Cheaper Inference
Model record / Z.ai
glm-5
Access glm-5 from Z.ai through one OpenAI-compatible API with live market-linked pricing and usage-based billing.
Text generationText inputReasoningStreaming45% below list
What you pay
Current catalog rates.
Input / 1M tokens$1.00 list$0.55
Output / 1M tokens$3.20 list$1.76
Cached input / 1M tokens$0.11
Current discount45%
Observed reliability
98.35
Successful provider-reaching requests
Output speed
105
Median tokens per second over sustained generations
TTFT
9.2 s
p50 · p90 18.4 s · n 1,287
Latency
11.9 s
p50 · p90 29.1 s · n 1,370
Evidence strength
—
At a glance
- Provider
- Z.ai
- Model ID
- glm-5
- Type
- Text generation
- Endpoints
- /v1/chat/completions, /v1/responses, /v1/messages
- Input
- text
- Output
- text
- Vision input
- Not supported
- Image editing
- Not supported
- Video input
- Not supported
- Reasoning
- Supported
- Streaming
- Supported
- Context window
- 198,000 tokens
Parameters by endpoint
The request field of each parameter on each endpoint, and the values it takes.
POST /v1/chat/completions
| Field | Values |
|---|---|
| reasoning.exclude | |
| max_tokens | |
| reasoning | effort: none, low, medium, high; enabled: true or false |
| response_format | |
| stop | |
| temperature | |
| tool_choice | |
| tools |
POST /v1/messages
| Field | Values |
|---|---|
| max_tokens | |
| thinking |
Pricing history
See how much this model saves and when its recorded price has been lowest.
Time zone
glm-5
Growing confidenceThis model averaged 45.0% below comparable direct provider prices across the selected range. Its strongest observed window was 8:00 PM–6:00 PM in UTC.
Last 24 hours
Average saved
45.0%
Last 24 hours
Cheapest time
8:00 PM–6:00 PM
45.0% average savings
Hourly coverage
23/24
23 total observations
Signal quality
Growing
Ready for planning
Typical unit savings$0.45 / 1M input tokens$1.44 / 1M output tokens
When this model is cheapest
Each bar is the average discount for that hour in UTC (UTC). Missing bars mean no observation was recorded.
ObservedCheapestNo data
Hover a bar for savings per token and observation counts.
Source buckets are UTC; labels are converted to UTC.
Last 24 hours
#83
of 408 ranked models
Last 7 days
#62
of 418 ranked models
Last 30 days
#57
of 418 ranked models
Ready when you are
Stop paying list price for tokens.
Marketplace pricing, capped at list, optimized further.