DeepSeek V4 Pro 0813: Launch Benchmarks and the Dated Price Gap
MODELS & COSTS
DeepSeek V4 Pro 0813: Launch Benchmarks and the Dated Price Gap
DeepSeek's 0813 table reports strong coding results at an unusually low launch output rate. Both parts are dated. The useful question now is which checkpoint and rate apply to the job you intend to run, rather than carrying the August price gap forward as a permanent offer.
If you missed the spring: DeepSeek previewed V4 in April as two models — V4-Pro (1.6T total parameters, 49B active, the premium tier) and V4-Flash (284B/13B, the workhorse) — both MIT-licensed, both with a 1M-token context window. Flash went official on July 31. Now Pro has followed, under the build tag 0813, with the same 1M context, 384K max output, and concurrency limits (500 for Pro vs 2500 for Flash). The one real change beyond the version tag: the official Pro now supports the Responses API, Codex-style agent integration, and the Anthropic-compatible endpoint — all Flash-only at the July 31 update. Same model ID, same endpoint, no code changes needed; the upgraded model just answers when you call deepseek-v4-pro.
DeepSeek-V4-Pro on Hugging Face (model card thumbnail; image: Hugging Face)
DeepSeek's published benchmark table
The 0813 eval table is out, and it settles the family drama that started on July 31 — when DeepSeek promoted V4-Flash to official status and its re-post-trained build (Flash-0731) beat V4-Pro-Preview on every agentic benchmark the company publishes. DeepSWE alone went from 7.3 (Flash-Preview) to 54.4 on that re-post-training — a 7x jump from a model that costs $0.14/$0.28. The obvious question: if the cheap model beats the expensive one, what is Pro for?
The official build is the answer, and this time the numbers shipped with the release.
DeepSeek's official agentic eval table for V4-Pro-0813 (image: DeepSeek; vendor-reported)
| Benchmark | V4-Pro-0813 | V4-Flash-0731 | V4-Pro-Preview | GLM-5.2 | Kimi-K3 | Opus-4.8 | Fable 5 |
|---|---|---|---|---|---|---|---|
| Terminal Bench 2.1 | 87.9 | 82.7 | 72.1 | 81.0 | 88.3 | 85.0 | 88.0 |
| NL2Repo | 61.5 | 54.2 | 38.5 | 48.9 | — | 69.7 | — |
| Cybergym | 83.3 | 76.7 | 52.7 | — | 80.0 | 78.3 | 83.1 |
| DeepSWE | 62.7 | 54.4 | 12.8 | 46.2 | 67.5 | 58.0 | 70.0 |
| Toolathlon-Verified | 74.1 | 70.3 | 55.9 | 59.9 | 76.5 | 76.2 | 77.9 |
| AutomationBench (Public) | 31.8 | 25.1 | 12.8 | 12.9 | 30.8 | 27.2 | 29.1 |
| HLE (with tools) | 60.0 | 51.5 | 48.2 | 54.7 | 56.0 | 57.9 | 63.0 |
Agentic benchmarks from the official V4-Pro-0813 release (DeepSeek-reported; Fable 5 evaluated with Anthropic's fallback harness)
The official build, measured: V4-Pro-0813 vs its preview and Flash across six agentic evals
The numbers tell a clean story. Versus its own preview, the official build is a different model: Terminal Bench 2.1 jumps 72.1 → 87.9, DeepSWE goes 12.8 → 62.7, AutomationBench 12.8 → 31.8. Versus the frontier, it sits right in the middle of the pack — it beats Claude Opus 4.8 on Terminal Bench (87.9 vs 85.0) and DeepSWE (62.7 vs 58.0), and matches Fable 5 on Cybergym (83.3 vs 83.1). The only leads against it: Kimi-K3, Fable 5, and Opus-4.8 (on NL2Repo and Toolathlon-Verified). The "open-weight model trades blows with the frontier" story is no longer just about price; the official build's scores put it in the same conversation on the board.
The launch-price comparison
Put V4 Pro next to the models people actually know and the numbers stop looking like a discount and start looking like a different category:
| Model | Input $/1M | Output $/1M | Output vs V4 Pro |
|---|---|---|---|
| DeepSeek V4 Pro | $0.435 | $0.87 | — |
| GPT-5.6 Sol | $5 | $30 | 34x |
| Claude Opus 5 | $5 | $25 | 29x |
| Fable 5 | $10 | $50 | 57x |
List prices per 1M tokens, August 2026
The official pricing page — Pro-0813 alongside Flash-0731, same rate card as the preview (image: DeepSeek)
The gap isn't 2x — it's 30-57x on output tokens (log scale, list prices Aug 2026)
Cache hits make it even more lopsided: V4 Pro's cached input runs at $0.003625/1M. At these rates, a dollar of V4 Pro output goes roughly 57x further than a dollar of Fable 5. DeepSeek has been running this playbook since R1 — open weights, MIT license, prices that look like they're from a decade ago — and the official 0813 build keeps the pricing exactly where the preview left it. the API docs now carry a notice that DeepSeek plans a significant price increase in the near future. If you've been waiting to wire V4 Pro into a pipeline, the current rate card may not last.
API release and downloadable checkpoint
One loose end: the 0813 checkpoint hasn't appeared on Hugging Face yet. The preview weights were always MIT and freely downloadable (~865GB for Pro), and DeepSeek shipped Flash-0731 weights the same day Flash went official — so there's a reasonable expectation Pro's will follow. But as of writing, the 0813 repo isn't up. Until it lands, "open weights" officially means the preview build, and the production-grade agent numbers above live on DeepSeek's API only.
The launch rate and benchmark table made 0813 a candidate for a cost-sensitive agent trial. The rows remain DeepSeek's evaluations, and the available API does not establish that the matching downloadable checkpoint has shipped. Test the endpoint separately from any later weight release.
The Fable 5 row uses the cited fallback harness, and the other comparisons also need their settings retained. A matching independent run would help establish how much of the preview-to-0813 gain persists outside the developer's setup. The table alone does not settle whether Pro is better value than Flash for a particular task.
The launch price should not be used as a current budget without checking the rate card. The subsequent pricing article records the August 16 peak and off-peak schedule. Calculate the relevant input, cache and output costs before comparing providers.
The durable questions are whether 0813 completes the intended tasks, whether its API compatibility works in the existing harness, and what those successful tasks cost under the applicable rate. An isolated output-price multiple answers only the last question's simplest component.
Related on this blog: Gemini 3.7 Flash: Half the Price, Still No 3.5 Pro · DeepSeek Added Vision to Flash. The Text Scores Went Up.
Links: Official pricing & model docs · API changelog · Hugging Face (preview weights) · Flash-0731 model card
Comments
Post a Comment