Online

GLM-5.3-Flash

Z.ai · OpenAI-compatible API

z-ai/glm-5.3-flash

Create account →Quickstart ↓

USD / 1M tokens

Input$0.099

Cached Input$0.025

Output$0.35

Context: 1M
Tool Calling: ✓
Reasoning: ✓
Vision: ✓
Streaming: ✓

OpenAI-compatible API

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.iteracompute.com/v1",
    api_key=os.environ["ITERACOMPUTE_API_KEY"],
)
response = client.chat.completions.create(
    model="z-ai/glm-5.3-flash",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.iteracompute.com/v1",
  apiKey: process.env.ITERACOMPUTE_API_KEY,
});
const response = await client.chat.completions.create({
  model: "z-ai/glm-5.3-flash",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

curl https://api.iteracompute.com/v1/chat/completions \
  -H "Authorization: Bearer $ITERACOMPUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-5.3-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

z-ai/glm-5.3-flashView Docs →

Catalog snapshot: 2026-10-09. Live prices have not been verified yet.

Overview

Text and image input, streaming, reasoning, tool calling and structured outputs; up to 131,072 output tokens.

Tasks and selection tradeoffs

Batch classification

Classify support tickets into an explicit set of labels and check a held-out sample.

Screenshot triage experiments

Evaluate screenshot descriptions against a manually labeled set before automating triage.

Task suggestions based on catalog features and price, not model quality benchmarks.

Choose your tool

OpenAI SDKCall from Python or JavaScript Vercel AI SDKBuild a TypeScript application

Choose a model and tool for your task →

Pricing

Prices in USD per 1M tokens.

Input$0.099

Cached Input$0.025

Output$0.35

Example task: Classify a batch of support tickets

Assume 12,000 aggregate input tokens and 1,000 billable output tokens across all calls. No cache hit.

12,000 × $0.099 / 1M + 1,000 × $0.35 / 1M = $0.001538

If usage actually reports 9,000 of those input tokens as cached, replace that portion at the cached-input rate ($0.025/1M): $0.000872. Cached tokens are part of total input, never added on top.

Illustrative calculation using the October 9, 2026 catalog snapshot, not a measured bill or promised task size. Live rates above may differ. Include every agent call and retry, repeated history and billable reasoning output; settle against actual usage and Console records.

Known limits and verification scope

The snapshot has lower input/output prices than GLM-5.3, and lists image input. Flash is not a measured latency promise; compare correctness and response time on the same sample.
Catalog context: 1,048,576 tokens. Input and requested output share the context budget; this is not a measured usable boundary.
The context and capability flags describe the public catalog. They do not establish a particular tool workflow or a quality score.
Start with one representative task. Check correctness, actual usage and response time before increasing traffic.
This page has no recorded end-to-end tool validation for this model. The integration examples let you run and record your own check.

Verified parameters and open questions

Parameter / protocol field	Evidence status
`model / messages`	Request example only; not live-verified for this model
`tools / tool_calls / tool messages`	Catalog lists tool calling; argument and result cycle unverified
`chat_template_kwargs.enable_thinking=false`	Qwen-specific option; do not copy to this model
`stream / temperature / top_p / max_tokens / response_format / reasoning_effort`	No verified values recorded for this exact model ID

A catalog capability flag is not a tested parameter value. Omit optional controls until checked with your exact model ID; an HTTP 200 alone does not prove the option took effect.

API

Base URL: https://api.iteracompute.com/v1
Endpoint: POST /v1/chat/completions
Model ID: z-ai/glm-5.3-flash
Authentication: Authorization: Bearer ITERACOMPUTE_API_KEY

View Docs

FAQ

How do I use GLM-5.3-Flash with the OpenAI SDK?

Set base_url to https://api.iteracompute.com/v1 and model to z-ai/glm-5.3-flash. Authenticate with your IteraCompute API key.

What does GLM-5.3-Flash cost?

See the pricing section for current input, cached-input and output rates in USD per 1M tokens. Check the refresh time before use.

What context length is available?

1,048,576 tokens.

Ready for your first request?

Create your key, choose a tool and get a non-empty first reply.

Create an account →Choose a tutorial