GLM-4.6: API Pricing, Context Window & Benchmarks
GLM-4.6 is a language model from ZAI, released in September 2025, with multimodal input.
GLM-4.6 is the latest version of Z.ai's flagship model, bringing significant improvements over GLM-4.5. Key features include: 200K token context window (expanded from 128K), superior coding performance with better real-world application in
GLM-4.6 benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for GLM-4.6 across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How GLM-4.6 holds up as conversations get longer.
Quality Tracker
GLM-4.6 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Fri Sep 04 2026GLM-4.6 pricing
Providers
GLM-4.6 starts at $0.550 per million input tokens and $2.19 per million output tokens via Fireworks. See all 2 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 |
|---|---|---|---|---|---|---|---|
 Fireworks | $0.550 | — | $2.19 | 131.1K/131.1K | — | — | / |
 DeepInfra | $0.600 | — | $2.00 | 131.1K/65.5K | 0.70 | — | / |
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-4.6 model size
GLM-4.6 has 357 billion parameters. See how it compares to other models in the same parameter range.
GLM-4.6 context window
Input and output token limits for GLM-4.6, plus how it ranks on long-context understanding.
GLM-4.6 API
Available from the model provider
GLM-4.6 has an official provider API. It is not currently routed through the LLM Stats gateway.
Read the official API documentationGLM-4.6 latency
GLM-4.6 time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
GLM-4.6 examples
Recent arena outputs from GLM-4.6, picked from the highest-ranked matchups.
GLM-4.6 license
GLM-4.6 is released under the MIT license, which permits commercial use, has 357.0B parameters.
- License
- MIT
- Commercial use allowed
- Parameters
- 357.0B
MIT License - allows commercial use
GLM-4.6 resources
Official sources for GLM-4.6: api documentation, official playground, paper or system card, official launch post.
GLM-4.6 vs other models
The most-compared alternatives to GLM-4.6 are Grok-3, GPT OSS 120B High, GPT-5.1. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like GLM-4.6
Models ranked just above and below GLM-4.6 by LLM Stats score.
FAQ
Common questions about GLM-4.6.