GLM 5.3 Flash API — pricing & examples

Q: Where does the thinking show up?

In message.reasoning_content, and in delta.reasoning_content when streaming. It is billed as completion tokens.

Models/Chat/GLM 5.3 Flash

ChatReasoningTool callingJSON mode1M context

Context window

1M tokens

Modality

Text → Text

Input

$0.20 / 1M tokens

Cached input

$0.04 / 1M tokens

Output

$0.66 / 1M tokens

Time to first token

0.52 s

First answer word

10.31 s at default reasoning

Output speed

89.7 tok/s

Model ID

zai-org/GLM-5.3-Flash

Quickstart

You need an API key to call this model. Create a free account or log in.

Set INFERENCE_API_KEY to your key from the API Keys page, then run:

curl https://api.inferenceapis.com/v1/chat/completions \
  -H "Authorization: Bearer $INFERENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org/GLM-5.3-Flash",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello! What can you do?"}
    ]
  }'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.inferenceapis.com/v1",
    api_key=os.environ["INFERENCE_API_KEY"],
)
response = client.chat.completions.create(
    model="zai-org/GLM-5.3-Flash",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello! What can you do?"},
    ],
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferenceapis.com/v1",
  apiKey: process.env.INFERENCE_API_KEY,
});
const response = await client.chat.completions.create({
  model: "zai-org/GLM-5.3-Flash",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Hello! What can you do?" },
  ],
});
console.log(response.choices[0].message.content);

When to use it

A good fit when

You want a low price with tool calling and JSON-schema output, and a simple way to shorten its thinking (reasoning_effort low)
Long inputs: 1M-token context

Look elsewhere when

Nothing specific; compare on your own prompts.

What it costs in practice

Workload	Cost
Chat assistant — 10,000 turns of 800 tokens in, 300 out	$3.58
Long prompts or RAG — 10,000 requests of 8,000 in, 500 out	$19.30
Generation-heavy — 10,000 requests of 500 in, 2,000 out	$14.20

Computed from the live rates below. This is a reasoning model, and thinking is billed as output, so real output counts run above the visible answer; see controlling reasoning to keep that down. There is no subscription or minimum; new accounts start with free credit.

Endpoint

POST https://api.inferenceapis.com/v1/chat/completions

Headers Authorization: Bearer $INFERENCE_API_KEY
Content-Type: application/json

Compatible OpenAI wire format. /openai/v1/… is accepted too, so Groq-style base URLs work with only the host changed.

Model IDs and aliases

Send any of these as model; they all resolve to this model and bill at its rate.

ID	Note
`zai-org/GLM-5.3-Flash`	Canonical
`glm-5.3-flash`	Alias

Request body

Parameter	Type	Description
`model` required	string	Model ID: `zai-org/GLM-5.3-Flash` — also accepted: `glm-5.3-flash`
`messages` required	array	Conversation so far. Each item has a `role` (`system`, `user` or `assistant`) and `content`.
`max_tokens`	integer	Maximum number of tokens to generate (includes reasoning tokens — use a few hundred or more).
`temperature`	number	Sampling temperature. Higher values give more varied output.
`top_p`	number	Nucleus sampling cutoff.
`stream`	boolean	Stream the response as server-sent events. The final chunk includes `usage`.
`tools`	array	Tool definitions for function calling (OpenAI format).
`response_format`	object	`{"type": "json_object"}` for JSON mode.
`stop`	string \| array	Sequences where the model stops generating.
`seed`	integer	Seed for more reproducible sampling.

Response

200 OK · application/json

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "model": "zai-org/GLM-5.3-Flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hi! I can answer questions, write and edit text, help with code and more.",
        "reasoning": "The user is greeting me and asking about capabilities..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": { "prompt_tokens": 28, "completion_tokens": 17, "total_tokens": 45 }
}

Controlling reasoning

Send reasoning_effort: "none" to switch thinking off. On our test question this model used 88 completion tokens by default and 18 with thinking off, and the answer started immediately instead of after the reasoning. Model families disagree on the parameter for this, and the wrong one is silently ignored, so the gateway accepts one spelling on every model (also "minimal", reasoning: {"enabled": false} and thinking: {"type": "disabled"}) and sends the switch this model honours; the X-Thinking: off response header confirms it. On the Responses API use reasoning: {"effort": "minimal"}. Leave thinking on for multi-step coding and maths; turn it off for extraction, classification, routing and chat. All models compared.

Python · openai SDK

resp = client.chat.completions.create(
    model="zai-org/GLM-5.3-Flash",
    reasoning_effort="none",        # thinking off; omit it to let the model reason
    messages=[{"role": "user", "content": "Extract the invoice number from: ..."}],
    max_tokens=500,
)
print(resp.choices[0].message.content)

Token counts are single measurements from September 17, 2026 and vary with the question; the direction is what matters.

Tested on this endpoint

Tool calling (`tools`, `tool_calls`)	Works
JSON mode (`response_format: json_object`)	Works
Schema-constrained output (`response_format: json_schema`)	Works
Streaming with `usage` in the final chunk	Works
System prompt followed	Works
Reasoning tokens reported in `usage`	Works

Each row is a live request we sent on September 17, 2026, not a claim copied from a model card. Streamed and parallel tool calls and tool_choice were tested too: full matrix for every model. Request examples are in the API documentation.

Pricing

Input	$0.20 / 1M tokens
Cached input	$0.04 / 1M tokens
Output	$0.66 / 1M tokens
Billing	Pay as you go from prepaid credits. No subscription, no daily request or token cap. See all pricing.

Notes

Reasoning model: max_tokens covers thinking and answer together, so allow a few hundred tokens or more.
The thinking is returned in reasoning_content (GPT-OSS uses reasoning) and billed as completion tokens; usage.completion_tokens_details.reasoning_tokens reports the count.

Compare GLM 5.3 Flash with…

GPT-OSS 120B DeepSeek V4 Flash DeepSeek V4.1 Flash Llama 3.3 70B Instruct GLM 5.3 DeepSeek V4 Pro MiniMax M3 Kimi K2.7 Code GPT-OSS 20B Qwen3.8 Flash Qwen3-VL 235B GPT-OSS 120B on Groq Llama 3.3 70B on Groq GPT-4o mini GPT-4.1 mini Gemini 2.5 Flash DeepSeek V4 Flash (DeepSeek API)

Questions about GLM 5.3 Flash

Who makes GLM?

Z.ai, the company formerly known as Zhipu AI. GLM 5.3 Flash is the fast tier of its GLM 5.3 family and is published with open weights.

Where does it run?

On serverless GPUs in the United States, behind our gateway. Requests are not sent to Z.ai.

When would I pick it over DeepSeek V4 Flash?

When the wait matters. Input prices are close. In our measurement GLM 5.3 Flash generated faster (90 against 54 tokens per second) and reached its first answer word in about 10 seconds against 20 at default reasoning; with reasoning_effort set to low that wait shrinks further. Comparison.

Where does the thinking show up?

In message.reasoning_content, and in delta.reasoning_content when streaming. It is billed as completion tokens.

Errors

Errors use the OpenAI envelope: {"error": {"message", "type", "code"}}. 401 missing or invalid key · 402 insufficient_balance · 404 model_not_found · 503 model_unavailable · 502 backend error, safe to retry. Full table with what to retry: API documentation. Errors from other providers: provider error reference.