Sarvam Vision
Sarvam Vision is Sarvam AI's document vision model for Indic and English pages. The documented API model ID is sarvam-vision, a 3B vision-language model covering 23 languages (22 Indian languages plus English).
Provider
Sarvam AI
Model family
Sarvam
Vision-language model
Cost tier
Vision
Status
Current
Release Sep 24, 2026
Why teams choose it
Use the API ID sarvam-vision. Do not send sarvam-vision-2-1
that string is not the documented model ID.
The September 24, 2026 post describes better tables, key-value extraction, Indic
handwriting, and cheaper inference for this document model.
Sarvam's marketing pricing page lists ₹0.50 per page
Hosted GLM, Gemma, and DeepSeek models on Sarvam are not Sarvam models.
Tradeoffs to know
- Ten pages per PDF and 200 MB per file. The docs rate limit is 10 requests per minute.
When not to use this
- This is not Sarvam 105B. Chat rates on the docs pricing page and the marketing pricing page differ for 105B and are not applied here.
Technical specs
- Inputs
- image, document
- Outputs
- text
- Capabilities
- document digitisation, key-value extraction, indic handwriting, 23 languages
- License
- Proprietary API
- Source
- https://docs.sarvam.ai/api/getting-started/models/sarvam-vision
- Languages
- 23
- Parameters
- 3B
- Max File Mb
- 200
- Max Pdf Pages
- 10
- Price Inr Per Page
- 0.5
- Requests Per Minute
- 10
Benchmarks
No independent or vendor benchmark scores in this catalog entry.
Sarvam family lineup
Related models
Sarvam Vision FAQ
What is Sarvam Vision?
Sarvam Vision is Sarvam AI's document vision model for Indic and English pages. The documented API model ID is sarvam-vision, a 3B vision-language model covering 23 languages (22 Indian languages plus English). Document AI digitise and extract accept up to 10 pages per PDF and 200 MB per file, at 10 requests per minute. Sarvam's public pricing page lists ₹0.50 per page. The September 24, 2026 post describes Vision 2.1 as a capability update; the docs still use sarvam-vision.
When does Sarvam Vision fit best?
Indic document digitisation
What should teams watch out for with Sarvam Vision?
Ten pages per PDF and 200 MB per file. The docs rate limit is 10 requests per minute.
Explore next
Models, tools, and comparisons that connect to this reference.