> 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. # GLM-5.3 > GLM-5.3 is a large-scale reasoning model built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1,048,576-token context window. GLM-5.3 is a large-scale reasoning model built for complex software engineering and long-horizon agent tasks. It supports text input and output with a **1,048,576-token context window**. ## At a glance | | | | ------------------ | ---------------------------------------------------------------------------------------------------------------------------------- | | **Model ID** | `glm5.3` | | **Best for** | Complex software engineering and long-horizon agent tasks | | **Context window** | 1,048,576 tokens | | **Input → output** | Text → text | | **Reasoning** | **`low`**, **`high`**, or **`max`** (default when omitted). See [Reasoning](#reasoning) | | **Tool calling** | Supported, including `parallel_tool_calls: false` | | **APIs** | [`POST /v2/chat/completions`](/api-reference/chat/chat-completions-v2) and [`POST /v2/responses`](/api-reference/responses/create) | | **Pricing** | ₹126 input · ₹20 cached input · ₹390 output per 1M tokens; reasoning is billed as output ([Pricing](/api/getting-started/pricing)) | ## Key capabilities #### Software engineering Reason across large repositories, implementation plans, and multi-step coding tasks. #### Long-horizon agents Use tool calling and extended context for workflows that require many dependent steps. #### Long context Process up to 1,048,576 tokens across the prompt and generated output. #### Streaming Receive reasoning and final-answer deltas as server-sent events. > **Tip** > > Moving from [OpenRouter](/api/token-factory/migrations/from-openrouter/overview), [Fireworks AI](/api/token-factory/migrations/from-fireworks/overview), or [Together AI](/api/token-factory/migrations/from-together/overview)? The migration guides map model IDs and request fields to Sarvam. ## Quickstart #### Python ```python from sarvamai import SarvamAI client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY") response = client.chat.completions_v2( model="glm5.3", messages=[ { "role": "user", "content": "Explain the difference between a B-tree and a B+ tree index.", } ], temperature=1, top_p=0.95, max_tokens=8000, ) print(response.choices[0].message.content) ``` #### JavaScript ```javascript import { SarvamAIClient } from "sarvamai"; const client = new SarvamAIClient({ apiSubscriptionKey: "YOUR_SARVAM_API_KEY", }); async function main() { const response = await client.chat.completionsV2({ model: "glm5.3", messages: [ { role: "user", content: "Explain the difference between a B-tree and a B+ tree index.", }, ], temperature: 1, top_p: 0.95, max_tokens: 8000, }); console.log(response.choices[0].message.content); } main(); ``` #### 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": "Explain the difference between a B-tree and a B+ tree index." } ], "temperature": 1, "top_p": 0.95, "max_tokens": 8000 }' ``` ## Supported parameters `model: "glm5.3"` on [Chat Completion V2](/api-reference/chat/chat-completions-v2) and [Responses](/api-reference/responses/create). Full request/response schemas live on those API reference pages; this table covers what's actually accepted for this model. | Parameter | Chat Completion V2 | Responses | | ----------------------------------------------------- | :------------------------------------------------: | :---------------------------------------------------------------------: | | Streaming (`stream`) | | | | Tool calling (`tools`, `tool_choice`) | | | | `parallel_tool_calls: false` enforced | | | | Structured output (`response_format` / `text.format`) | | | | Log probabilities (`logprobs`, `top_logprobs`) | `400` | `400` | | Multiple choices (`n` > 1) | `400` | `400` | | Reasoning control | `reasoning_effort`: `low`, `high`, `max` (default) | `reasoning.effort`: `low` or `high` only; literal `"max"` returns `400` | | Turn reasoning off | always thinks | always thinks | All `400`s above are `invalid_request_error` for unsupported/invalid parameters. ## Reasoning GLM-5.3 has three reasoning modes, `low`, `high`, and `max`, but which values you can pass depends on the API: | Route | Field | Accepted values | | ------------------------------------------------------------- | ------------------ | ------------------------------------------------------------------------------------------------------------------------ | | [Chat Completion V2](/api-reference/chat/chat-completions-v2) | `reasoning_effort` | `"low"`, `"high"`, or `"max"`; omitting the field also gives `max` | | [Responses](/api-reference/responses/create) | `reasoning.effort` | `"low"` or `"high"` only. To get `max`-level reasoning, omit the field, sending the literal string `"max"` returns `400` | Read the reasoning trace from `choices[].message.reasoning_content` on chat, or from the reasoning item's `content[0].text` in `output` on Responses. Its `summary` is empty unless you set `reasoning.summary` to `"auto"` or `"detailed"`. Reasoning tokens are billed as output tokens either way, and count against `max_tokens` on chat (defaults to `2048` when omitted) or `max_output_tokens` on Responses (no default, omitting it means unbounded generation). At the default `max` effort, reasoning often uses several thousand tokens, so leave room for the answer. Reasoning can't be turned off, but at `low` effort GLM-5.3 often skips it on simple prompts: `reasoning_tokens` is `0` and Responses returns no reasoning item. ## Response fields (chat) | Field | Notes | | -------------------------------------------------- | --------------------------------------------- | | `choices[].message.reasoning_content` | Reasoning trace; billed as completion tokens. | | `usage.completion_tokens_details.reasoning_tokens` | Tokens spent on reasoning. | Full response shape: [Chat Completion V2](/api-reference/chat/chat-completions-v2). ## Known limitations * **Output token budget.** `max_tokens` on chat defaults to `2048` when omitted; `max_output_tokens` on Responses has no default and allows unbounded generation. Reasoning counts against whichever budget applies, so a small `max_tokens` on chat can leave little or no room for the actual answer. * **Context-length checks are approximate**, and more conservative for Latin-script text than for Indic scripts. Treat the model's own limit as authoritative. Parameter errors (`n`, `logprobs`, `stop`, and similar) are documented on [Chat Completion V2](/api-reference/chat/chat-completions-v2). ## Limits and errors | Area | Limit or condition | API response | Recommended action | | -------------- | ------------------------------------------------ | ---------------------------------------------------------- | ------------------------------------------------------------------------- | | Context | Prompt tokens plus `max_tokens` exceed 1,048,576 | `400 invalid_request_error` | Shorten the prompt or reduce `max_tokens`. | | Output | `max_tokens` exceeds 1,048,576 | `400 invalid_request_error` | Set `max_tokens` within the context window. | | Modality | Request includes image input | `400 invalid_request_error` | Send text input only. | | Parameters | More than four `stop` sequences | `400 invalid_request_error` | Send at most four stop strings. | | Request body | Wrong JSON types (serde validation) | `400 invalid_request_error` | Match types in the API Reference; read `error.message`. | | Request size | Request body exceeds 10 MiB (10,485,760 bytes) | `413 invalid_request_error`, with the limit in the message | Shorten the prompt. | | Authentication | API key is missing or invalid | `403 invalid_api_key_error` | Check the `api-subscription-key` header. | | Model | Model ID is unknown or unavailable | `404 not_found_error` | Confirm the ID with [`GET /v2/models`](/api-reference/chat/models-v2). | | Quota | No credits remain | `402 insufficient_quota_error` | Add credits in the [dashboard](https://indus.sarvam.ai/billing?ref=docs). | | Rate limit | Request or concurrency limit is exceeded | `429 rate_limit_exceeded_error` | Back off and retry. | | Availability | Model remains overloaded after retries | `503 model_overloaded` | Retry later. |