Sarvam M
API id
sarvam-mInput / 1M
-
not listed
Output / 1M
-
not listed
Context window
8K
tokens
Max output
32K
tokens per reply
Hosts
1
1 listings
Released
-
date not published
Where to run it
1 host serve Sarvam M. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
SarvamCloud sarvam-m | - | sarvam-m |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
Similar models
This model has no listed price, so these are current models with similar capabilities.
Smaller Independent models
No similar Independent model keeps its key capabilities.
Other frontier labs
Open-weight picks
Call it
Using Sarvam's API.
Python
from litellm import completion
response = completion(
model="sarvam/sarvam-m",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
Which APIs offer Sarvam M?
Sarvam M runs on 1 API: Sarvam.
What is Sarvam M's context window?
8K tokens, with up to 32K tokens in one reply.
Is Sarvam M being retired?
It has been retired: Sarvam retired it on 5 Jun 2026.
What is Sarvam M's API model id?
Use sarvam-m with Sarvam.
Sources
Raw catalog entry for sarvam-m on Sarvam
{
"cache_creation_input_token_cost": 0,
"cache_creation_input_token_cost_above_1hr": 0,
"cache_read_input_token_cost": 0,
"deprecation_date": "2026-06-05",
"input_cost_per_token": 0,
"litellm_provider": "sarvam",
"max_input_tokens": 8192,
"max_output_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 0,
"source": "https://docs.sarvam.ai/changelog/2026/6/5.md",
"supports_reasoning": true
}