GLM-5.3 (Max)Ready
glm-5-3
Serverless APILLMReasoningPrompt cachingOpen weights
A strong all-round reasoner popular for coding and agentic pipelines. It ranks #12 of the top 20 frontier models on the Artificial Analysis Intelligence Index with a score of 44.8. Released August 18, 2026.
1M
Context
753B
Parameters
#12
Intelligence rank · 44.8
Open
Weights · GLM-5.3 License
View full spec
ReleasedAug 18, 2026
Knowledge cutoff—
Size classlarge
Input modalitiestext
Output modalitiestext
Median output speed81 tok/s
Median time to first token2.7s
LicenseGLM-5.3 License
Usage guide
1. Choose how you'd like to use GLM-5.3 (Max)
☁️ Serverless
Use with pay-per-token pricing. Zero setup, no cold starts, automatic failover between upstream routes.
Usage tiers · Standard • Priority
Try it — sign in
curl https://tokenhub-staging.coality.io/v1/chat/completions \
-H "Authorization: Bearer $TOKEN_HUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5-3",
"messages": [{"role": "user", "content": "Explain vector databases in one paragraph"}]
}'Pricing
| Bucket | Price | Notes |
|---|---|---|
| Input tokens | $1.75 | per 1M tokens |
| Output tokens | $5.50 | per 1M tokens |
| Cache read | $0.3250 | cached input · 81% off |
| Cache write | — | per 1M tokens |
Billed per token with micro-dollar precision · effective Oct 26, 2026 · default key limits 600 req/min · 200K tokens/min
Benchmarks
GPQA Diamond
91.7
Humanity's Last Exam
42.3
SciCode
59.0
Terminal-Bench 4.0
41.9
Long Context Reasoning
79.7
Frontier Code
40.1
Scores from the Artificial Analysis evaluation suite (0–100 scale).
About this model
753B-parameter open-weight model, with a 1M context window, visible reasoning traces, prompt caching at a 81% discount on cached input, 81 output tokens/s median serving speed and 2.7s to first token.