sarvam · Efficient
Sarvam 105B
Sarvam 105B is a 105B parameter chat completion model from Sarvam AI with multilingual support, streaming, tool calling, reasoning controls, and a 128k context window.
- Reasoning
- Tools
- Input
- Text
- Output
- Text
- Reasoning effort
- low · medium · high
- Discovery tier
- Efficient
Pricing
USD per 1M tokens- Input
- $0.054
- Output
- $0.21
- Cache read
- $0.0336
Reference prices as published by the model provider. API example
Specifications
- Context window
- 131.1K
- Max output
- 4.1K
- Average output (7 days)
- 1.1K tokens
- Longer than 74% of 468 models
Side by side
Sarvam 105B compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| Sarvam 105BsarvamThis model | Mistral Small 4 119BMistralRemove | |
|---|---|---|
| Provider | sarvam | Mistral |
| Discovery tier | Efficient | Open weights |
| Added | May 12, 2026 | Mar 16, 2026 |
| Limits | ||
| Context window | 131.07K | 262.14KBest |
| Max output | 4.1K | 16.38KBest |
| Average output | 1.1K tokens | 92 tokens |
| Pricing, USD per 1M tokens | ||
| Input | $0.054Best | $0.40 |
| Output | $0.21Best | $1.40 |
| Cache read | $0.0336 | — |
| Performance | ||
| Throughput | — | 128.8 tok/s |
| Time to first token | — | 0.7 s |
| Request success (24h) | — | 99.6% |
| Benchmark indexes | ||
| Intelligence Index | 8.8 | 9.0Best |
| Capabilities | ||
| Reasoning | Yes | Yes |
| Tools | Yes | Yes |
| Vision | No | Yes |
| Structured output | No | Yes |
| Reasoning effort | low, medium, high | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- Sarvam 105B
- Mistral Small 4 119B
Intelligence Index
- Sarvam 105B8.8
- Mistral Small 4 119B9.0
Sarvam 105B tested at high reasoning effort
Sarvam 105B: Better than 16% of 326 scored models
Document reasoning
AA-LCRv1.1
Reasoning across long documents
- Sarvam 105B: 0.0%
- Mistral Small 4 119B: 28.3%Top
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- Sarvam 105B: 11.0%Top
- Mistral Small 4 119B: 3.8%
GPQA Diamond
Graduate-level science questions
- Sarvam 105B: 73.8%Top
- Mistral Small 4 119B: 57.1%
IFBench
Following precise output instructions
- Sarvam 105B: 34.4%Top
- Mistral Small 4 119B: 32.8%
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- Sarvam 105B: 1.5%
- Mistral Small 4 119B: 10.6%Top
τ²-Bench Telecom
Tool use in a customer-support simulation
- Sarvam 105B: 46.8%Top
- Mistral Small 4 119B: 18.4%
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- Sarvam 105B: 0.0%
- Mistral Small 4 119B: 28.3%Top
Scores from Artificial Analysis, updated Oct 26, 2026. Sarvam 105B was tested at high reasoning effort; compare scores measured at the same effort.Artificial Analysis
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "sarvam-105b",
"reasoning_effort": "medium",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="sarvam-105b",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)