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 involving long execution chains, with improved complex instruction decomposition, tool use, scheduled and persistent execution, and overall stability across extended tasks.
Modalities
In / Out Price
$1.20 / $4per 1M
Context
203K
Released
Mar 15, 2026
This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.
| Source | Benchmark | Score |
|---|---|---|
| Artificial Analysis | GLM-5-Turbo GPQA Diamond | 84.7% |
| Artificial Analysis | GLM-5-Turbo HLE | 27.8% |
| Artificial Analysis | GLM-5-Turbo IFBench | 73.2% |
| Artificial Analysis | GLM-5-Turbo τ²-Bench Telecom | 98.5% |
| Artificial Analysis | GLM-5-Turbo AA-LCR | 71.7% |
| Artificial Analysis | GLM-5-Turbo CritPt | 0.3% |
| Artificial Analysis | GLM-5-Turbo Terminal-Bench Hard | 33.3% |
| Artificial Analysis | GLM-5-Turbo AA-Omniscience Accuracy | 28.4% |
| Artificial Analysis | GLM-5-Turbo AA-Omniscience Non-Hallucination Rate | 37.4% |
| Design Arena | GLM 5 Turbo Models Arena 3D Elo | 1278 |
| Design Arena | GLM 5 Turbo Models Arena Asciiart Elo | 1172 |
| Design Arena | GLM 5 Turbo Models Arena Code Categories Elo | 1278 |
| Design Arena | GLM 5 Turbo Models Arena Data Visualization Elo | 1278 |
| Design Arena | GLM 5 Turbo Models Arena Game Development Elo | 1274 |
| Design Arena | GLM 5 Turbo Models Arena SVG Elo | 1229 |
| Design Arena | GLM 5 Turbo Models Arena UI Component Elo | 1279 |
| Design Arena | GLM 5 Turbo Models Arena Website Elo | 1276 |
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
Token volume and request traffic to this model over time.
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
| $1.20 | $4.00 | $0.24 | 6.53s | 12 tps | -- |
Throughput
12tok/s
P50, best across providers
Latency
6.53s
P50, best provider
100.00%
99.88%
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.
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 involving long execution chains, with improved complex instruction decomposition, tool use, scheduled and persistent execution, and overall stability across extended tasks.
GLM 5 Turbo costs $1.20/M input tokens and $4.00/M output tokens, with separate rates for Cache Read at $0.24/M tokens.
GLM 5 Turbo has a 202,752 token context window. It supports up to 131,072 completion tokens.
Yes. GLM 5 Turbo accepts tools and tool_choice for function calling. It supports response_format for JSON output, without JSON-schema enforcement.
GLM 5.3 FlashX, GLM 5.3 Flash, GLM 5.3 and 11 more are other text models from Z.ai.
GLM 5 Turbo was released on March 15, 2026.