Z.ai · Released Mar 15, 2026
GLM 5 Turbo
GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...
- Released
- Mar 15 2026
- Context window
- 203K 131K out
- Input / 1M tokens
- $1.20 from $0.72
- Output / 1M tokens
- $4.00 from $3.19
Where to run it
18 providers compared
Included in Z.AI Coding Plan. Cheapest: 302.AI at $0.72 / $3.20 per 1M input / output tokens — 46% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Z.AI Coding Plansubscription plan | Plan | Plan | Plan | 200K | 131K | — | Plan |
| 302.AI | $0.72 | $3.20 | — | 200K | 131K | — | Cheapest |
| ZenMux | $0.73 | $3.19 | $0.17 | 200K | 128K | — | +0% |
| CrossModel | $0.90 | $3.70 | $0.18 | 200K | 128K | — | +19% |
| Z.AI | $1.20 | $4.00 | $0.24 | 203K | 131K | 100%24h | +42% |
| NanoGPT | $1.20 | $4.00 | $0.24 | 203K | 131K | — | +42% |
| Venice AI | $1.20 | $4.00 | $0.24 | 200K | 33K | — | +42% |
| Kilo Gateway | $1.20 | $4.00 | $0.24 | 203K | 131K | — | +42% |
| Vercel AI Gateway | $1.20 | $4.00 | $0.24 | 203K | 131K | — | +42% |
| LLM Gateway | $1.20 | $4.00 | $0.24 | 200K | 128K | — | +42% |
| Tempr Gateway | $1.20 | $4.00 | $0.24 | 200K | 131K | — | +42% |
| DevPass (LLM Gateway) | $1.20 | $4.00 | $0.24 | 200K | 131K | — | +42% |
| Merge Gateway | $1.20 | $4.00 | $0.24 | 200K | 131K | — | +42% |
| Ofox | $1.20 | $4.00 | $0.24 | 200K | 131K | — | +42% |
| Impossibl | $1.20 | $4.00 | $0.24 | 200K | 131K | — | +42% |
| TensorX | $1.20 | $4.00 | $0.30 | 203K | 131K | — | +42% |
| Eden AI | $1.20 | $4.00 | $0.24 | 203K | 131K | — | +42% |
| AI/ML API | $1.56 | $5.20 | $0.31 | 262K | 131K | — | +84% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated GLM 5 Turbo. Scores appear here automatically once it does.
Specs
Details
- Model ID
z-ai/glm-5-turbo- Developer
- Z.ai
- Release date
- Mar 15, 2026 ·
- Context window
- 202,752 tokens
- Max output
- 131,072 tokens
- API price
- $1.20 / $4.00 per 1M input / output tokens
- Providers
- 18
- Input types
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- No
- 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.