Qwen3.8 27B
Intelligence
26.49
#134 of 520 models
Output speed
46.5 tok/s
Measured generation rate
Cost / index task
$0.834
Measured evaluation workload
End-to-end latency
58ms
First answer 47ms
01 / Position
A model in the landscape
Compare this model with peers across intelligence, speed, cost, and individual evaluations.
02 / Evidence
Benchmark results
21 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
- $0.500
- Output / 1M
- $3.00
- Cache read / 1M
- $0.050
- Cache write / 1M
- —
- Cache-hit discount
- 90%
Response & usage
- Output speed
- 46.5 tok/s
- First chunk
- 4ms
- First answer
- 47ms
- Output / task
- 45.4k
- Reasoning / task
- 25.9k
Evaluation workload
- Canonical input
- 4.57B
- Canonical output
- 82.44M
- Answer / task
- 19.6k
- Index time / task
- 15.4m
- Run cost
- $875.916
By prompt type
| Prompt | Output speed | First chunk | First answer | End to end |
|---|---|---|---|---|
| Medium | 47.7 tok/s | 1ms | 43ms | 54ms |
| Long | 46.5 tok/s | 4ms | 47ms | 58ms |
| Hundred K | 77.5 tok/s | 18ms | 44ms | 51ms |
| Medium Parallel | 42.3 tok/s | 1ms | 49ms | 60ms |
04 / Access
License & availability
Recorded license
Apache 2.0
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
- qwen/qwen3.8-27b
- Tokenizer
- Qwen
- Instruct type
- —
- Captured endpoints
- 16
| Provider | Quantization | Context | tok/s |
|---|---|---|---|
| Darkbloom | fp4 | 262.1k | — |
| DeepInfra | bf16 | 262.1k | — |
| Phala | unknown | 262.1k | — |
| DekaLLM | unknown | 262.1k | — |
| Mancer 2 | fp8 | 262.1k | — |
| Reka | fp8 | 262.1k | — |
| Parasail | fp8 | 262.1k | — |
| Chutes | fp8 | 262.1k | — |
| AkashML | fp8 | 262.1k | — |
| Ionstream | fp8 | 262.1k | — |
| Io Net | fp8 | 65.5k | — |
| CoreWeave | fp8 | 262.1k | — |
| Novita | unknown | 1M | — |
| Alibaba | unknown | 1M | — |
| Cloudflare | unknown | 262.1k | — |
| Venice | fp8 | 262.1k | — |
05 / Audit
Underlying fields
Inspect the captured model and routing records. Artificial Analysis destination links are omitted.