# Sarvam 105B API prices

Sarvam 105B (sarvam) — 131k context, 131k max output.
2 metered per-token offers from 3 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| FastRouter | $0.04 | $0.16 | — | 131k |
| NanoGPT | $0.054 | $0.2124 | $0.0336 | 131k |

## Summary

- Cheapest input: $0.04 per 1M tokens (FastRouter)
- Cheapest output: $0.16 per 1M tokens (FastRouter)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-09-01
- Inputs: text

## FAQ

### What is the cheapest Sarvam 105B API?

As of Oct 4, 2026, FastRouter has the lowest Sarvam 105B output price at $0.16 per 1M tokens, and FastRouter has the lowest input price at $0.04 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Sarvam 105B?

3 providers list Sarvam 105B on Sovyron; 2 of them sell it at a metered per-token price.

### Is Sarvam 105B free?

No provider in the Sovyron catalog lists a free tier for Sarvam 105B.

### What is the context window of Sarvam 105B?

Sarvam 105B supports a 131k-token context window and up to 131k output tokens.

HTML page: https://sovyron.com/models/sarvam-105b/
Full dataset: https://sovyron.com/data/catalog.json