GLM-4.7: Benchmarks, Pricing & Context Window
GLM-4.7 is a language model from ZAI, released in December 2025, with multimodal input, a 203K-token context window, and pricing from $0.400/M input, $0.080/M cached input, $1.75/M output.
GLM 4.7 is a coding‑centric model that thinks before acting, preserves its reasoning across turns, and lets you control thinking per request for speed or accuracy. It upgrades agentic workflows with stronger multi‑step tool use, better
GLM-4.7 benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for GLM-4.7 across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How GLM-4.7 holds up as conversations get longer.
Quality Tracker
GLM-4.7 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Thu Sep 10 2026GLM-4.7 pricing
Providers
GLM-4.7 starts at $0.400 per million input tokens and $1.75 per million output tokens via DeepInfra. Reused prompt prefixes cost $0.0800 per million cached input tokens. 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 | $0.0800 | $1.75 | 202.8K/202.8K | — | — | / |
 Fireworks | $0.600 | — | $2.20 | 202.8K/131.1K | — | — | / |
 Novita | $0.600 | — | $2.20 | 204.8K/131.1K | — | — | / |
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-4.7 model size
GLM-4.7 has 358 billion parameters. See how it compares to other models in the same parameter range.
GLM-4.7 context window
Input and output token limits for GLM-4.7, plus how it ranks on long-context understanding.
Try now
huggleMake it with
GLM-4.7.
GLM-4.7 latency
GLM-4.7 time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
GLM-4.7 examples
Recent arena outputs from GLM-4.7, picked from the highest-ranked matchups.
GLM-4.7 license
GLM-4.7 is released under the MIT license, which permits commercial use, has 358.0B parameters.
- License
- MIT
- Commercial use allowed
- Parameters
- 358.0B
MIT License - allows commercial use
GLM-4.7 resources
Official sources for GLM-4.7: provider documentation, official playground, paper or system card, official launch post, model weights.
GLM-4.7 vs other models
The most-compared alternatives to GLM-4.7 are GLM-5.1, GPT-5 High, Seed 2.0 Lite. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like GLM-4.7
Models ranked just above and below GLM-4.7 by LLM Stats score.
FAQ
Common questions about GLM-4.7.