro-preview-05-06",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: google/gemini-2.5-pro-preview-05-06
Editor's verdict
Gemini 2.5 Pro Preview 05-06 is Google's proprietary multimodal with a 1049K-token context window.
At $10.00 per 1M output tokens, it is premium-priced for its class.
It is available through Google's API and aggregators like OpenRouter.
Best suited to very large context window and native support for multiple modalities.
Frequently asked questions
The model supports a context length of 1048576 tokens.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Other Gemini models
Sibling versions in the Gemini family from Google.