Z.ai · Released Aug 11, 2025
GLM 4.5V
GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video…
- Released
- Aug 11 2025
- Context window
- 66K 16K out
- Input / 1M tokens
- $0.60 from $0.27
- Output / 1M tokens
- $1.80 from $0.86
Where to run it
16 providers compared
Cheapest: 302.AI at $0.29 / $0.86 per 1M input / output tokens — 65% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| 302.AI | $0.29 | $0.86 | — | 64K | 16K | — | Cheapest |
| Zhipu AI | $0.30 | $0.90 | $0.06 | 64K | 16K | — | +4% |
| AIHubMix | $0.27 | $1.10 | — | 64K | 16K | — | +11% |
| NovitaFP8 | $0.60 | $1.80 | $0.11 | 66K | 16K | 100%24h | +108% |
| Z.AIFP8 | $0.60 | $1.80 | $0.11 | 66K | 16K | 100%24h | +108% |
| NanoGPTno tool calling | $0.60 | $1.80 | $0.30 | 66K | 16K | — | +108% |
| Kilo Gateway | $0.60 | $1.80 | $0.11 | 66K | 16K | — | +108% |
| Vercel AI Gateway | $0.60 | $1.80 | $0.11 | 66K | 16K | — | +108% |
| LLM Gateway | $0.60 | $1.80 | $0.11 | 66K | 16K | — | +108% |
| Novita AI | $0.60 | $1.80 | $0.11 | 66K | 16K | — | +108% |
| Jiekou.AI | $0.60 | $1.80 | — | 66K | 16K | — | +108% |
| Tempr Gateway | $0.60 | $1.80 | $0.11 | 64K | 16K | — | +108% |
| DevPass (LLM Gateway) | $0.60 | $1.80 | $0.11 | 128K | 16K | — | +108% |
| Hugging Face | $0.60 | $1.80 | — | 66K | 16K | — | +108% |
| Merge Gateway | $0.60 | $1.80 | $0.11 | 128K | 32K | — | +108% |
| AI/ML API | $0.82 | $2.48 | $0.15 | 66K | 16K | — | +186% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated GLM 4.5V. Scores appear here automatically once it does.
Specs
Details
- Model ID
z-ai/glm-4.5v- Developer
- Z.ai
- Release date
- Aug 11, 2025 ·
- Context window
- 65,536 tokens
- Max output
- 16,384 tokens
- API price
- $0.60 / $1.80 per 1M input / output tokens
- Providers
- 16
- Input types
- text, image
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.