GLM
Z.ai's open-weight family, behind the cheap coding subscriptions.
GLM is the model family from Z.ai, and the reason its coding plan turns up in every "cheaper than Claude Code" thread — the weights are published, plenty of providers serve them, and the Flash models are some of the cheapest usable coding models anywhere. The 5.3 line runs to a million tokens of context, with Flash variants that also read images and video. Z.ai's own chat app is listed separately under Chats.
At a glance — GLM 5.1
- Cost
- $0.965 in · $3.032 out per 1M tokensMid-range
- Memory
- 205K tokens — about 300 pages
- Reads
- Text
- Can do
- Use tools (agents)
- Structured output
- Thinking mode
- Good at
- Coding: better than 61% · Agentic work: better than 59% · Overall: better than 53%
- Reliability
- 99.99% uptime, last 24h
- Released
- Apr 7, 2026
Advanced details
- API model ID
z-ai/glm-5.1- Max output
- 131K tokens
- Max input
- 170K tokens
- Cached input
- $0.179 per 1M
- Tokenizer
- Other
- Coding index
- 55.8
- Agentic work index
- 23.9
- Overall index
- 26.1
Providers
The same model, hosted by different companies. OpenRouter picks one per request and falls back to the next if it fails.
| Provider | Input /1M | Output /1M | Cached /1M | Max output | Uptime 24h |
|---|---|---|---|---|---|
| Baidu · fp8 | $0.965 | $3.032 | $0.179 | 131K | 99.63% |
| StreamLake · fp8 | $0.966 | $3.036 | $0.179 | 128K | 99.75% |
| Chutes · fp8 | $0.98 | $3.08 | $0.098 | 66K | 93.54% |
| DeepInfra · fp4 | $1.05 | $3.50 | $0.205 | 66K | 99.95% |
| SiliconFlow · fp8 | $1.19 | $3.74 | $0.60 | 131K | 99.82% |
| Phala | $1.21 | $4.20 | $0.60 | 128K | 93.25% |
| AtlasCloud · fp8 | $1.26 | $3.96 | $0.234 | 182K | 98.74% |
| Alibaba · fp8 | $1.33 | $4.18 | $0.247 | 131K | 97.47% |
| Novita · fp8 | $1.38 | $4.40 | $0.26 | 131K | 99.08% |
| Nebius · fp8 | $1.40 | $4.40 | — | 182K | 99.79% |
| GMICloud · fp8 | $1.40 | $4.40 | $0.26 | 182K | 98.94% |
| Friendli | $1.40 | $4.40 | $0.26 | 182K | 99.99% |
| Z.AI · fp8 | $1.40 | $4.40 | $0.26 | 131K | 99.93% |
| Venice · fp8 | $1.401 | $4.404 | $0.26 | 80K | 99.97% |
Supported parameters
- frequency_penalty
- include_reasoning
- logit_bias
- logprobs
- max_tokens
- min_p
- presence_penalty
- reasoning
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_logprobs
- top_p
Live from OpenRouter, refreshed hourly. Scores from Artificial Analysis.
Key info
- Pricing
- Open source
- Category
- Models
- Best for
- Intermediate
- Made by
- Z.ai
- Weights
- Open
- Good for
- Coding on a budget