Skip to contentATP Token

GLM-5

Z.aiAll Z.ai models

Input

$1.00

USD / 1M tokens

Output

$3.20

USD / 1M tokens

Context

200K

tokens

Released

2026-02-12

Positioning: Balanced. Price level 2 of 4 among text models.

GLM-5 is Z.ai's foundation model for agentic engineering, a 744B-parameter mixture-of-experts with 40B active per token, released under the MIT license. Z.ai documents a 200K context, up to 128K output, switchable thinking modes, function calling, context caching, and structured JSON output. On ATP it is the entry tier of the GLM-5 family, below GLM-5.1 and GLM-5.2.

ThinkingToolsVision
Get started freeAll model pricesCompare

Z.ai's GLM-5 overview lists a 200K context length and up to 128K maximum output tokens.

Pricing

Pay for what you use: credits are deducted only when a request succeeds.
Prices in USD · $1 = 100 credits
Input
$1.00
Output
$3.20
USD / 1M tokens

Z.ai · Family · USD / 1M tokens

Text models from the same vendor on ATP. Bars fill up to the family's highest price.
All Z.ai models
ModelInputOutput
GLM-5.1glm-5-1$1.54$4.84
GLM-5.2glm-5-2$1.40$4.40
GLM-5 This pageglm-5$1.00$3.20

Cost per 1,000 typical requests

A quick estimate with fixed token counts per request. No caching, no retries. Try the estimator with your own numbers.
WorkloadUSD / 1,000
Short chat turn800 / 400$2.08
RAG answer4,000 / 500$5.60
Agent step with tools20,000 / 1,500$24.80

Where it fits

Good fit
  • Tool-invoking agents and function calling at the lowest GLM-5 family rate on ATP
  • Structured JSON extraction from contracts, reports, and tickets
  • Everyday coding and drafting, toggling thinking off when speed matters
Usually not ideal
  • Inputs beyond 200K tokens — GLM-5.2 offers a 1M context on ATP
  • Workloads that need the newest GLM generation — GLM-5.1 and GLM-5.2 supersede it

Benchmarks

Vendor-reported
  • SWE-bench Verified77.8%

    OpenHands, tailored prompt; temperature=0.7, top_p=0.95, 200K context

    Z.ai
  • Terminal-Bench 2.0 (Terminus 2)56.2%

    Terminus framework, timeout 2h, 128K context; 60.7 on Z.ai's verified Terminal-Bench 2.0

    Z.ai
  • HLE (w/ Tools)50.4%

    text-only subset; max context 202,752 tokens

    Z.ai
  • BrowseComp62.0%

    without context management (75.9 with context management)

    Z.ai

Scores as published by each vendor, not measured by ATP. Test conditions vary, so they are not directly comparable across vendors.

Same controls on every model: project keys, per-project model access, credit budgets, and a log of every request.Set up your organization

Cost estimator

Plug in your usage to see roughly what a month costs.
0200
0100
ESTIMATE
$16.40
USD / month
1,640 credits / month
  • Input$10.00
  • Output$6.40

$16.40 USD / month · 1,640 credits / month

An estimate at our USD prices (USD 1 = 100 credits). What each request actually cost shows up in your console's request log.

Quickstart

Keep your SDK. Point it at ATP and use a project key. Read the docs
quickstart.py · OpenAI SDK
from openai import OpenAI

client = OpenAI(
  base_url="https://api.atptoken.ai/v1",
  api_key="atp-•••"
)

r = client.chat.completions.create(
  model="glm-5",
  messages=[{"role":"user","content":"hi"}],
)

Compare with similar models

Same type and positioning, from other vendors, closest in price first.
Compare side by side

Related models

All Z.ai models
GLM-5.1glm-5-1$1.54 / $4.84In / out · per 1M tokensGLM-5.2glm-5-2$1.40 / $4.40In / out · per 1M tokensGPT-5.4 Progpt-5.4-pro$30.00 / $180.00In / out · per 1M tokensClaude Fable 5claude-fable-5$10.00 / $50.00In / out · per 1M tokensGPT-5.6 Solgpt-5.6-sol$5.00 / $30.00In / out · per 1M tokensGPT-5.5gpt-5.5$5.00 / $30.00In / out · per 1M tokens

FAQ

4
Can GLM-5 use tools, read images, or think before answering?
GLM-5 supports tool calling, vision input and extended thinking, but not audio.
How much context does GLM-5 take?
Z.ai lists a 200,000-token context window for GLM-5. Source: Z.ai — GLM-5 overview (developer docs). The model list your key can see shows the limit you actually get.
How is GLM-5 priced?
You pay per 1M input tokens and per 1M output tokens. You only pay when a request succeeds. $1 = 100 credits. See pricing
Is there a newer Z.ai model than GLM-5 on ATP?
Yes. GLM-5.2 (glm-5-2) came out on Jun 16, 2026, after GLM-5 (Feb 12, 2026), and is the newer Z.ai text option on ATP. Both stay available: compare family prices on this page, then turn on the id you want for your project.

Sources

The model description on this page cites these sources. Prices come from ATP.
Get started

Start with $5. Credits never expire.

Create a project key, turn this model on, and pay only for what you use.

Get started freeTalk to enterprise