GLM-4.5: API Pricing, Context Window & Benchmarks
GLM-4.5 is a language model from ZAI, released in July 2025.
GLM-4.5 is an Agentic, Reasoning, and Coding (ARC) foundation model designed for intelligent agents, featuring 355 billion total parameters with 32 billion active parameters using MoE architecture. Trained on 23T tokens through multi-stage
GLM-4.5 benchmarks
Rankings
Quality Tracker
GLM-4.5 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Fri Aug 07 2026GLM-4.5 pricing
Providers
GLM-4.5 starts at $0.400 per million input tokens and $1.60 per million output tokens via DeepInfra. See all 3 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 DeepInfra | $0.400 | — | $1.60 | 131.1K/131.1K | 0.00 | — | / |
 Fireworks | $0.550 | — | $2.19 | 131.1K/131.1K | 0.00 | — | / |
 Novita | $0.600 | — | $2.20 | 131.1K/98.3K | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
GLM-4.5 model size
GLM-4.5 has 355 billion parameters and was trained on 23 trillion tokens. See how it compares to other models in the same parameter range.
GLM-4.5 context window
Input and output token limits for GLM-4.5, plus how it ranks on long-context understanding.
GLM-4.5 API
Available from the model provider
GLM-4.5 has an official provider API. It is not currently routed through the LLM Stats gateway.
Read the official API documentationGLM-4.5 latency
GLM-4.5 time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Provider operational metrics
Time to first token, output throughput, and failed-request rate from live API traffic
GLM-4.5 examples
Recent arena outputs from GLM-4.5, picked from the highest-ranked matchups.
GLM-4.5 license
GLM-4.5 is released under the MIT license, which permits commercial use, has 355.0B parameters.
- License
- MIT
- Commercial use allowed
- Parameters
- 355.0B
MIT License - allows commercial use
GLM-4.5 resources
Official sources for GLM-4.5: api documentation, official playground, paper or system card, official launch post, source repository, model weights.
GLM-4.5 vs other models
The most-compared alternatives to GLM-4.5 are o1-pro, Gemini 2.5 Pro, Qwen3-235B-A22B-Thinking-2507. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like GLM-4.5
Models ranked just above and below GLM-4.5 by LLM Stats score.
FAQ
Common questions about GLM-4.5.