Chat Completions Overview

Sarvam AI provides powerful chat completion APIs designed to build intelligent conversational AI experiences, with native support for Indian languages and deep contextual reasoning.

Our Chat Completion APIs support the following chat models:

Model Variants

Both Sarvam-30B (64K context) and Sarvam-105B (128K context) also have shorter-context variants that are more cost-efficient for workloads that don’t need the full context window:

Simply pass the variant name as the model parameter (e.g., model="sarvam-105b-32k") to use the extended context version.

Features

Code Examples

1
from sarvamai import SarvamAI
2
3
client = SarvamAI(
4
    api_subscription_key="YOUR_SARVAM_API_KEY",
5
)
6
response = client.chat.completions(messages=[
7
    {"role": "user", "content": "Hey, what is the capital of India?"}
8
])
9
print(response)

API Response Format

Success Response Structure

1
{
2
  "id": "chatcmpl-abc123",
3
  "object": "chat.completion",
4
  "created": 1699000000,
5
  "model": "sarvam-105b",
6
  "choices": [
7
    {
8
      "index": 0,
9
      "message": {
10
        "role": "assistant",
11
        "content": "The capital of India is New Delhi. It has been the capital since 1931."
12
      },
13
      "finish_reason": "stop"
14
    }
15
  ],
16
  "usage": {
17
    "prompt_tokens": 15,
18
    "completion_tokens": 25,
19
    "total_tokens": 40
20
  }
21
}

Response Fields

Error Responses

All errors return a JSON object with an error field containing details about what went wrong.

Error Response Structure

1
{
2
  "error": {
3
    "message": "Human-readable error description",
4
    "code": "error_code_for_programmatic_handling",
5
    "request_id": "unique_request_identifier"
6
  }
7
}

Error Codes Reference

Example Error Response

1
{
2
  "error": {
3
    "message": "Invalid value for parameter 'temperature': must be between 0 and 2",
4
    "code": "unprocessable_entity_error",
5
    "request_id": "20241115_abc12345"
6
  }
7
}

1
from sarvamai import SarvamAI
2
from sarvamai.core.api_error import ApiError
3
4
client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
5
6
try:
7
    response = client.chat.completions(
8
        messages=[
9
            {"role": "user", "content": "What is the capital of India?"}
10
        ]
11
    )
12
    print(response.choices[0].message.content)
13
except ApiError as e:
14
    if e.status_code == 400:
15
        print(f"Bad request: {e.body}")
16
    elif e.status_code == 403:
17
        print("Invalid API key. Check your credentials.")
18
    elif e.status_code == 422:
19
        print(f"Invalid parameters: {e.body}")
20
    elif e.status_code == 429:
21
        print("Rate limit exceeded. Wait and retry.")
22
    else:
23
        print(f"Error {e.status_code}: {e.body}")