GLM-4.5V: Benchmarks, Pricing & Context Window
GLM-4.5V is a language model from ZAI, released in August 2025, with multimodal input.
GLM-4.5V is a multimodal (vision-language) model based on GLM-4.5-Air (106B total, 12B active) that extends hybrid reasoning to images and video. It achieves state-of-the-art results across 40+ VLM benchmarks (image reasoning, video
GLM-4.5V pricing
Providers
GLM-4.5V 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 | — | — | / |
 Novita | $0.600 | — | $2.20 | 131.1K/65.5K | — | — | / |
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-4.5V model size
GLM-4.5V has 108 billion parameters. See how it compares to other models in the same parameter range.
GLM-4.5V context window
Input and output token limits for GLM-4.5V, plus how it ranks on long-context understanding.
Try now
huggleMake it with
GLM-4.5V.
GLM-4.5V latency
GLM-4.5V time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
GLM-4.5V examples
Recent arena outputs from GLM-4.5V, picked from the highest-ranked matchups.
GLM-4.5V license
GLM-4.5V is released under the MIT license, which permits commercial use, has 108.0B parameters.
- License
- MIT
- Commercial use allowed
- Parameters
- 108.0B
MIT License - allows commercial use
GLM-4.5V resources
Official sources for GLM-4.5V: official playground, paper or system card, source repository, model weights.
FAQ
Common questions about GLM-4.5V.