GLM-5.1
Intelligence
26.45
#135 of 520 models
Output speed
37.4 tok/s
Measured generation rate
Cost / index task
$0.922
Measured evaluation workload
End-to-end latency
117ms
First answer 103ms
01 / Position
A model in the landscape
Compare this model with peers across intelligence, speed, cost, and individual evaluations.
02 / Evidence
Benchmark results
24 distinct evaluations grouped by topic. Explore cross-model charts or switch to the full results list.
Domain capability
03 / Operation
Speed, tokens & price
Prices are per million tokens; latency and task costs describe the captured evaluation rather than a universal provider guarantee.
Token pricing
- Input / 1M
- $1.20
- Output / 1M
- $4.40
- Cache read / 1M
- $0.260
- Cache write / 1M
- —
- Cache-hit discount
- 80.8%
Response & usage
- Output speed
- 37.4 tok/s
- First chunk
- 2ms
- First answer
- 103ms
- Output / task
- 41.3k
- Reasoning / task
- 26.9k
Evaluation workload
- Canonical input
- 1.8B
- Canonical output
- 142.83M
- Answer / task
- 14.4k
- Index time / task
- 15.5m
- Run cost
- $1,418.324
By prompt type
| Prompt | Output speed | First chunk | First answer | End to end |
|---|---|---|---|---|
| Long | 37.4 tok/s | 2ms | 103ms | 117ms |
04 / Access
License & availability
Recorded license
MIT
The publisher-linked license text defines permitted use and redistribution. Review it before using the model.
- Weight access
- Open weights
- Classification
- Permissive
- Reasoning
- Yes
Routing and providers
- OpenRouter ID
- z-ai/glm-5.1
- Tokenizer
- Other
- Instruct type
- —
- Captured endpoints
- 14
| Provider | Quantization | Context | tok/s |
|---|---|---|---|
| Baidu | fp8 | 202.8k | — |
| StreamLake | fp8 | 200k | — |
| Chutes | fp8 | 202.8k | — |
| DeepInfra | fp4 | 202.8k | — |
| SiliconFlow | fp8 | 204.8k | — |
| Phala | unknown | 202.8k | — |
| AtlasCloud | fp8 | 202.8k | — |
| Alibaba | fp8 | 202.7k | — |
| Novita | fp8 | 204.8k | — |
| Nebius | fp8 | 202.8k | — |
| GMICloud | fp8 | 202.8k | — |
| Friendli | unknown | 202.8k | — |
| Z.AI | fp8 | 202.8k | — |
| Venice | fp8 | 200k | — |
05 / Audit
Underlying fields
Inspect the captured model and routing records. Artificial Analysis destination links are omitted.