# Sarvam Prism: an open-weights decision model on Sarvam 105B that returns probabilities, not text

Canonical: https://theagenticweekly.com/news/sarvam-prism-open-weights-decision-model · Evidence: Reported · First seen: 2026-11-04 12:58 UTC · Source published: not stated by the source · Brief published: 2026-11-04 13:05 UTC · Updated: 2026-11-04 13:05 UTC · Author: Agentic Weekly

> Sarvam Prism, released by Sarvam AI on November 3, 2026, is a decision model built on Sarvam 105B: you send an input and questions with fixed options, and it returns a probability for every option. Its model card says "It does not generate text, so the answer is always one of your options." Weights are Apache 2.0.

Models in this brief: [Sarvam Prism](https://theagenticweekly.com/models/sarvam-prism)

## What changed

- Sarvam AI's release post (Nov 3, 2026) introduces Prism as a "System One" decision model trained on the Sarvam 105B-10B base, which the post ties to mixture-of-experts trade-offs.
- It answers yes/no, pick-one and ordered-scale questions about a text or JSON input with a probability for every option, in one call; images are not supported (hosted API docs).
- Weights are on Hugging Face (sarvamai/prism) under Apache 2.0. Running them needs one NVIDIA GPU with FP8 support and about 120 GB of free memory, such as a B200 or H200, and about 106 GB of disk.
- The hosted API (model ID sarvam-prism, POST /v2/systemone) costs ₹4 per 1M input tokens with output not billed, and allows 32,768 tokens per question and 2 to 255 options per choice question.
- Sarvam reports a 71.8 average across three indices at a 44 ms median response on one B200, which it calls the highest score under 100 ms among the 25 decision models it tested; it scores 82.5 on Sarvam's internal Indian-language benchmark.

## Who it matters for

Teams that today prompt a chat model to "answer yes or no" or "pick one of these labels" and then parse the reply: ticket routing, triage, moderation, prompt-injection checks and judging agent runs. Prism returns a typed answer with a probability, so your code sets the threshold for acting on its own. Sarvam's agent-trace test (700 recorded runs) puts Prism at 78.5% accuracy against 70.7% for Claude Haiku 5.5, on Sarvam's own setup.

Sarvam credits TypeSafe's Jev with starting the decision-model category last month; Prism adds an Apache 2.0 option that enterprises can fine-tune on their own decision data. Self-hosting is a data-center job, though: one B200 or H200 class GPU. Teams without that hardware would use the hosted API, priced in rupees.

## In the source's words

> "It does not generate text, so the answer is always one of your options."
> (Sarvam-Prism model card, Hugging Face, https://huggingface.co/sarvamai/prism)

> "We are releasing Prism with open weights so that enterprises can train this calibrated base on their own data and run it on their own infrastructure."
> (Sarvam AI blog, Introducing Sarvam Prism, https://www.sarvam.ai/blogs/sarvam-prism)

## What we have not verified

- We have not run Prism, locally or through the API.
- All benchmark, speed and calibration numbers are Sarvam's own; it ran the 25 models through its indices itself, one index is Sarvam's recreation of the Artificial Analysis Decision Index and another is internal.
- The release post says the model handles up to 131,072 tokens per question; the hosted API docs list 32,768. We report the API limit.
- Pricing is as listed in Sarvam's API docs on November 4, 2026.

## Timeline

- Source published: not stated by the source
- First seen by our watcher: 2026-11-04 12:58 UTC (via X news search (daily release scan))
- Brief published: 2026-11-04 13:05 UTC

## Sources

- [Sarvam AI blog: Introducing Sarvam Prism (Nov 3, 2026)](https://www.sarvam.ai/blogs/sarvam-prism) (primary source) (fetched 2026-11-04)
- [Sarvam-Prism model card, Hugging Face](https://huggingface.co/sarvamai/prism) (primary source) (fetched 2026-11-04)
- [Sarvam API docs: Sarvam Prism](https://docs.sarvam.ai/api/token-factory/models/sarvam-prism) (primary source) (fetched 2026-11-04)

## Related

- [Sarvam Prism: specs, price and alternatives](https://theagenticweekly.com/models/sarvam-prism)
- [All news briefs](https://theagenticweekly.com/news)
- [This week's releases](https://theagenticweekly.com/this-week)
- [New AI models this week](https://theagenticweekly.com/models/this-week)
- [AI model releases by month](https://theagenticweekly.com/models/releases)
- [Best LLM for coding](https://theagenticweekly.com/best/llm-for-coding)

## How to cite

Agentic Weekly, "Sarvam Prism: an open-weights decision model on Sarvam 105B that returns probabilities, not text", published 2026-11-04 13:05 UTC, https://theagenticweekly.com/news/sarvam-prism-open-weights-decision-model