Skip to content
AI Atlas
ModelActiveOpen weightsIdentity probable

DeepSeek-V4-Pro-0813

DeepSeekfamily · DeepSeekapi-docs.deepseek.com/quick_start/pricing

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Open in Graph
data quality69

Updated 3 h ago · first seen 11 Sept 2026

model_01M293WR72MZADET5XMEQDT9QV

Overview

Identity

Canonical model
Yesidentity confidence: mediumOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
Official checkpoints
official_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
Artifacts
None recordedSeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
Provider deployments
4
API aliases
deepseek-v4-prodeepseek/deepseek-v4-pro-0813fireworks/deepseek-v4-pro-0813Identifiers under which providers and evaluators refer to this model.
Folded evaluation variants
0Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.

Openness

Open weights— weights downloadable; 7 dimensions unknown.

Weights downloadable under a permissive or Creative Commons licence allowing commercial use; code or data may be missing.

  • Weights

    Yes

  • Inference code

    —

  • Training code

    —

  • Training data

    —

  • Dataset

    —

  • Commercial use

    —

  • Redistribution

    —

  • Derivatives

    —

dimensions marked null are unknown, not false

Key facts

Release date

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Official page
api-docs.deepseek.com/quick_start/pricing

Source:DeepSeek — site & API docsT1observed 13 h agohigh

API model id

Source:DeepSeek — site & API docsT1observed 13 h agohigh

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Architecture

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Hugging Face repo

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Capabilities

Modalities

Modalities
text
Input
text
Output
text

Capabilities

  • Tool calling

    Yes

    DeepSeek — site & API docs · T1

  • Structured output

    Yes

    DeepSeek — site & API docs · T1

  • Reasoning

    Yes

    DeepSeek — site & API docs · T1

  • Vision

    No

    DeepSeek — site & API docs · T1

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

Context window

Source:DeepSeek — site & API docsT1observed 13 h agohigh

Max output

Source:DeepSeek — site & API docsT1observed 13 h agohigh

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Benchmarks8

Compare with another model →

Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric

Benchmark results grouped by comparability group
Benchmark · groupBest scoreTrustConfigurationResultsvs leaderEvaluatedSource
LiveBench Agentic Codingcoding · average score · variant=Agentic CodingOfficial boardvariantAgentic Codingrelease2026-06-251−22.3 ptvs DeepSeek-V4.1-Flash25 Jun 2026livebench.aiT2
LiveBench Codingcoding · average score · variant=CodingOfficial boardvariantCodingrelease2026-06-251−9.22 ptvs Claude Fable 5.125 Jun 2026livebench.aiT2
LiveBenchgeneral · global_averageOfficial boardrelease2026-06-251−5.98 ptvs Claude Fable 5.125 Jun 2026livebench.aiT2
LiveBench Data Analysisgeneral · average score · variant=Data AnalysisOfficial boardvariantData Analysisrelease2026-06-251−3.73 ptvs gpt-6-astra25 Jun 2026livebench.aiT2
LiveBench Languagegeneral · average score · variant=LanguageOfficial boardvariantLanguagerelease2026-06-251−8.61 ptvs Claude Fable 525 Jun 2026livebench.aiT2
LiveBench Instruction Followinginstruction-following · average score · variant=IFOfficial boardvariantIFrelease2026-06-251−13.7 ptvs Gemini 3.8 Flash25 Jun 2026livebench.aiT2
LiveBench Mathematicsmath · average score · variant=MathematicsOfficial boardvariantMathematicsrelease2026-06-251−1.92 ptvs Claude Fable 5.125 Jun 2026livebench.aiT2
LiveBench Reasoningreasoning · average score · variant=ReasoningOfficial boardvariantReasoningrelease2026-06-251−6.81 ptvs gpt-6-astra25 Jun 2026livebench.aiT2

Current rows only, grouped by benchmark → canonical metric → comparability group (task configuration). Effort variants folded into this model appear as rows of the same group. 8 current rows in total. “vs leader” compares with the current leader of the benchmark's primary group only; other groups are not directly comparable. Comparability rules →

Providers & Pricing7

All offers in the price terminal →
Provider deployments, cheapest output first
ProviderContextInput / 1MCached inOutput / 1MNative unitsStatusObservedSource
DeepSeek APIcheapest outputdeepseek/deepseek-v4-pro-08131.05Mout 393.2K$0.018—active3 h agosince 12 Sept 2026openrouter.aiT2
OpenRouterdeepseek/deepseek-v4-pro-08131.05Mout 393.2K$0.018—active22 min agosince 12 Sept 2026openrouter.aiT2
DeepSeek APIdeepseek/deepseek-v4-pro-0813:batch1.05Mout 943.7K$0.022—active3 h agosince 11 Sept 2026openrouter.aiT2
OpenRouterdeepseek/deepseek-v4-pro-0813:batch1.05Mout 943.7K$0.022—active22 min agosince 12 Sept 2026openrouter.aiT2
DeepSeek APIdeepseek-v4-pro—$0.044off_peak_input_per_mtok=0.66off_peak_output_per_mtok=1.98off_peak_cached_input_per_mtok=0.022active13 h agosince 11 Sept 2026api-docs.deepseek.comT1
Fireworks AIfireworks/deepseek-v4-pro-0813—$0.044—active6 h agosince 11 Sept 2026app.fireworks.aiT1
Together AIdeepseek-v4-pro-0813—$0.13—active11 h agosince 11 Sept 2026together.aiT1

