MODEL PROOF
DeepSeek V4.1 Flash
FRONTIER
Nothing scores at least as high for less, or higher for the same price, under this workload.
Price under confirmation since 2026-10-12. Upstream lists another price for this model now, or other prices from its sellers. What is shown is the last we published; the new figures are published once a second day shows the same values. · Serving precision differs between offers.
- Independent LMArena score
- 1,462.5 ± 6.29 · 12,000 votes
- Context window
- 1.05M
- Maximum output
- 943.72K
- Input modalities
- text, image
- Output modalities
- text
- Published input price
- $0.053 / 1M tokens
- Published output price
- $0.570 / 1M tokens
- Pricing kind
- fixed
Inspect complete billing conditions and endpoint terms below.
Price from Morph: the cheapest offer that is serving, at standard delivery, with at least 90% of the reference context and at a declared precision that is not 4-bit (fp8), at its standard rate. The maker’s own precision is not known.
Price under confirmation since 2026-10-12 Upstream lists another price for this model now, or other prices from its sellers. What is shown is the last we published; the new figures are published once a second day shows the same values.
Cheaper right now: $0.113/M at Decart — 4-bit It does not pass the like-for-like test, so it never sets a rank.
Every price dimension · USD per million tokens
| Input | $0.053/M |
|---|---|
| Output | $0.570/M |
| Cached input | $0.010/M |
| Cache write | Unknown/M |
| Cache write 1h | Unknown/M |
| Reasoning | Unknown/M |
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 $0.053/M from Morph.
31 provider offers · rates, limits and conditions
Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test.
| Seller | Input | Output | Precision | Uptime (1d) |
|---|---|---|---|---|
| Relacerelace Endpoint terms
| $0.027 | $1.20 | undeclared | 99.98% |
| OpenInferenceopen-inference/fp4 Endpoint terms
| $0.037 | $1.32 | fp4 | 97.24% |
| Morphmorph/fp8 Endpoint terms
| $0.053 | $0.570 | fp8 | 95.04% |
| Waferwafer Endpoint terms
| $0.060 | $1.20 | undeclared | 99.78% |
| InferenceNetinference-net Endpoint terms
| $0.070 | $0.300 | undeclared | 99.74% |
| Sail Researchsail-research/fp4 Endpoint terms
| $0.080 | $0.400 | fp4 | 99.70% |
| Decartdecart/fp4 Endpoint terms
| $0.090 | $0.180 | fp4 | 98.96% |
| DekaLLMdekallm Endpoint terms
| $0.120 | $2.40 | undeclared | 99.77% |
| Rekareka Endpoint terms
| $0.135 | $1.08 | undeclared | 99.10% |
| Ionstreamionstream Endpoint terms
| $0.139 | $1.18 | undeclared | 99.87% |
| DeepInfradeepinfra/fp8 Endpoint terms
| $0.140 | $0.420 | fp8 | 99.94% |
| StreamLakestreamlake/fp8 Endpoint terms
| $0.141 | $0.564 | fp8 | 99.88% |
| AtlasCloudatlas-cloud/fp8 Endpoint terms
| $0.141 | $0.564 | fp8 | 99.62% |
| GMICloudgmicloud/fp8 Endpoint terms
| $0.180 | $0.720 | fp8 | 99.67% |
| DigitalOceandigitalocean Endpoint terms
| $0.180 | $0.720 | undeclared | 98.28% |
| Novitanovita/fp8 Endpoint terms
| $0.195 | $0.780 | fp8 | 99.55% |
| CoreWeavecoreweave/fp8 Endpoint terms
| $0.200 | $0.650 | fp8 | 99.10% |
| Phalaphala Endpoint terms
| $0.210 | $0.840 | undeclared | 99.53% |
| Makoramakora/fp8 Endpoint terms
| $0.270 | $1.15 | fp8 | 99.87% |
| Baidubaidu/fp8 Endpoint terms
| $0.300 | $1.20 | fp8 | 99.71% |
| BaseTenbaseten/fp8 Endpoint terms
| $0.300 | $1.20 | fp8 | 99.59% |
| SiliconFlowsiliconflow/fp8 Endpoint terms
| $0.300 | $1.20 | fp8 | 99.72% |
| BaseTenbaseten/fp8 Endpoint terms
| $0.300 | $1.20 | fp8 | 99.84% |
| Parasailparasail/fp8 Endpoint terms
| $0.300 | $1.20 | fp8 | 99.65% |
| Venicevenice/fp8 Endpoint terms
| $0.300 | $1.20 | fp8 | 99.79% |
| Alibabaalibaba Endpoint terms
| $0.300 | $1.20 | undeclared | 99.42% |
| DeepSeekdeepseek Endpoint terms
| $0.300 | $1.20 | undeclared | 99.99% |
| Togethertogether Endpoint terms
| $0.300 | $1.20 | undeclared | 99.94% |
| Modalmodal Endpoint terms
| $0.300 | $1.20 | undeclared | 99.82% |
| Fireworksfireworks Endpoint terms
| $0.300 | $1.20 | undeclared | 70.58% |
| Fireworksfireworks/us Endpoint terms
| $0.450 | $1.80 | undeclared | 88.87% |
Independent scores
| LMArena Elo | 1462.5max |
|---|---|
| LMArena row | deepseek-v4.1-flash-max |
LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero.
Capability
| Context window | 1M |
|---|---|
| Max output | 943K |
| Input modes | text, image |
| Tool use | yes |
| Reasoning | optional |
| Open weights | Unknown |
Provenance
| Price source | Published record of 2026-10-06, under confirmation since 2026-10-12 |
|---|---|
| Fetched | 2026-10-21 |
| Held | Price and provider offers kept at the published record of 2026-10-06 until a second day confirms the newer upstream value, or after 3 days until one day’s two readings agree. |
| Quality data | verified |
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?
$0.053/M in, $0.570/M out: the published record of 2026-10-06, under confirmation since 2026-10-12. That is the API row, not a subscription.
Does DeepSeek V4.1 Flash have an independent quality score?
DeepSeek V4.1 Flash has an LMArena score in this catalogue.
What beats DeepSeek V4.1 Flash?
Nothing scores at least as high as DeepSeek V4.1 Flash for less, or higher for the same price.
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.
Is the cheapest DeepSeek V4.1 Flash endpoint the same product?
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.053/M from Morph.
MODEL MONUMENT
Save or share this proof
Badge
The verdict as one SVG, for a README or a docs page. It states this model's dominance status at the balanced workload on the LMArena lens, with the date it was computed, and it is rebuilt with the catalogue — so it changes when the verdict changes, including to one you would rather it did not.
[](https://undominated.ai/models/deepseek__deepseek-v4.1-flash/)<a href="https://undominated.ai/models/deepseek__deepseek-v4.1-flash/"><img src="https://undominated.ai/badge/deepseek__deepseek-v4.1-flash.svg" alt="DeepSeek V4.1 Flash — Undominated.ai dominance verdict" height="36"></a>Direct file: https://undominated.ai/badge/deepseek__deepseek-v4.1-flash.svg — a static SVG, written by scripts/build-badges.mjs on every build, so the copy you embed is never
older than the last deploy.
