# Sarvam Prism decision model pricing and access by Sarvam AI

> Sarvam Prism returns probabilities for text or JSON questions. Compare its hosted API limits and rupee pricing with the custom FP8 weight package.

Updated 2026-11-07 (Australia/Adelaide)

## Quick answers

### What is Sarvam Prism by Sarvam AI?

[Sarvam Prism](<https://decisionmodels.ai/models/sarvam-prism>): A Sarvam-105B decision fine-tune, offered as custom FP8 weights and a hosted API.

[Sarvam Prism facts](<https://decisionmodels.ai/models/sarvam-prism>)

[Source](<https://www.sarvam.ai/blogs/sarvam-prism>)

### How much does Sarvam Prism cost?

[Sarvam Prism](<https://decisionmodels.ai/models/sarvam-prism>): Published price (vendor-reported): Sarvam API: ₹4 per million input tokens; output free

[Sarvam Prism facts](<https://decisionmodels.ai/models/sarvam-prism>)

[Source](<https://docs.sarvam.ai/api/token-factory/models/sarvam-prism>)

### Who makes Sarvam Prism?

[Sarvam Prism](<https://decisionmodels.ai/models/sarvam-prism>): Sarvam AI

[Sarvam Prism facts](<https://decisionmodels.ai/models/sarvam-prism>)

[Source](<https://www.sarvam.ai/blogs/sarvam-prism>)

### Are Sarvam Prism's weights open?

[Sarvam Prism](<https://decisionmodels.ai/models/sarvam-prism>): Public weights and prism.py; hosted POST /v2/systemone Licence: Apache-2.0

[Sarvam Prism facts](<https://decisionmodels.ai/models/sarvam-prism>)

[Source](<https://www.sarvam.ai/blogs/sarvam-prism>)

By Sarvam AI · Hugging Face package release: 2026-11-03 · OPEN

A Sarvam-105B decision fine-tune, offered as custom FP8 weights and a hosted API. It returns option probabilities without generating text. Choice options are sorted by key before scoring. The hosted API and downloadable runtime have different context limits.

## Facts

- Size: 105B; about 106 GB of weight files
- Inputs: Text or JSON; no images
- Context: Hosted: 32,768 tokens per question; local runtime: 131,072
- Hardware: Local FP8 runtime needs about 120 GB free GPU memory; tested on B200
- Licence: Apache-2.0
- Price: Sarvam API: ₹4 per million input tokens; output free · [Compare prices](<https://decisionmodels.ai/pricing>)
- Access: Public weights and prism.py; hosted POST /v2/systemone

## Claims and sources

- **VENDOR-REPORTED**: Sarvam reports 44 ms median and 420 ms p95 on 1,000 serial public-index requests on a B200. [source](<https://huggingface.co/sarvamai/prism>)
- **VENDOR-REPORTED**: In its 2,000-question shuffle test, fixed-order preprocessing yields zero changed answers; scoring options as sent changes 4.0%. Sorting is part of the tested system. [source](<https://www.sarvam.ai/blogs/sarvam-prism>)

## Links

- [Source: Launch and evaluation](<https://www.sarvam.ai/blogs/sarvam-prism>)
- [Source: Card, runtime and weights](<https://huggingface.co/sarvamai/prism>)
- [Source: Hosted API limits and price](<https://docs.sarvam.ai/api/token-factory/models/sarvam-prism>)

## Related projects

No related projects are listed in the registry.
