> 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 Flash > GLM-5.3 Flash is a faster open-weight reasoning model with text and image input, a 1,048,576-token context window, and tool calling. GLM-5.3 Flash is a faster sibling of [GLM-5.3](/api/token-factory/models/glm-5-3), served on Sarvam infrastructure as an [open-weight model](/api/token-factory/models). It accepts **text and images** and has a **1,048,576-token context window**. ## At a glance | | | | ------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------- | | **Model ID** | `glm5.3-flash` | | **Best for** | Fast reasoning, agents, and image understanding | | **Context window** | 1,048,576 tokens | | **Input → output** | Text + image → text | | **Reasoning** | **`low`**, **`high`** (default when omitted), or **`max`**. 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** | ₹13.5 / ₹2.5 cached / ₹45 per 1M tokens (input / cached input / output); reasoning is billed as output — see [Pricing](/api/getting-started/pricing) | ## Key capabilities #### Long context Process up to 1,048,576 tokens across the prompt, reasoning, and generated output. #### Image input Send base64-encoded images alongside text. #### Reasoning Receive reasoning in `reasoning_content` separately from the final answer in `content`. #### Tool calling Use OpenAI-compatible `tools` and `tool_choice` for agentic workflows. #### Structured output Constrain answers with `response_format` JSON schemas. #### Log probabilities Request `logprobs` and `top_logprobs`, and `n` > 1 choices. > **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-flash", messages=[ { "role": "user", "content": "Write a Python function that checks whether a string is a palindrome.", } ], max_tokens=2000, ) 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-flash", messages: [ { role: "user", content: "Write a Python function that checks whether a string is a palindrome.", }, ], max_tokens: 2000, }); 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-flash", "messages": [ { "role": "user", "content": "Write a Python function that checks whether a string is a palindrome." } ], "max_tokens": 2000 }' ``` ## Supported parameters `model: "glm5.3-flash"` 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`) | | send `top_logprobs` with `include: ["message.output_text.logprobs"]`; `logprobs: true` returns `400` | | Multiple choices (`n` > 1) | | N/A — Responses has no `n` | | Reasoning control | `reasoning_effort`: `low`, `high` (default), `max` | `reasoning.effort`: `low` or `high` (default); `"max"` returns `400` | | Turn reasoning off | always thinks | always thinks | > **Warning** > > On `POST /v2/responses`, `logprobs` is only populated when the request includes > `"include": ["message.output_text.logprobs"]`. Without it, `output[].content[].logprobs` > is always an empty array even if `top_logprobs` is set. Verified against the live API on > 2026-10-22. ## Reasoning GLM-5.3 Flash reasons by default, at `high` effort. The two APIs accept different values: | Route | Field | Accepted values | | ------------------------------------------------------------- | ------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | | [Chat Completion V2](/api-reference/chat/chat-completions-v2) | `reasoning_effort` | `"low"`, `"high"`, or `"max"`; omitting the field gives `high` | | [Responses](/api-reference/responses/create) | `reasoning.effort` | `"low"` or `"high"` only; omitting the field gives `high`. The literal string `"max"` returns `400`, so `max` effort is available on Chat Completion V2 only | Read the reasoning trace from `choices[].message.reasoning_content` on chat. On Responses, `output` starts with a `reasoning` item; read its `content[0].text` (`summary` is empty, unlike GLM-5.3). Reasoning tokens are billed as output tokens and count against `max_tokens` / `max_output_tokens`. ## Image input Send images as **base64 data URIs** in an `image_url` content part on chat, or an `input_image` part on Responses. ```python import base64 with open("chart.png", "rb") as f: data_uri = "data:image/png;base64," + base64.b64encode(f.read()).decode() response = client.chat.completions_v2( model="glm5.3-flash", messages=[ { "role": "user", "content": [ {"type": "text", "text": "Summarise this chart."}, {"type": "image_url", "image_url": {"url": data_uri}}, ], } ], max_tokens=2000, ) ``` ## How it differs from GLM-5.3 | | `glm5.3` | `glm5.3-flash` | | ---------------------------- | --------------------- | -------------- | | Image input | Not supported | Supported | | Log probabilities | Not supported (`400`) | Supported | | Multiple choices (`n` > 1) | Not supported (`400`) | Supported | | `parallel_tool_calls: false` | Not enforced | Enforced | ## Known limitations * Reasoning and the final answer share the **`max_tokens`** / **`max_output_tokens`** budget. * Set **`max_tokens`** explicitly. When it's omitted, generation isn't capped at a small default and long answers can run to tens of thousands of tokens. ## Limits and errors | Area | Limit or condition | API response | Recommended action | | -------------- | ----------------------------------------------- | ---------------------------------------------------------- | ------------------------------------------------------------------------- | | Output | `max_tokens` exceeds 1,048,576 | `400 invalid_request_error` | Set `max_tokens` within the context window. | | Request size | Request body exceeds 10 MiB (10,485,760 bytes) | `413 invalid_request_error`, with the limit in the message | Reduce the request body; base64 images count toward the limit. | | Reasoning | Reasoning consumes the full `max_tokens` budget | `200` with `finish_reason: "length"` | Raise `max_tokens` or lower the reasoning effort. | | 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` | Check the spelling; model IDs are case-sensitive. | | 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. |