Open-Weight Models on Sarvam AI

Run leading open-weight models on Sarvam infrastructure through the same OpenAI-compatible /v2 API, with your existing Sarvam API key and credits. Switching models is a one-line change to the model field.

GLM-5.3, GLM-5.3 Flash, and Gemma 4 31B are generally available. DeepSeek V4.1 Flash 1017, DeepSeek V4 Pro, Kimi K3, MiMo V2.6 Flash, and MiMo V2.6 Pro are in beta.

Choose a model

Pick a use case, or filter by status and input type. Click a model ID to copy it.

I need

Showing 8 of 8 models

GLM-5.3 GA

Software engineering and long-horizon agents.

Context: 1M
Reasoning: On, can't turn off
Input: Text
₹ per 1M in / out: ₹126 / ₹390

GLM-5.3 Flash GA

Faster GLM-5.3 with image input.

Context: 1M
Reasoning: On, can't turn off
Input: TextImage
₹ per 1M in / out: ₹13.5 / ₹45

Gemma 4 31B GA

Fast direct answers and image understanding.

Context: 256K
Reasoning: Off by default
Input: TextImage
₹ per 1M in / out: ₹35 / ₹90

DeepSeek V4.1 Flash 1017 Beta

Low-cost reasoning for long documents and agents.

Context: 1M
Reasoning: On, can turn off
Input: TextImage
₹ per 1M in / out: ₹25 / ₹105

DeepSeek V4 Pro Beta

Larger DeepSeek V4 for harder text reasoning.

Context: 1M
Reasoning: On, can turn off
Input: Text
₹ per 1M in / out: ₹115 / ₹350

Kimi K3 Beta

Always-on reasoning with image and video input.

Context: 1M
Reasoning: On, can't turn off
Input: TextImageVideo
₹ per 1M in / out: ₹270 / ₹1,350

MiMo V2.6 Flash Beta

Lowest-cost reasoning across text, image, audio, and video.

Context: 1M
Reasoning: On, can turn off
Input: TextImageAudioVideo
₹ per 1M in / out: ₹12.5 / ₹25

MiMo V2.6 Pro Beta

Larger MiMo V2.6 for harder multimodal tasks.

Context: 1M
Reasoning: On, can turn off
Input: TextImageAudioVideo
₹ per 1M in / out: ₹40 / ₹80

Prices are in ₹ per 1M tokens; reasoning is billed as output. See Pricing. Each model’s reasoning default, and how to turn it off, is under Reasoning.

Every model supports tool calling, streaming, and structured output (response_format). Support for log probabilities, multiple choices (n > 1), and other parameters varies by model — see each model’s own Supported Parameters table, or V2 feature support for the full matrix.

All models as a table

Model	Context	Input	₹ per 1M in / out
GLM-5.3 `glm5.3`	1M	Text	126 / 390
GLM-5.3 Flash `glm5.3-flash`	1M	Text, image	13.5 / 45
Gemma 4 31B `gemma4`	256K	Text, image	35 / 90
DeepSeek V4.1 Flash 1017 (beta) `deepseekv4.1-flash-1017`	1M	Text, image	25 / 105
DeepSeek V4 Pro (beta) `deepseekv4-pro`	1M	Text	115 / 350
Kimi K3 (beta) `kimi-k3`	1M	Text, image, video	270 / 1,350
MiMo V2.6 Flash (beta) `mimo-v2.6-flash`	1M	Text, image, audio, video	12.5 / 25
MiMo V2.6 Pro (beta) `mimo-v2.6-pro`	1M	Text, image, audio, video	40 / 80

Coding and agents: glm5.3, the strongest reasoning
Lowest cost: mimo-v2.6-flash, the lowest per-token price
Fastest answers, with image input: gemma4, which skips reasoning by default
Reasoning on images: glm5.3-flash or kimi-k3

Quickstart

Get an API key

Create an API key in the dashboard.

Set your key

export SARVAM_API_KEY="your-api-key"

Make your first call

Open-weight models are served on POST /v2/chat/completions. Pick your SDK:

Python (Sarvam SDK)

Python (OpenAI SDK)

JavaScript

cURL

import os
from sarvamai import SarvamAI
client = SarvamAI(api_subscription_key=os.environ["SARVAM_API_KEY"])
response = client.chat.completions_v2(
    model="glm5.3",  # or "gemma4", "deepseekv4.1-flash-1017", "kimi-k3", ...
    messages=[
        {"role": "user", "content": "Summarise the causes of the 2008 financial crisis."}
    ],
    max_tokens=1000,
)
print(response.choices[0].message.content)

Already use the OpenAI SDK? Point base_url at https://api.sarvam.ai/v2 and pass your Sarvam key as api_key. The endpoint also accepts Authorization: Bearer <key>. Native Sarvam clients use the api-subscription-key header. See Authentication.

Common patterns

Streaming

Reasoning

Tool calling

Images (Gemma)

Set stream=True to receive server-sent events. Reasoning models stream reasoning_content deltas first, then the final content.

stream = client.chat.completions.create(
    model="glm5.3",
    messages=[{"role": "user", "content": "What is 17 * 23?"}],
    reasoning_effort="low",
    max_tokens=1000,
    stream=True,
)
for chunk in stream:
    if not chunk.choices:
        continue
    delta = chunk.choices[0].delta
    if getattr(delta, "reasoning_content", None):
        print(delta.reasoning_content, end="", flush=True)  # thinking
    if delta.content:
        print(delta.content, end="", flush=True)  # answer

Reasoning

Most models think before answering; Gemma 4 does only when you set an effort. Defaults, and whether thinking can be turned off, differ by model:

Model	Default effort	Turn thinking off
`glm5.3`	`max`	Not supported
`glm5.3-flash`	`high`	Not supported
`gemma4`	Off; turn it on with `reasoning_effort` (`low` or `high` on Responses)	Off by default
`deepseekv4.1-flash-1017`	`high`	`reasoning_effort: "none"`
`deepseekv4-pro`	`high`	`reasoning_effort: "none"` or `thinking: {"type": "disabled"}`
`kimi-k3`	`max`	Not supported; thinking is always on
`mimo-v2.6-flash`, `mimo-v2.6-pro`	On	`reasoning_effort: "none"`, `thinking: {"type": "disabled"}`, or `chat_template_kwargs.enable_thinking: false`. Other effort values only switch thinking on

Send thinking and chat_template_kwargs through extra_body in the SDKs. Accepted effort values are listed on each model page.

On the Responses API, do not send the string "max" to glm5.3 or glm5.3-flash. It returns 400. Omit reasoning.effort instead: that gives max on glm5.3 and high on glm5.3-flash.

Reasoning tokens count toward max_tokens and are billed as output. If you see empty content with finish_reason: "length", the model spent the whole budget thinking. Raise max_tokens or lower the effort. On glm5.3, max_tokens defaults to 2048.

Troubleshooting

Symptom	Likely cause	Fix
`403 invalid_api_key_error`	Missing or wrong key header	Check `api-subscription-key` or the Bearer token
`404 not_found_error`	Unknown or wrongly cased model ID	IDs are case-sensitive. List the models enabled for your key with `GET /v2/models`
`400` “This model is currently in beta”	Your key doesn’t have beta access	Contact us to enable beta models for your key
Empty `content`, `finish_reason: "length"`	Reasoning used the token budget	Raise `max_tokens` or lower `reasoning_effort`
`400 invalid_request_error` on a specific parameter	Parameter unsupported by this model	Check the model’s own Supported Parameters table
`402 insufficient_quota_error`	No credits left	Add credits in the dashboard
`429 rate_limit_exceeded_error` / `model_rate_limit_exceeded_error`, or `503 model_overloaded`	Rate limit, model capacity, or overload	Retry with exponential backoff

Production tips

Retry on 429 and 503

Rate limits and temporary overload are retryable. The OpenAI SDK retries these automatically with backoff when you raise max_retries:

client = OpenAI(
    base_url="https://api.sarvam.ai/v2",
    api_key=os.environ["SARVAM_API_KEY"],
    max_retries=4,
    timeout=120,  # reasoning at high effort can take a while
)

Budget tokens for reasoning

Set max_tokens well above your expected answer length, at least a few thousand for high or max effort, because thinking tokens share the same budget.

Match effort to the task

Use low for extraction, classification and chat. Reserve high and max for math, debugging and multi-step planning, where extra thinking improves quality at higher latency and cost.

Switch models without code changes

Read the model ID from configuration, for example model=os.environ.get("SARVAM_MODEL", "glm5.3"), so you can compare models on your own prompts. Only change parameters the target model supports, see the comparison table above.

Platform details

Endpoints and model discovery

Chat: POST https://api.sarvam.ai/v2/chat/completions, see the API reference.
Responses: POST https://api.sarvam.ai/v2/responses, see the API reference.
Models: GET /v2/models lists the models enabled for your key. Beta models appear only for keys that have beta access.

Billing and rate limits

Usage is metered per token against your Sarvam credits, see Pricing. Reasoning is billed as output. Limits apply per API key, see Credits & Rate Limits.

Beta models

DeepSeek V4.1 Flash 1017, DeepSeek V4 Pro, Kimi K3, MiMo V2.6 Flash, and MiMo V2.6 Pro are in beta. See Beta models.

Next steps

Chat Completions guide

Streaming, tool calling and structured outputs.

Responses API

Stateless responses with reasoning and tools.

Pricing

Per-token rates for every model.

Migrate from another provider

Move from OpenRouter, Fireworks AI, or Together AI.