DeepSeek V4 Pro 0813
Price from the model maker's own API, verified 8h ago · cached input $0.02 /M
Added automatically from the public model catalog. Family and licence details are not curated yet; benchmark scores appear as upstream leaderboards list this model.
Benchmarks
knowledge
A human-validated factuality benchmark of short factual questions whose answers can be checked against a single ground truth. Penalises hallucinations by scoring confidently-wrong answers below abstentions.
math
AIME-style competition problems written specifically for the OTIS mock contest, then run as an evaluation by Epoch AI. Closer in spirit to the public AIME but with novel problems unlikely to appear in training data.
reasoning
Second-generation ARC challenge testing fluid reasoning over abstract visual puzzles. Resists training-data memorisation by construction: each puzzle is novel and solutions require multi-step pattern induction. Frontier models are only just starting to score above chance on the harder tier.
composite
Saturation-resistant composite capability score stitched together from ~40 underlying benchmarks using Item Response Theory. Each benchmark is weighted by its fitted difficulty and discriminative slope, so doing well on hard, contamination-resistant evals (FrontierMath, ARC-AGI 2, Humanity's Last Exam) moves the score and saturated benchmarks contribute almost nothing. Imported per-model from Epoch AI's published index; we anchor it to the same min-max scale we use for every other benchmark so it's directly weightable in scenarios.
reliability
Share of nightly probe requests over the last 14 days that streamed a complete answer without an error, timeout or empty response. Needs at least five attempts before a figure is shown.
Reliability monitor
Loading drift signal…
Hosted endpoints
| Host | Input $/M | Output $/M | Context | Speed | TTFT | Uptime 24h | Quant |
|---|---|---|---|---|---|---|---|
| Host 83 | $0.13 | $0.40 | 1.0M | 43 tok/s | 1.09 s | 100.0% | fp8 |
| Host 123 | $0.45 | $0.80 | 1.0M | 100 tok/s | 0.69 s | 100.0% | fp4 |
| Host 74 | $0.45 | $0.80 | 1.0M | 93 tok/s | 0.75 s | 100.0% | fp4 |
| Host 46 | $0.66 | $1.98 | 1.0M | — | — | 100.0% | unknown |
| Host 77maker's API | $0.66 | $1.98 | 1.0M | — | — | 100.0% | unknown |
| Host 37 | $1.30 | $2.60 | 1.0M | — | — | 99.1% | fp8 |
| Host 81 | $0.37 | $2.93 | 1.0M | — | — | 100.0% | unknown |
| Host 47 | $0.99 | $2.97 | 1.0M | — | — | 100.0% | fp8 |
| Host 44 | $1.06 | $3.17 | 1.0M | — | — | 100.0% | fp8 |
| Host 90 | $1.12 | $3.37 | 1.0M | — | — | 99.5% | unknown |
| Host 138 | $1.08 | $3.80 | 1.0M | — | — | 99.1% | unknown |
| Host 115 | $1.31 | $3.96 | 1.0M | — | — | 99.9% | fp8 |
| Host 121 | $1.32 | $3.96 | 1.0M | — | — | 100.0% | unknown |
| Host 79 | $1.32 | $3.96 | 1.0M | — | — | 100.0% | fp8 |
| Host 29 | $1.32 | $3.96 | 1.0M | — | — | 98.9% | fp8 |
| Host 63 | $1.32 | $3.96 | 1.0M | — | — | 100.0% | unknown |
| Host 39 | $1.32 | $3.96 | 1.0M | — | — | 100.0% | unknown |
| Host 43 | $1.32 | $3.96 | 1.0M | — | — | 100.0% | fp8 |
| Host 71 | $1.32 | $3.96 | 1.0M | — | — | 100.0% | unknown |
| Host 86 | $1.45 | $4.36 | 1.0M | — | — | 100.0% | unknown |
| Host 134 | $1.65 | $4.95 | 1.0M | — | — | 100.0% | unknown |
| Host 75 | $0.25 | $5.00 | 1.0M | — | — | 100.0% | mxfp4 |
| Host 56 | $0.12 | $8.00 | 1.0M | — | — | 97.0% | fp4 |