Gemini 2.5 Flash
model
gemini-2-5-flashBudgetStableVisionStreamingVisionToolsBatchLong contextUnited States
Context
1.0M
Input / 1M tokens
$0.3000
Output / 1M tokens
$2.50
Cached input / 1M tokens
$0.0705
Cache write / 1M tokens
— (bills at input price)
About this model
Gemini 2.5 Flash
Gemini 2.5 Flash — speed + cost-optimized variant of 2.5 Pro. Sub-second TTFT, 1M-token context, native multimodal at budget pricing. Best for high-volume multimodal workloads.
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
- $0.3000 per 1M tokens
- Output price
- $2.50 per 1M tokens
- Processing region(s)
- us
- Route
- Via Google's API
- Cheapest plan
- Available from the Pro plan
- Price comparison
- Priced below 127 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 Flash
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-flash | Via Google's API | $0.3000 / $2.50 | us | Guarded | 1.0M |
| gemini-2.5-flash | Via Google's API | $0.3000 / $2.50 | us | Guarded | 1.0M |
Best for
Use cases
- High-volume image + document processing
- Real-time multimodal UX
- Long-context RAG at scale
- Cheap-tier for cost-sensitive customers
Strengths
What it does well
- 1M-token context at budget price
- Native multimodal
- Sub-second TTFT typical
- Strong extraction + classification
Limitations
Know the trade-offs
- Reasoning depth limited vs 2.5 Pro
- Code generation trails dedicated coders
Code example
Chat completion with Gemini 2.5 Flash
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-flash",
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 Flash in the Anoman catalog.