GLM-5.3-Flash
GLM 5.3 Flash
Intelligence
41.91
#49 of 520 models
Output speed
94.6 tok/s
Measured generation rate
Cost / index task
$0.253
Measured evaluation workload
End-to-end latency
29ms
First answer 24ms
01 / Position
A model in the landscape
Compare this model with peers across intelligence, speed, cost, and individual evaluations.
02 / Evidence
Benchmark results
23 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
- $0.150
- Output / 1M
- $0.500
- Cache read / 1M
- $0.026
- Cache write / 1M
- —
- Cache-hit discount
- 82.7%
Response & usage
- Output speed
- 94.6 tok/s
- First chunk
- 2ms
- First answer
- 24ms
- Output / task
- 68.7k
- Reasoning / task
- 46.6k
Evaluation workload
- Canonical input
- 6.48B
- Canonical output
- 180.68M
- Answer / task
- 22k
- Index time / task
- 9.4m
- Run cost
- $280.282
By prompt type
| Prompt | Output speed | First chunk | First answer | End to end |
|---|---|---|---|---|
| Medium | 97 tok/s | 2ms | 23ms | 28ms |
| Long | 94.6 tok/s | 2ms | 24ms | 29ms |
| Hundred K | 104.7 tok/s | 8ms | 27ms | 31ms |
| Medium Parallel | 89.4 tok/s | 2ms | 25ms | 30ms |
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-5.3-flash
- Tokenizer
- Other
- Instruct type
- —
- Captured endpoints
- 29
| Provider | Quantization | Context | tok/s |
|---|---|---|---|
| DeepInfra | fp4 | 1.05M | — |
| InferenceNet | fp4 | 1.05M | — |
| Relace | unknown | 1.05M | — |
| Wafer | unknown | 1.05M | — |
| GMICloud | fp8 | 1.05M | — |
| Novita | fp8 | 1.05M | — |
| StreamLake | fp8 | 1.02M | — |
| Sail Research | fp8 | 1.05M | — |
| Sail Research | fp8 | 1.05M | — |
| BaseTen | fp8 | 1.05M | — |
| Near AI | fp8 | 1.05M | — |
| Crusoe | fp4 | 1.05M | — |
| CoreWeave | nvfp4 | 1.05M | — |
| AtlasCloud | fp8 | 1.05M | — |
| Fireworks | unknown | 1.05M | — |
| Phala | fp8 | 1.05M | — |
| Friendli | unknown | 1.05M | — |
| SiliconFlow | fp8 | 1.05M | — |
| DigitalOcean | unknown | 1.05M | — |
| Together | unknown | 1.05M | — |
| Reka | fp8 | 262.1k | — |
| Parasail | fp8 | 1.05M | — |
| BaseTen | fp8 | 1.05M | — |
| Venice | unknown | 1.05M | — |
| Io Net | fp8 | 262.1k | — |
| Cloudflare | unknown | 1.31M | — |
| Z.AI | fp8 | 1.05M | — |
| NextBit | fp8 | 1.05M | — |
| Modal | fp8 | 1.05M | — |
05 / Audit
Underlying fields
Inspect the captured model and routing records. Artificial Analysis destination links are omitted.