MODEL PROOF
DeepSeek V4 Pro 0813
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
- 393.22K
- Input modalities
- text
- Output modalities
- text
- Published input price
- $1.30 / 1M tokens
- Published output price
- $2.60 / 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: $0.970/M at Ionstream — promotion 36% · precision not disclosed It does not pass the like-for-like test, so it never sets a rank.
Every price dimension · USD per million tokens
| Input | $1.30/M |
|---|---|
| Output | $2.60/M |
| Cached input | $0.100/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 $1.30/M from DeepInfra.
22 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
| $0.251 | $4.20 | fp4 | 99.96% |
| Sail Researchsail-research/us Endpoint terms
| $0.400 | $4.30 | fp4 | 99.67% |
| Sail Researchsail-research/fp4 Endpoint terms
| $0.400 | $4.30 | fp4 | 99.62% |
| Waferwafer Endpoint terms
| $0.400 | $5.00 | undeclared | 99.72% |
| Ionstreamionstream Endpoint terms
| $0.634 | $1.98 | undeclared | 99.26% |
| StreamLakestreamlake Endpoint terms
| $0.660 | $1.98 | undeclared | 99.46% |
| Phalaphala Endpoint terms
| $0.957 | $2.88 | undeclared | 98.46% |
| Novitanovita/fp8 Endpoint terms
| $0.990 | $2.97 | fp8 | 99.98% |
| GMICloudgmicloud/fp8 Endpoint terms
| $1.06 | $3.17 | fp8 | 99.90% |
| Alibabaalibaba Endpoint terms
| $1.12 | $3.37 | undeclared | 98.47% |
| DeepInfradeepinfra/fp8 Endpoint terms
| $1.30 | $2.60 | fp8 | 99.13% |
| CoreWeavecoreweave/fp8 Endpoint terms
| $1.31 | $3.96 | fp8 | 99.98% |
| AtlasCloudatlas-cloud/fp8 Endpoint terms
| $1.32 | $3.96 | fp8 | 99.24% |
| Nebiusnebius/fp8 Endpoint terms
| $1.32 | $3.96 | fp8 | 98.46% |
| Baidubaidu/fp8 Endpoint terms
| $1.32 | $3.96 | fp8 | 99.95% |
| Parasailparasail/fp8 Endpoint terms
| $1.32 | $3.96 | fp8 | 98.46% |
| SiliconFlowsiliconflow/fp8 Endpoint terms
| $1.32 | $3.96 | fp8 | 99.98% |
| DeepSeekdeepseek Endpoint terms
| $1.32 | $3.96 | undeclared | 99.96% |
| Togethertogether Endpoint terms
| $1.32 | $3.96 | undeclared | 97.14% |
| DigitalOceandigitalocean Endpoint terms
| $1.32 | $3.96 | undeclared | 99.53% |
| Cloudflarecloudflare Endpoint terms
| $1.32 | $3.96 | undeclared | 98.97% |
| Venicevenice Endpoint terms
| $1.65 | $4.95 | undeclared | 94.48% |
Independent scores
No independent benchmark has measured this model. Unrated is not a score of zero.
Capability
| Context window | 1M |
|---|---|
| Max output | 393K |
| Input modes | text |
| Tool use | yes |
| Reasoning | optional |
| Open weights | Unknown |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-10-06 |
| Quality data | unrated |
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
Questions this page answers
What does DeepSeek V4 Pro 0813 cost?
$1.30/M in, $2.60/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.
Does DeepSeek V4 Pro 0813 have an independent quality score?
DeepSeek V4 Pro 0813 has no independent quality score in this catalogue. Unrated is not a score of zero.
What beats DeepSeek V4 Pro 0813?
DeepSeek V4 Pro 0813 has no independent quality score. Unrated is not a score of zero.
Does this page use Artificial Analysis scores for DeepSeek V4 Pro 0813?
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 Pro 0813 scored zero?
Unrated is not a score of zero.
Is the cheapest DeepSeek V4 Pro 0813 endpoint the same product?
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $1.30/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-pro-0813/)<a href="https://undominated.ai/models/deepseek__deepseek-v4-pro-0813/"><img src="https://undominated.ai/badge/deepseek__deepseek-v4-pro-0813.svg" alt="DeepSeek V4 Pro 0813 — Undominated.ai dominance verdict" height="36"></a>Direct file: https://undominated.ai/badge/deepseek__deepseek-v4-pro-0813.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.
