> For clean Markdown of any page, append `.md` to the page URL. > For a complete documentation index, see https://docs.sarvam.ai/llms.txt. > For full documentation content in one file, see https://docs.sarvam.ai/llms-full.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.sarvam.ai/_mcp/server. # Sarvam-105B > Sarvam-105B - 105B parameter flagship multilingual language model delivering state-of-the-art performance on Indian language understanding, reasoning, and generation tasks. **Sarvam-105B (Flagship Chat LLM)** Sarvam AI's flagship Mixture-of-Experts reasoning model trained from scratch, with Multi-head Latent Attention (MLA) for efficient long-context inference. Matches or outperforms most open and closed-source frontier models of its class across knowledge, reasoning, and agentic benchmarks. **Highlights:** * **105B+ total parameters** — our most capable MoE model with Multi-head Latent Attention * Pre-trained on **12 trillion tokens** across code, math, multilingual, and web data * **98.6 on Math500**, **88.3 on AIME 25** (96.7 with tools), **49.5 on BrowseComp** * State-of-the-art Indian language performance: wins 90% of pairwise comparisons * Powers **Indus**, Sarvam's AI assistant for complex reasoning and agentic workflows * OpenAI-compatible chat completions API | Apache 2.0 open-source ## At a Glance | | | | --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Model ID** | `sarvam-105b` (flagship) · [`sarvam-105b-conversations`](#conversational-variant) (conversational) | | **What it does** | Flagship chat LLM — complex reasoning, coding, and agentic workflows (105B+ MoE with MLA). The conversational variant is post-trained for real-time dialogue and voice-agent use cases. | | **Languages** | 10 most-spoken Indian languages + English; native script, romanized, and code-mixed input | | **APIs** | [Chat Completions](/api/api-guides-tutorials/chat-completion/overview) (`POST /v1/chat/completions`; `sarvam-105b` also on `/v2/chat/completions`, OpenAI-compatible, streaming supported) | | **Input limits** | 128K-token context window (`sarvam-105b`); 32K-token context window (`sarvam-105b-conversations`) — [all limits](#limits) | | **Benchmarks** | [Key Features](#key-features) and the [model blog](https://www.sarvam.ai/blogs/sarvam-30b-105b) | | **Pricing** | [Pricing page](/api/getting-started/pricing) | | **Best for** | Multi-step reasoning, code generation, long-context document analysis, agentic tool use | | **Known limitations** | [See below](#known-limitations) | ## Key Features #### Flagship Indian Language Support Wins 90% of pairwise comparisons across Indian language benchmarks and 84% on STEM, math, and coding. Trained extensively on native script, romanized, and code-mixed inputs across the 10 most-spoken Indian languages. #### Advanced Reasoning 98.6 on Math500, 88.3 on AIME 25 (96.7 with tools), 85.8 on HMMT, and 69.1 on Beyond AIME — reflecting deep multi-step reasoning and complex mathematical problem solving. #### Agentic Capabilities 49.5 on BrowseComp and 68.3 on Tau2 (avg.) — highest among compared models. Optimized for tool use, long-horizon reasoning, and environment interaction in real-world workflows. #### Efficient MoE Architecture Mixture-of-Experts Transformer with 128 sparse experts and Multi-head Latent Attention (MLA), a compressed attention formulation that reduces memory requirements for long-context inference. ## Learn More For detailed information on architecture, training methodology, performance benchmarks, and inference optimizations, visit [our blog](https://www.sarvam.ai/blogs/sarvam-30b-105b). ## Model Specifications #### Key Considerations * Model IDs: `sarvam-105b`, `sarvam-105b-conversations` * Total Parameters: 105B+ with MoE architecture and 128 sparse experts * Attention: Multi-head Latent Attention (MLA) * Pre-training Data: 12T tokens * Temperature range: 0 to 2 * Top-p range: 0 to 1 * Supports streaming and non-streaming responses * OpenAI-compatible chat completions format * License: Apache 2.0 **Sarvam-105B** is our flagship chat model, delivering the highest quality outputs for complex reasoning and agentic tasks. Use model ID **`sarvam-105b-conversations`** when you need a conversational variant tuned for real-time dialogue and voice agents — see [Conversational variant](#conversational-variant). **Sarvam-M (24B)** has been [deprecated](/api/getting-started/models/sarvam-m) and is no longer available through the API. ## Conversational variant Model ID **`sarvam-105b-conversations`** is a post-trained variant of Sarvam-105B for **real-time conversational workloads** — voice agents, chatbots, and multi-turn dialogue where natural, colloquial Indic responses matter more than deep reasoning traces. | | `sarvam-105b` | `sarvam-105b-conversations` | | ------------------ | ------------------------------------------------------------------ | ------------------------------------------------------------- | | **Best for** | Complex reasoning, coding, long-context analysis, agentic tool use | Real-time dialogue, voice agents, customer-facing chat | | **Endpoint** | `POST /v1/chat/completions` or `POST /v2/chat/completions` | `POST /v1/chat/completions` only | | **Context window** | 128K tokens | 32K tokens | | **Pricing** | [Sarvam 105B](/api/getting-started/pricing) | [Sarvam 105B Chat](/api/getting-started/pricing) — same rates | Both model IDs share the same OpenAI-compatible request schema and Indian language coverage, but `sarvam-105b-conversations` has a smaller 32K context window (vs. 128K for `sarvam-105b`). Pass the model ID in the `model` field — everything else stays the same. #### Python ```python from sarvamai import SarvamAI client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY") response = client.chat.completions( model="sarvam-105b-conversations", messages=[ {"role": "user", "content": "who are you?"} ], temperature=1, top_p=1, max_tokens=100, ) print(response.choices[0].message.content) ``` #### JavaScript ```javascript import { SarvamAIClient } from "sarvamai"; const client = new SarvamAIClient({ apiSubscriptionKey: "YOUR_SARVAM_API_KEY", }); async function main() { const response = await client.chat.completions({ model: "sarvam-105b-conversations", messages: [ { role: "user", content: "who are you?" }, ], temperature: 1, top_p: 1, max_tokens: 100, }); console.log(response.choices[0].message.content); } main(); ``` #### cURL ```bash curl -X POST https://api.sarvam.ai/v1/chat/completions \ -H "api-subscription-key: $SARVAM_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "messages": [ {"role": "user", "content": "who are you?"} ], "model": "sarvam-105b-conversations", "temperature": 1, "top_p": 1, "max_tokens": 100, "stream": false, "n": 1, "frequency_penalty": 0, "presence_penalty": 0 }' ``` ## Key Capabilities #### Basic Chat Completion Simple, one-turn interaction where the user asks a question and the model replies with the highest quality response leveraging its 105B parameter knowledge. #### Python ```python from sarvamai import SarvamAI client = SarvamAI( api_subscription_key="YOUR_SARVAM_API_KEY", ) response = client.chat.completions( model="sarvam-105b", messages=[ {"role": "user", "content": "Explain the economic impact of GST implementation in India."} ], temperature=0.5, top_p=1, max_tokens=2000, ) print(response.choices[0].message.content) ``` #### JavaScript ```javascript import { SarvamAIClient } from "sarvamai"; const client = new SarvamAIClient({ apiSubscriptionKey: "YOUR_SARVAM_API_KEY", }); async function main() { const response = await client.chat.completions({ model: "sarvam-105b", messages: [ { role: "user", content: "Explain the economic impact of GST implementation in India.", }, ], temperature: 0.5, top_p: 1, max_tokens: 2000, }); console.log(response.choices[0].message.content); } main(); ``` #### cURL ```bash curl -X POST https://api.sarvam.ai/v1/chat/completions \ -H "api-subscription-key: $SARVAM_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "messages": [ {"role": "user", "content": "Explain the economic impact of GST implementation in India."} ], "model": "sarvam-105b", "temperature": 0.5, "top_p": 1, "max_tokens": 2000 }' ``` #### Multi-turn Conversation Involves multiple exchanges between the system, user, and assistant. Sarvam-105B excels at maintaining deep context across long conversations. #### Python ```python from sarvamai import SarvamAI client = SarvamAI( api_subscription_key="YOUR_SARVAM_API_KEY", ) response = client.chat.completions( model="sarvam-105b", messages=[ {"role": "system", "content": "You are a senior legal advisor specializing in Indian corporate law."}, {"role": "user", "content": "What are the key compliance requirements for a startup in India?"}, {"role": "assistant", "content": "Key compliance requirements include company registration under the Companies Act 2013, GST registration, PF/ESI registration for employees, and annual filings with MCA."}, {"role": "user", "content": "Can you elaborate on the annual filing requirements and deadlines?"