Any info on the upcoming 2.5 Pro Batch API would be much appreciated, specifically:
- date of arrival
- discount % vs real-time API
- any rate limits such as RPD
Many Thanks,
Elias
Any info on the upcoming 2.5 Pro Batch API would be much appreciated, specifically:
Many Thanks,
Elias
Here are the updates on the Gemini 2.5 Pro Batch API based on official sources and news:
1.Date of Arrival
Gemini 2.5 Pro launched in public preview on April 4, 2025 via the Gemini API in Google AI Studio, with Vertex AI support rolling out gradually .
General availability (including batch access) is expected by June 2025, aligning with scheduled release timelines .
2.Discount vs Real-Time API
Pricing for Batch API tokens (input/output) is the same as real-time:
For prompts ≤ 200k tokens:
Input: $1.25 per million tokens
Output: $10.00 per million tokens
For prompts >200k tokens:
Input: $2.50 per million tokens
Output: $15.00 per million tokens
There’s no extra discount for batch usage—they share the same pricing tiers.
3.Rate Limits
Rate limits for Gemini APIs—including batch and real-time are governed by:
These limits vary by usage tier:
You can request upgrades or rate limit increases via the AI Studio dashboard once your project qualifies.