Migrating Chat Completion from Fireworks AI to Sarvam

Last updated: October 23, 2026

This guide covers moving Fireworks AI Chat Completions and Responses calls for open-weight models to Sarvam’s /v2 API.

Migration checklist

1. Create an API key in the Sarvam dashboard.
2. Change base_url to https://api.sarvam.ai/v2 and api_key to your Sarvam key.
3. Replace each model ID using the model ID table. Fast, US, and deployment IDs map to the same Sarvam ID.
4. Use string values for reasoning_effort (low, high, max, or none) (Reasoning).
5. Remove Fireworks-only fields: prompt_truncate_len, context_length_exceeded_behavior, perf_metrics_in_response, and others (list).
6. Set max_tokens explicitly: only glm5.3 defaults to 2048 on Sarvam.
7. Trim long conversations yourself: Sarvam doesn’t truncate prompts.
8. If you use the Responses API, follow Migrating the Responses API.
9. Run your tests and watch for 400 responses that name a field.

Quick start

from openai import OpenAI
client = OpenAI(
    api_key="YOUR_FIREWORKS_API_KEY",
    base_url="https://api.fireworks.ai/inference/v1",
)
response = client.chat.completions.create(
    model="accounts/fireworks/models/kimi-k3",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Suggest a name for a coffee shop in Bengaluru."},
    ],
    reasoning_effort="low",
    extra_body={"prompt_truncate_len": 100000},
)
print(response.choices[0].message.content)

Reasoning

Fireworks-only fields to remove

Sarvam validates request fields and returns 400 invalid_request_error with Unsupported parameter(s) for fields it doesn’t support, so leftover Fireworks options fail loudly instead of being ignored.

Parameter concept map

Responses API

Fireworks stores responses and chains them with previous_response_id; Sarvam’s Responses API is stateless, so you send the history in input instead. For base URL and field changes, reasoning items, function tools, and server-side tools, see Migrating the Responses API from Fireworks.

What’s different by design

• No deployments to manage. Models that need an on-demand deployment on Fireworks, such as Gemma 4 31B and DeepSeek V4 Pro, are called by model ID on Sarvam.
• Strict request validation. Unsupported fields return 400 with the field named, instead of being dropped silently. gemma4 is less strict: it accepts some fields, such as prediction and logit_bias, and ignores them.
• No silent truncation. Sarvam rejects a prompt that doesn’t fit, rather than cutting old messages or lowering max_tokens for you.
• Stateless Responses. Your app keeps the conversation history, as with Chat Completions.

Platform features without a direct equivalent

Full example

A wrapper with retries on 429 and 503, which Fireworks returns when it sheds load and Sarvam returns when a model is overloaded:

from openai import OpenAI
client = OpenAI(
    api_key="YOUR_FIREWORKS_API_KEY",
    base_url="https://api.fireworks.ai/inference/v1",
)
def ask(prompt: str) -> str:
    response = client.chat.completions.create(
        model="accounts/fireworks/models/deepseek-v4p1-flash",
        messages=[{"role": "user", "content": prompt}],
        reasoning_effort="low",
        extra_body={"context_length_exceeded_behavior": "truncate"},
    )
    return response.choices[0].message.content

Common mistakes

See also

• Migration overview: base URL, auth, and model IDs
• Chat Completion overview
• Responses API guide
• Open-Weight Models
• Errors & Troubleshooting