---
type: "post"
id: "served-over-mcp-parses-documents-with-sarvam-vision-3537ad"
slug: "served-over-mcp-parses-documents-with-sarvam-vision-3537ad"
title: "Served over MCP, parses documents with Sarvam Vision 2.1 , deployable air-gapped."
description: "Sarvam AI announced Sarvam Vision 2.1 on September 24, 2026, an update to its document-intelligence vision-language model."
retrieval_nugget: "Sarvam AI announced Sarvam Vision 2.1 on September 24, 2026, an update to its document-intelligence vision-language model."
published_at: "2026-10-26"
updated_at: "2026-10-26"
record_date: "2026-10-26"
date_kind: "published_at"
topics: ["mcp"]
entities: ["Sarvam AI","Sarvam Vision 2.1","olmOCR-Bench","OmniDocBench"]
related_patterns: ["harness-architecture-outlives-model-choice"]
novelty_label: "new_fact"
what_changed: "Sarvam Vision 2.1 adds production-oriented document parsing capabilities, cheaper optimized inference, and air-gapped deployment; the archive’s document-AI stories concern other products."
prior_refs: []
source_url: "https://www.sarvam.ai/blogs/sarvam-vision-2-1"
source_urls: ["https://www.sarvam.ai/blogs/sarvam-vision-2-1"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:served-over-mcp-parses-documents-with-sarvam-vision-3537ad"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/served-over-mcp-parses-documents-with-sarvam-vision-3537ad/","markdown":"https://newruntime.com/posts/served-over-mcp-parses-documents-with-sarvam-vision-3537ad.md","json":"https://newruntime.com/posts/served-over-mcp-parses-documents-with-sarvam-vision-3537ad.json"}
---

# Served over MCP, parses documents with Sarvam Vision 2.1 , deployable air-gapped.

## Retrieval answer

Sarvam AI announced Sarvam Vision 2.1 on September 24, 2026, an update to its document-intelligence vision-language model.

Sarvam AI announced Sarvam Vision 2.1 on September 24, 2026, an update to its document-intelligence vision-language model. The company says it adds stronger multi-page table parsing, key-value extraction from forms, and Indic handwritten-text recognition. Its architecture combines a VLM with a semantic layout parser and a reading-order network.

Sarvam reports an overall score of 87.30 on olmOCR-Bench, versus 86.10 for Infinity-Parser2 Pro and 85.10 for Opus 5 in its comparison table. On OmniDocBench v1.6, it reports 94.97, behind PaddleOCR-VL 1.6 at 96.01. The post also says inference-stack optimization lowered the serving price from the level announced at the original launch, without stating the new price.

The company describes the release as optimized for production workloads and says it addressed hallucinations and inconsistencies. The source does not provide independent benchmark validation, a public price, or evidence of performance on a specific customer's documents.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Mcp](https://newruntime.com/topics/mcp.md): Explore the mcp topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)