USD per 1M tokens as published by each provider; native units (per-request fees, flex/priority tiers) are kept verbatim. Rows are append-only — every price change is kept in the history below. Cost of a workload →

Price history

Step lines per provider; amber markers are recorded changes. Click a marker or a row for the evidence behind that price.

Output price · USD / 1M tokens 4 providers

Output price history of DeepSeek-V4-Pro-0813$0$1$2$3$4$5Sept 26Sept 26Sept 26Sept 26DeepSeek API: first observed → $3.96 · 11 Sept 2026Fireworks AI: first observed → $3.96 · 11 Sept 2026DeepSeek API: $3.96 → $1.74 · 11 Sept 2026DeepSeek API: $1.74 → $1.98 · 11 Sept 2026Together AI: first observed → $3.96 · 11 Sept 2026DeepSeek API: $1.98 → $1.73 · 12 Sept 2026OpenRouter: first observed → $1.73 · 12 Sept 2026OpenRouter: $1.73 → $1.98 · 12 Sept 2026
  • DeepSeek API
  • Fireworks AI
  • Together AI
  • OpenRouter
  • OpenRouter$1.73 → $1.9812 Sept 2026
  • OpenRouterfirst observed $1.7312 Sept 2026
  • DeepSeek API$1.98 → $1.7312 Sept 2026
  • Together AIfirst observed $3.9611 Sept 2026
  • DeepSeek API$1.74 → $1.9811 Sept 2026
  • DeepSeek API$3.96 → $1.7411 Sept 2026
  • Fireworks AIfirst observed $3.9611 Sept 2026
  • DeepSeek APIfirst observed $3.9611 Sept 2026

Input price · USD / 1M tokens 4 providers

Input price history of DeepSeek-V4-Pro-0813$0$0.50$1$1.5$2Sept 26Sept 26Sept 26Sept 26DeepSeek API: first observed → $1.32 · 11 Sept 2026Fireworks AI: first observed → $1.32 · 11 Sept 2026DeepSeek API: $1.32 → $0.579 · 11 Sept 2026DeepSeek API: $0.579 → $0.66 · 11 Sept 2026Together AI: first observed → $1.32 · 11 Sept 2026DeepSeek API: $0.66 → $0.578 · 12 Sept 2026OpenRouter: first observed → $0.578 · 12 Sept 2026OpenRouter: $0.578 → $0.66 · 12 Sept 2026
  • DeepSeek API
  • Fireworks AI
  • Together AI
  • OpenRouter
  • OpenRouter$0.578 → $0.6612 Sept 2026
  • OpenRouterfirst observed $0.57812 Sept 2026
  • DeepSeek API$0.66 → $0.57812 Sept 2026
  • Together AIfirst observed $1.3211 Sept 2026
  • DeepSeek API$0.579 → $0.6611 Sept 2026
  • DeepSeek API$1.32 → $0.57911 Sept 2026
  • Fireworks AIfirst observed $1.3211 Sept 2026
  • DeepSeek APIfirst observed $1.3211 Sept 2026

Versions & Artifacts0

Version history

Context windowfirst observation only

11 Sept 2026current

Max outputfirst observation only

11 Sept 2026current

Opennessfirst observation only

12 Sept 2026current

Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.

Artifacts 0

No artifact (checkpoint, quantisation, conversion or packaging) points to this model yet.

Timeline3

Full timeline →
  • Listed by providerModelDeepSeek-V4-Pro-0813DeepSeek

    OpenRouter lists DeepSeek-V4-Pro-0813 at $0.66 in / $1.98 out per 1M tokens

    openrouter
    openrouter.ai
  • Listed by providerModelDeepSeek-V4-Pro-0813DeepSeek

    OpenRouter lists DeepSeek-V4-Pro-0813 at $0.57816 in / $1.73448 out per 1M tokens

    openrouter
    openrouter.ai
  • Price changedModelDeepSeek-V4-Pro-0813DeepSeek

    DeepSeek API changed pricing for DeepSeek-V4-Pro-0813: $0.57948 in / $1.73844 out per 1M tokens → $0.57816 in / $1.73448 out per 1M tokens

    $0.579 in / $1.74 out→$0.578 in / $1.73 outopenrouter
    openrouter.ai

Change history33

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.

