> This page is for Model APIs. > Sarvam Voice Agents (Samvaad) is a voice AI agent platform for Indian languages: build, test and deploy AI calling agents on your own phone numbers, from ₹3 a minute. Start here: https://docs.sarvam.ai/voice-agents/why-voice-agents. > For clean Markdown of any page, append `.md` to the page URL. > For a complete documentation index, see https://docs.sarvam.ai/llms.txt. For a section index, append `/llms.txt` to any section URL (for example https://docs.sarvam.ai/voice-agents/llms.txt). > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.sarvam.ai/_mcp/server. # Open-Weight Models > Open-weight models served on Sarvam infrastructure through the OpenAI-compatible chat completions API, using your existing Sarvam API key and credits. 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. > **Note** > > 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](/api-reference/beta-apis). ## Choose a model Pick a use case, or filter by status and input type. Click a model ID to copy it. Prices are in ₹ per 1M tokens; reasoning is billed as output. See [Pricing](/api/getting-started/pricing). Each model's reasoning default, and how to turn it off, is under [Reasoning](#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](/api/token-factory/chat-completions#v2-feature-support) for the full matrix. #### All models as a table | Model | Context | Input | ₹ per 1M in / out | | --------------------------------------------------------------------------------------------------------------- | ------: | ------------------------- | ----------------: | | [GLM-5.3](/api/token-factory/models/glm-5-3) `glm5.3` | 1M | Text | 126 / 390 | | [GLM-5.3 Flash](/api/token-factory/models/glm-5-3-flash) `glm5.3-flash` | 1M | Text, image | 13.5 / 45 | | [Gemma 4 31B](/api/token-factory/models/gemma-4-31b) `gemma4` | 256K | Text, image | 35 / 90 | | [DeepSeek V4.1 Flash 1017](/api/token-factory/models/deepseek-v4.1-flash-1017) (beta) `deepseekv4.1-flash-1017` | 1M | Text, image | 25 / 105 | | [DeepSeek V4 Pro](/api/token-factory/models/deepseek-v4-pro) (beta) `deepseekv4-pro` | 1M | Text | 115 / 350 | | [Kimi K3](/api/token-factory/models/kimi-k3) (beta) `kimi-k3` | 1M | Text, image, video | 270 / 1,350 | | [MiMo V2.6 Flash](/api/token-factory/models/mimo-v2.6-flash) (beta) `mimo-v2.6-flash` | 1M | Text, image, audio, video | 12.5 / 25 | | [MiMo V2.6 Pro](/api/token-factory/models/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](https://indus.sarvam.ai/key-management?ref=docs). #### Set your key ```bash 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 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) ``` #### Python (OpenAI SDK) ```python import os from openai import OpenAI client = OpenAI( base_url="https://api.sarvam.ai/v2", api_key=os.environ["SARVAM_API_KEY"], ) response = client.chat.completions.create( 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) ``` #### JavaScript ```javascript import { SarvamAIClient } from "sarvamai"; const client = new SarvamAIClient({ apiSubscriptionKey: process.env.SARVAM_API_KEY, }); const response = await client.chat.completionsV2({ 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, }); console.log(response.choices[0].message.content); ``` #### cURL ```bash curl -X POST https://api.sarvam.ai/v2/chat/completions \ -H "api-subscription-key: $SARVAM_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "glm5.3", "messages": [ {"role": "user", "content": "Summarise the causes of the 2008 financial crisis."} ], "max_tokens": 1000 }' ``` > **Info** > > **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 `. Native > Sarvam clients use the `api-subscription-key` header. See [Authentication](/api-reference/authentication). ## Common patterns #### Streaming Set `stream=True` to receive server-sent events. Reasoning models stream `reasoning_content` deltas first, then the final `content`. ```python 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 Control thinking depth with `reasoning_effort`. Accepted values and the default vary by model — see the [Reasoning](#reasoning) table below. The thinking is returned separately in `reasoning_content`. ```python response = client.chat.completions.create( model="glm5.3-flash", messages=[{"role": "user", "content": "Is 391 prime? Explain briefly."}], reasoning_effort="low", max_tokens=1500, ) message = response.choices[0].message print("Thinking:", message.reasoning_content) print("Answer:", message.content) ``` #### Tool calling Use OpenAI-style `tools`. When the model decides to call a function, the response has `finish_reason: "tool_calls"`. ```python tools = [{ "type": "function", "function": { "name": "get_weather", "description": "Get the current weather for a city", "parameters": { "type": "object", "properties": {"city": {"type": "string"}}, "required": ["city"], }, }, }] response = client.chat.completions.create( model="glm5.3-flash", messages=[{"role": "user", "content": "What's the weather in Pune?"}], tools=tools, max_tokens=1000, ) call = response.choices[0].message.tool_calls[0] print(call.function.name, call.function.arguments) # get_weather {"city":"Pune"} ``` #### Images (Gemma) `gemma4` accepts images as **base64 data URIs**. Remote `http(s)` URLs are rejected. ```python import base64 with open("chart.png", "rb") as f: encoded = base64.b64encode(f.read()).decode() response = client.chat.completions.create( model="gemma4", messages=[{ "role": "user", "content": [ {"type": "text", "text": "What trend does this chart show?"}, {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{encoded}"}}, ], }], max_tokens=500, ) print(response.choices[0].message.content) ``` ## 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](/api/token-factory/models). > **Warning** > > 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`. > **Tip** > > 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`](/api-reference/chat/models-v2) | | `400` "This model is currently in beta" | Your key doesn't have beta access | [Contact us](/api/getting-started/help) 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](https://indus.sarvam.ai/billing?ref=docs) | | `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`: ```python 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](/api-reference/chat/chat-completions-v2). * **Responses:** `POST https://api.sarvam.ai/v2/responses`, see the [API reference](/api-reference/responses/create). * **Models:** [`GET /v2/models`](/api-reference/chat/models-v2) 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](/api/getting-started/pricing). Reasoning is billed as output. Limits apply per API key, see [Credits & Rate Limits](/api/getting-started/pricing#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](/api-reference/beta-apis). ## Next steps #### [Chat Completions guide](/api/token-factory/chat-completions) Streaming, tool calling and structured outputs. #### [Responses API](/api-reference/responses/create) Stateless responses with reasoning and tools. #### [Pricing](/api/getting-started/pricing) Per-token rates for every model. #### [Migrate from another provider](/api/token-factory/migrations/from-openrouter/overview) Move from OpenRouter, Fireworks AI, or Together AI.