Gemini 2.5 Pro
model
gemini-2-5-proMidStableVisionStreamingVisionToolsBatchLong contextUnited States
Context
1.0M
Input / 1M tokens
$1.25
Output / 1M tokens
$10.00
Cached input / 1M tokens
$0.2938
Cache write / 1M tokens
— (bills at input price)
About this model
Gemini 2.5 Pro
Gemini 2.5 Pro — Google's flagship reasoning model with 2M-token context. Best for long-document analysis where you need to feed entire codebases, books, or video transcripts in one prompt.
Key facts
- Maker
- Context window
- 1.0M tokens
- Max output
- 66K tokens
- Lane
- Guarded: the provider has confirmed it does not train on your data
- Modality
- Text and image input
- Input price
- $1.25 per 1M tokens
- Output price
- $10.00 per 1M tokens
- Processing region(s)
- us
- Route
- Via Google's API
- Cheapest plan
- Available from the Pro plan
- Price comparison
- Priced below 51 of 250 pro-band guarded models on Anoman (blended price: 1 part input to 3 parts output).
Released
2025-03
Training cutoff
2024-09
Parameters
Not disclosed (MoE)
Ways to call
Ways to call Gemini 2.5 Pro
Each model ID below is callable through the Anoman AI API. Price and processing region depend on the route.
| Model ID | Route | Input / output per 1M tokens | Region(s) | Lane | Context |
|---|---|---|---|---|---|
| gemini-2-5-pro | Via Google's API | $1.25 / $10.00 | us | Guarded | 1.0M |
| gemini-2.5-pro | Via Google's API | $1.25 / $10.00 | us | Guarded | 1.0M |
Best for
Use cases
- Very long-document analysis (up to 2M tokens)
- Codebase-wide refactoring questions
- Multimodal RAG over PDFs
- Reasoning over structured data
Strengths
What it does well
- 2M-token context window — largest in catalog
- Strong on long-context retrieval (Needle-in-a-haystack)
- Native multimodal (images, audio, video)
- Competitive pricing for long-context
Limitations
Know the trade-offs
- Tool calling less reliable than GPT-5.x / Claude
- Refusal behavior more conservative
- Throughput slow at very long contexts
Code example
Chat completion with Gemini 2.5 Pro
from openai import OpenAI
client = OpenAI(
base_url="https://api.anoman.io/v1",
api_key="anm-sk-..."
)
response = client.chat.completions.create(
model="gemini-2-5-pro",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)Alternatives
Similar models in our catalog
Same maker first, then the closest price to Gemini 2.5 Pro in the Anoman catalog.