Viewing AI Atlas as of 11 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

Back to today →

Attributes as of 11 Sept 2026 19 claims in force

Family
DeepSeek
Release date
12 Aug 2026
Context window
1M tokens
Max output
384K tokens
Modalities
text
Input modalities
text
Output modalities
text
Tokenizer
DeepSeek
API model id
deepseek-v4-pro
Hugging Face repo
deepseek-ai/DeepSeek-V4-Pro-0813
Livebench hf link
https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro
Openrouter id
deepseek/deepseek-v4-pro-0813
Reasoning
Yes
Structured output
Yes
Supported parameters
frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
Tool calling
Yes
Vision
No
33 claims · 22 properties11 conflicting

Familyfamily1

Claim history for Family
ValueValid from → toStatusSourceConfidenceExtractor
DeepSeek → currentcurrentDeepSeek — site & API docsT1highdeterministic

Release daterelease_date1

Claim history for Release date
ValueValid from → toStatusSourceConfidenceExtractor
12 Aug 2026 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Opennessopenness1

Claim history for Openness
ValueValid from → toStatusSourceConfidenceExtractor
open-weights → currentcurrentAI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2highderived

Context windowcontext_length8conflicting claims

Claim history for Context window
ValueValid from → toStatusSourceConfidenceExtractor
1.05M tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
1.05M tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
1.05M tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
1.05M tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
1.05M tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
1.05M tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
1.05M tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
1M tokens → currentcurrentDeepSeek — site & API docsT1conflicteddeterministic

Max outputmax_output_tokens5conflicting claims

Claim history for Max output
ValueValid from → toStatusSourceConfidenceExtractor
393.2K tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
393.2K tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
393.2K tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
393.2K tokens → currentconflictingOpenRouter public model & pricing listingT2mediumdeterministic
384K tokens → currentcurrentDeepSeek — site & API docsT1conflicteddeterministic

Modalitiesmodalities1

Claim history for Modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Input modalitiesmodalities_input1

Claim history for Input modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Output modalitiesmodalities_output1

Claim history for Output modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Tokenizertokenizer1

Claim history for Tokenizer
ValueValid from → toStatusSourceConfidenceExtractor
DeepSeek → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

API model idapi_model_id1

Claim history for API model id
ValueValid from → toStatusSourceConfidenceExtractor
deepseek-v4-pro → currentcurrentDeepSeek — site & API docsT1highdeterministic

Hugging Face repohf_repo1

Claim history for Hugging Face repo
ValueValid from → toStatusSourceConfidenceExtractor
deepseek-ai/DeepSeek-V4-Pro-0813 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Official pageofficial_url1

Claim history for Official page
ValueValid from → toStatusSourceConfidenceExtractor
https://api-docs.deepseek.com/quick_start/pricing/ → currentcurrentDeepSeek — site & API docsT1highdeterministic

Descriptiondescription1

Claim history for Description
ValueValid from → toStatusSourceConfidenceExtractor
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro. → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Openrouter idopenrouter_id1

Claim history for Openrouter id
ValueValid from → toStatusSourceConfidenceExtractor
deepseek/deepseek-v4-pro-0813 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Openrouter listed atopenrouter_listed_at1

Claim history for Openrouter listed at
ValueValid from → toStatusSourceConfidenceExtractor
12 Aug 2026 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Reasoningreasoning1

Claim history for Reasoning
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentDeepSeek — site & API docsT1highdeterministic

Structured outputstructured_output1

Claim history for Structured output
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentDeepSeek — site & API docsT1highdeterministic

Supported parameterssupported_parameters1

Claim history for Supported parameters
ValueValid from → toStatusSourceConfidenceExtractor
frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Tool callingtool_calling1

Claim history for Tool calling
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentDeepSeek — site & API docsT1highdeterministic

Visionvision1

Claim history for Vision
ValueValid from → toStatusSourceConfidenceExtractor
No → currentcurrentDeepSeek — site & API docsT1highdeterministic

Weights availableweights_available1

Claim history for Weights available
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentAI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2highderived

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

Provenance

Attributed facts

22

Source tiers

T1T29 / 13

Freshest observation

3 h ago

Conflicts

11 flagged

Source documents 5

Source documents
SourceDocumentTypeTierLast observedSnapshots
DeepSeek — site & API docsapi-docs.deepseek.com/quick_start/pricing pricingT1· Official1 h ago1
Together AI — pricingtogether.ai/pricing pricingT1· Official1 h ago1
Fireworks AI — pricingdocs.fireworks.ai/serverless/pricing.md pricingT1· Official2 h ago2
OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary22 min ago10
LiveBenchlivebench.ai/table_2026_06_25.csv leaderboardT2· Quality secondary11 h ago1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

Data quality (69/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →