MODEL PROOF
DeepSeek V4.1 Flash
NOT INDEPENDENTLY RATED
No independent LMArena score is published for this model.
- Independent LMArena score
- Not independently rated
- Context window
- 1.05M
- Maximum output
- 384K
- Input modalities
- text, image
- Output modalities
- text
- Published input price
- $0.150 / 1M tokens
- Published output price
- $0.600 / 1M tokens
- Pricing kind
- fixed
MODEL MONUMENT
Save or share this proof
DeepSeek: DeepSeek V4.1 Flash. Balanced workload. Not independently rated. Evidence as of 19 Sept 2026.
$0.150/M in, $0.600/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription. DeepSeek V4.1 Flash has no independent quality score. Unrated is not a score of zero.
Every price dimension
| Input | $0.150/M |
|---|---|
| Output | $0.600/M |
| Cached input | $0.0030/M |
Price varies by time of day.
Who sells it
The same weights, different shops. Cheapest is not like-for-like when serving precision differs.
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.140/M from DeepInfra.
| Seller | Input | Output | Precision | Uptime (1d) |
|---|---|---|---|---|
| Relace | $0.130 | $0.520 | fp4 | 99.78% |
| Morph | $0.135 | $0.540 | undeclared | 99.69% |
| DeepInfra | $0.140 | $0.420 | fp8 | 99.81% |
| Alibaba | $0.150 | $0.600 | undeclared | 99.96% |
| DeepSeek | $0.150 | $0.600 | undeclared | 99.99% |
| Sail Research | $0.200 | $0.600 | fp4 | 99.90% |
| Wafer | $0.200 | $0.600 | undeclared | 99.75% |
| Fireworks | $0.220 | $0.660 | undeclared | 99.71% |
| StreamLake | $0.282 | $1.13 | fp8 | 99.55% |
| GMICloud | $0.285 | $1.14 | fp8 | 99.86% |
| Novita | $0.285 | $1.14 | fp8 | 99.87% |
| AtlasCloud | $0.300 | $1.20 | fp8 | 99.85% |
| BaseTen | $0.300 | $1.20 | fp8 | 99.98% |
| SiliconFlow | $0.300 | $1.20 | fp8 | 96.91% |
| Parasail | $0.300 | $1.20 | fp8 | 96.04% |
| Makora | $0.300 | $1.20 | undeclared | 97.90% |
| DigitalOcean | $0.300 | $1.20 | undeclared | 99.11% |
| Together | $0.300 | $1.20 | undeclared | 99.95% |
| Modal | $0.300 | $1.20 | undeclared | 99.92% |
| Phala | $0.345 | $1.38 | undeclared | 99.74% |
| Venice | $0.375 | $1.50 | fp8 | 99.85% |
Independent scores
No independent benchmark has measured this model. Unrated is not a score of zero.
Capability
| Context window | 1.0M |
|---|---|
| Max output | 384K |
| Input modes | text, image |
| Tool use | yes |
| Reasoning | optional |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-09-19 |
| Quality data | unrated |
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
Questions this page answers
What does DeepSeek V4.1 Flash cost?
$0.150/M in, $0.600/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.
Does DeepSeek V4.1 Flash have an independent quality score?
DeepSeek V4.1 Flash has no independent quality score in this catalogue. Unrated is not a score of zero.
What beats DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash has no independent quality score. Unrated is not a score of zero.
Does this page use Artificial Analysis scores for DeepSeek V4.1 Flash?
No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated.