MODEL PROOF
DeepSeek V4 Flash 0731
NOT INDEPENDENTLY RATED
No independent LMArena score is published for this model.
Serving precision differs between offers.
- Independent LMArena score
- Not independently rated
- Context window
- 1.05M
- Maximum output
- 943.72K
- Input modalities
- text
- Output modalities
- text
- Published input price
- $0.060 / 1M tokens
- Published output price
- $0.180 / 1M tokens
- Pricing kind
- fixed
Inspect complete billing conditions and endpoint terms below.
Price from DeepInfra: the cheapest offer that is serving, at standard delivery and at a declared precision that is not 4-bit (fp8), at its standard rate. The maker’s own precision is not known.
Cheaper right now: $0.066/M at StreamLake — promotion 90% It does not pass the like-for-like test, so it never sets a rank.
Every price dimension · USD per million tokens
| Input | $0.060/M |
|---|---|
| Output | $0.180/M |
| Cached input | $0.015/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 $0.060/M from DeepInfra.
26 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/fp4 Endpoint terms
| $0.010 | $1.28 | fp4 | 99.93% |
| OpenInferenceopen-inference/fp4 Endpoint terms
| $0.011 | $1.41 | fp4 | 96.84% |
| Sail Researchsail-research/fp4 Endpoint terms
| $0.019 | $0.300 | fp4 | 96.24% |
| Sail Researchsail-research/us Endpoint terms
| $0.019 | $0.420 | fp4 | 94.46% |
| Rekareka Endpoint terms
| $0.021 | $0.528 | undeclared | 99.84% |
| StreamLakestreamlake/fp8 Endpoint terms
| $0.044 | $0.132 | fp8 | 99.77% |
| Inceptroninceptron/fp4 Endpoint terms
| $0.050 | $0.650 | fp4 | 99.87% |
| DeepInfradeepinfra/fp8 Endpoint terms
| $0.060 | $0.180 | fp8 | 99.52% |
| DigitalOceandigitalocean Endpoint terms
| $0.119 | $0.238 | undeclared | 99.95% |
| BaseTenbaseten/fp8 Endpoint terms
| $0.130 | $0.260 | fp8 | 99.82% |
| BaseTenbaseten/fp8 Endpoint terms
| $0.130 | $0.260 | fp8 | 99.83% |
| CoreWeavecoreweave/fp8 Endpoint terms
| $0.130 | $0.280 | fp8 | 99.63% |
| Parasailparasail/fp8 Endpoint terms
| $0.140 | $0.280 | fp8 | 99.52% |
| Coherecohere Endpoint terms
| $0.140 | $0.280 | undeclared | 98.46% |
| Togethertogether Endpoint terms
| $0.140 | $0.280 | undeclared | 99.61% |
| Venicevenice Endpoint terms
| $0.175 | $0.350 | undeclared | 97.99% |
| Mancer 2mancer/fp8 Endpoint terms
| $0.200 | $0.600 | fp8 | 97.45% |
| SiliconFlowsiliconflow/fp8 Endpoint terms
| $0.220 | $0.660 | fp8 | 99.49% |
| Waferwafer/fast Endpoint terms
| $0.220 | $0.840 | undeclared | 99.94% |
| GMICloudgmicloud/fp8 Endpoint terms
| $0.286 | $0.858 | fp8 | 99.99% |
| Phalaphala Endpoint terms
| $0.308 | $0.924 | undeclared | 99.81% |
| Alibabaalibaba Endpoint terms
| $0.352 | $1.06 | undeclared | 99.08% |
| Novitanovita/fp8 Endpoint terms
| $0.409 | $1.23 | fp8 | 99.99% |
| Baidubaidu/fp8 Endpoint terms
| $0.440 | $1.32 | fp8 | 99.94% |
| AtlasCloudatlas-cloud/fp4 Endpoint terms
| $0.440 | $1.32 | fp4 | 99.86% |
| Cloudflarecloudflare Endpoint terms
| $0.440 | $1.32 | undeclared | 99.98% |
Independent scores
No independent benchmark has measured this model. Unrated is not a score of zero.
Best rankings by task
- SVG #30 1186
- 3D #39 1216
- Websites #40 1245
- UI components #41 1242
- Code categories #42 1234
- Game development #43 1221
- Data visualisation #57 1188
- ASCII art #62 1100
Per-task Elo and rank from Design Arena, via OpenRouter’s model feed. The rank is the feed’s, and it counts models OpenRouter does not list.
Capability
| Context window | 1M |
|---|---|
| Max output | 943K |
| Input modes | text |
| Tool use | yes |
| Reasoning | optional |
| Open weights | Unknown |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-10-06 |
| Quality data | unrated |
Our take
editorial — not a measurementThis dated Flash identity must be checked separately from other DeepSeek variants. Use its own accepted output ceiling, prices and proof when evaluating large text-generation jobs. Do not transfer a peak/off-peak tariff, weight release or benchmark result from another DeepSeek model.
Strengths
- Text input and tool use are listed
- The record separates the context window from the output ceiling
Weaknesses
- A family name does not establish the same pricing schedule
- Verify the exact weight release and licence before planning self-hosting
Reach for it when
- Large text-generation evaluations with explicit output limits
- Comparisons that retain the dated model identity
Avoid it if
- You need multimodal input
- The plan depends on a tariff or weight release from another variant
Sources: api-docs.deepseek.com
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
Questions this page answers
What does DeepSeek V4 Flash 0731 cost?
$0.060/M in, $0.180/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.
Does DeepSeek V4 Flash 0731 have an independent quality score?
DeepSeek V4 Flash 0731 has no independent quality score in this catalogue. Unrated is not a score of zero.
What beats DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731 has no independent quality score. Unrated is not a score of zero.
Does this page use Artificial Analysis scores for DeepSeek V4 Flash 0731?
No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated.
Does a missing score mean DeepSeek V4 Flash 0731 scored zero?
Unrated is not a score of zero.
Is the cheapest DeepSeek V4 Flash 0731 endpoint the same product?
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.060/M from DeepInfra.
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-flash-0731/)<a href="https://undominated.ai/models/deepseek__deepseek-v4-flash-0731/"><img src="https://undominated.ai/badge/deepseek__deepseek-v4-flash-0731.svg" alt="DeepSeek V4 Flash 0731 — Undominated.ai dominance verdict" height="36"></a>Direct file: https://undominated.ai/badge/deepseek__deepseek-v4-flash-0731.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.
