DeepSeek V4.1 Flash
Intelligence
39.55
#61 of 520 models
Output speed
208.3 tok/s
Measured generation rate
Cost / index task
$0.265
Measured evaluation workload
End-to-end latency
13ms
First answer 11ms
01 / Position
A model in the landscape
Compare this model with peers across intelligence, speed, cost, and individual evaluations.
02 / Evidence
Benchmark results
18 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
- $0.300
- Output / 1M
- $1.20
- Cache read / 1M
- $0.006
- Cache write / 1M
- —
- Cache-hit discount
- 98%
Response & usage
- Output speed
- 208.3 tok/s
- First chunk
- 1ms
- First answer
- 11ms
- Output / task
- 88.6k
- Reasoning / task
- 62.7k
Evaluation workload
- Canonical input
- 9.26B
- Canonical output
- 253.11M
- Answer / task
- 25.9k
- Index time / task
- 5.2m
- Run cost
- $476.89
By prompt type
| Prompt | Output speed | First chunk | First answer | End to end |
|---|---|---|---|---|
| Medium | 225.9 tok/s | 1ms | 10ms | 12ms |
| Long | 208.3 tok/s | 1ms | 11ms | 13ms |
| Hundred K | 246.3 tok/s | 2ms | 11ms | 13ms |
| Medium Parallel | 211.9 tok/s | 1ms | 10ms | 13ms |
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
- deepseek/deepseek-v4.1-flash
- Tokenizer
- DeepSeek
- Instruct type
- —
- Captured endpoints
- 22
| Provider | Quantization | Context | tok/s |
|---|---|---|---|
| Relace | fp4 | 1.05M | — |
| Morph | unknown | 1.05M | — |
| DeepInfra | fp8 | 1.05M | — |
| Alibaba | unknown | 1M | — |
| DeepSeek | unknown | 1.05M | — |
| Sail Research | fp4 | 1.05M | — |
| Wafer | unknown | 1.05M | — |
| Fireworks | unknown | 1.05M | — |
| StreamLake | fp8 | 1.02M | — |
| GMICloud | fp8 | 1.05M | — |
| Novita | fp8 | 1.05M | — |
| AtlasCloud | fp8 | 1.05M | — |
| BaseTen | fp8 | 1.05M | — |
| Makora | unknown | 1.05M | — |
| DigitalOcean | unknown | 1.05M | — |
| Together | unknown | 1.05M | — |
| SiliconFlow | fp8 | 1.05M | — |
| Modal | unknown | 1.05M | — |
| BaseTen | fp8 | 1.05M | — |
| Parasail | fp8 | 1.05M | — |
| Phala | unknown | 1.05M | — |
| Venice | fp8 | 1M | — |
05 / Audit
Underlying fields
Inspect the captured model and routing records. Artificial Analysis destination links are omitted.