} ], temperature=0.3, top_p=1, max_tokens=2000 ) print(response.choices[0].message.content) ``` #### JavaScript ```javascript import { SarvamAIClient } from "sarvamai"; const client = new SarvamAIClient({ apiSubscriptionKey: "YOUR_SARVAM_API_KEY" }); async function main() { const response = await client.chat.completions({ model: "sarvam-105b", messages: [ { role: "system", content: "You are a senior legal advisor specializing in Indian corporate law." }, { role: "user", content: "What are the key compliance requirements for a startup in India?" }, { role: "assistant", content: "Key compliance requirements include company registration under the Companies Act 2013, GST registration, PF/ESI registration for employees, and annual filings with MCA." }, { role: "user", content: "Can you elaborate on the annual filing requirements and deadlines?" } ], temperature: 0.3, top_p: 1, max_tokens: 2000 }); console.log(response.choices[0].message.content); } main(); ``` #### cURL ```bash curl -X POST https://api.sarvam.ai/v1/chat/completions \ -H "api-subscription-key: $SARVAM_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "messages": [ {"role": "system", "content": "You are a senior legal advisor specializing in Indian corporate law."}, {"role": "user", "content": "What are the key compliance requirements for a startup in India?"}, {"role": "assistant", "content": "Key compliance requirements include company registration under the Companies Act 2013, GST registration, PF/ESI registration for employees, and annual filings with MCA."}, {"role": "user", "content": "Can you elaborate on the annual filing requirements and deadlines?"} ], "model": "sarvam-105b", "temperature": 0.3, "top_p": 1, "max_tokens": 2000 }' ``` #### Streaming Stream responses token-by-token for real-time output. Ideal for chat interfaces and applications requiring progressive response rendering. #### Python ```python from sarvamai import SarvamAI client = SarvamAI( api_subscription_key="YOUR_SARVAM_API_KEY", ) for chunk in client.chat.completions( model="sarvam-105b", messages=[ {"role": "user", "content": "Write a detailed analysis of India's digital transformation journey."} ], temperature=0.7, max_tokens=2000, stream=True, ): if chunk.choices: delta = chunk.choices[0].delta if delta.content: print(delta.content, end="", flush=True) print() ``` #### JavaScript ```javascript import { SarvamAIClient } from "sarvamai"; const client = new SarvamAIClient({ apiSubscriptionKey: "YOUR_SARVAM_API_KEY" }); async function main() { const stream = await client.chat.completions({ model: "sarvam-105b", messages: [ { role: "user", content: "Write a detailed analysis of India's digital transformation journey." } ], temperature: 0.7, max_tokens: 2000, stream: true, }); for await (const chunk of stream) { if (chunk.choices?.[0]?.delta?.content) { process.stdout.write(chunk.choices[0].delta.content); } } console.log(); } main(); ``` #### cURL ```bash curl -X POST https://api.sarvam.ai/v1/chat/completions \ -H "api-subscription-key: $SARVAM_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "messages": [ {"role": "user", "content": "Write a detailed analysis of India'\''s digital transformation journey."} ], "model": "sarvam-105b", "temperature": 0.7, "max_tokens": 2000, "stream": true }' ``` ## Limits | Limit | Value | | ---------------------------------------- | ---------------------------------------------------------------------------------------------- | | Context window | 128K tokens (`sarvam-105b`) / 32K tokens (`sarvam-105b-conversations`) | | `max_tokens` | Starter 4096 / Pro 16384 / Business 128000 | | `temperature` | 0–2 (default 0.5 when reasoning is enabled — the default — and 0.2 when reasoning is disabled) | | `top_p` | 0–1 | | `n` (completions per request) | 1–128 | | `frequency_penalty` / `presence_penalty` | -2 to 2 | | `stop` | Up to 4 sequences | | Rate limits | See [Rate Limits](/api/getting-started/ratelimits) | ## Known Limitations | Limitation | Detail | Workaround | | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------- | | **Thinking mode is on by default** | Reasoning (`reasoning_effort`, default `low`) is enabled by default, and reasoning tokens count toward completion tokens — a small `max_tokens` can be consumed entirely by reasoning | Increase `max_tokens` to leave room for the visible answer, or disable reasoning with `reasoning_effort=None` | ## Next Steps #### [Developer quickstart](/api/api-guides-tutorials/chat-completion/overview) Learn how to integrate chat completion into your application. #### [API Reference](/api-reference/chat/chat-completions) Complete API documentation for chat completion endpoints.