# Sarvam 105B 1711

> Sarvam's 105B MoE flagship joins the catalog on the new 1711 weights: 10.3B active parameters, a 128K context, tool calling and Indian-language support. BYOK only.

- Date: 2026-11-22
- HTML: https://anyrouter.dev/blog/releases/sarvam-105b-1711

## Models

- `sarvam/sarvam-105b` (Sarvam 105B) — Flagship 1711 weights. 105B total / 10.3B active MoE, 128K context, text in and out, tool calling and reasoning. BYOK.

## Notes

[`sarvam/sarvam-105b`](https://anyrouter.dev/model/sarvam/sarvam-105b) runs Sarvam's 1711 weights. It is a 105B-parameter sparse mixture-of-experts model with 10.3B active parameters and multi-head latent attention, built for reasoning, agentic tool use and the ten most-spoken Indian languages.

The API exposes a 128K context window. Reasoning is on by default and reasoning tokens count toward `max_tokens`; set `reasoning_effort` to `none` to turn it off. Open weights are Apache 2.0 in NVFP4 and BF16.

```ts
import { createAnyRouter } from "@anyr/ai-sdk-provider"
import { generateText } from "ai"
const anyrouter = createAnyRouter()
const { text } = await generateText({ model: anyrouter("sarvam/sarvam-105b"), prompt: "Hello" })
```

_AI SDK._

```bash
curl -fsSL https://anyr.dev/cli.sh | bash
anyr login
anyr claude --model "sarvam/sarvam-105b"
```

_Coding agent._

It is **BYOK-only**. Add your own Sarvam key under [Dashboard → BYOK](https://anyrouter.dev/dashboard/byok). AnyRouter does not charge credits for the hop. Read the [model card](https://huggingface.co/sarvamai/sarvam-105b-1711) for the full benchmark table.
