LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

DeepSeek V4 Pro 0813

deepseek·deepseek/deepseek-v4-pro-0813·BETA·Open weights·deepseek-thinking series
DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

Specs & pricing

Input / output per 1M tokens
Official price·DeepSeek
$0.66 / $1.98
Blended $0.99 · Cache read $0.022
Lowest paid·IteraComputeGateway
$0.60 / $1.79
Blended $0.90 · 7.1× spread
1 more $0 channels
Context
1,048,576
Output limit
393,216
Knowledge cutoff
—
Released / updated
2026-08-13 / 2026-08-22
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
Modalities
Text
License
MIT
Weights
Hugging Face

DeepSeek V4 Pro 0813 is offered by 67 providers on this page. Public prices are shown for 61 of them. Its official list price is $0.66 per 1M input tokens and $1.98 per 1M output tokens. Prices vary about 7.1× across the providers that host it. It also has 1 free ($0) channel and 4 covered by a paid subscription; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Artificial Analysis rates it 23.1 on the Intelligence Index, with 41.1 for Strategy & Ops, its strongest domain. Against its lowest blended price of $0.897 per 1M, that is roughly 26 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 69 tokens per second, with 1.68s to the first token. Running one task of the Artificial Analysis suite costs about $1.7691, which reflects how many tokens its reasoning consumes rather than the unit price alone.

The context window is 1,048,576 tokens at the reference host, but hosts report different limits, from 979,000 to 1,048,600, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice.

Quality & performanceArtificial Analysis · Intelligence Index v5 · rep. tier Max

Intelligence23.1
Value26
Engineering29.8
Finance & Accounting30.4
Legal27.5
Strategy & Ops41.1
Economics29.3
Output speed69 tok/s
TTFT1.68 s
Cost per task$1.77
Value formulaIQ 23.1 ÷ min blended $0.897 = 26
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 12.6 · 70 tok/s
HighIQ 20.8 · 74 tok/s
MaxIQ 23.1 · 69 tok/s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 67 providers61 with public prices · 1 free · 4 subscription-covered

  • ProviderInput / Output
  • SCNet Token PlanGateway
    DeepSeek-V4-Pro-0813
    Subscription
    Cache read $0Context 1,000,000 ⚠Output limit 384,000
  • Alibaba Token PlanGateway
    Subscription
    Cache read $0Context 1,000,000 ⚠Output limit 384,000
  • Alibaba Token Plan (China)Gateway
    Subscription
    Cache read $0Context 1,000,000 ⚠Output limit 384,000
  • SenseNova (China)Gateway
    deepseek-v4-pro
    Free
    Cache read $0Context 1,048,576Output limit 65,536
  • IteraComputeGateway
    $0.60 / $1.79
    Cache read $0.044Context 1,048,576Output limit 393,216
  • RunInfraGateway
    deepseek-ai/DeepSeek-V4-Pro-0813
    $0.60 / $1.90
    Cache read $0.03Context 1,048,576Output limit 32,768deprecated
  • DeepSeekOfficialFirst-party
    deepseek-v4-pro
    $0.66 / $1.98
    Cache read $0.022Context 1,048,576Output limit 393,216
  • TokenifyGateway
    deepseek/deepseek-v4-pro
    $0.66 / $1.98
    Cache read $0.044Context 1,000,000 ⚠Output limit 384,000
  • Eden AIGateway
    $0.66 / $1.98
    Cache read $0.066Context 1,000,000 ⚠Output limit 384,000
  • Eden AIGateway
    $0.66 / $1.98
    Cache read $0.022Context 1,000,000 ⚠Output limit 384,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
SCNet Token Plan
DeepSeek-V4-Pro-0813
GatewaySubscription$0—1,000,000 ⚠384,000
Alibaba Token PlanGatewaySubscription$0$01,000,000 ⚠384,000
Alibaba Token Plan (China)GatewaySubscription$0$01,000,000 ⚠384,000
SenseNova (China)
deepseek-v4-pro
GatewayFree$0—1,048,57665,536
IteraComputeGateway$0.60$1.79$0.044—1,048,576393,216
RunInfra
deepseek-ai/DeepSeek-V4-Pro-0813
Gateway$0.60$1.90$0.03—1,048,57632,768deprecated
DeepSeekOfficial
deepseek-v4-pro
First-party$0.66$1.98$0.022—1,048,576393,216
Tokenify
deepseek/deepseek-v4-pro
Gateway$0.66$1.98$0.044—1,000,000 ⚠384,000
Eden AIGateway$0.66$1.98$0.066—1,000,000 ⚠384,000
Eden AIGateway$0.66$1.98$0.022—1,000,000 ⚠384,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

Toggle (on / off)effort = higheffort = maxeffort = loweffort = noneeffort = mediumbudget_tokens ≥ 1 ≤ 393,216effort = minimaleffort = xhigh

Interleaved thinking (reasoning between tool calls) is declared by 29 of 67 providers.

1 / 67 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1IteraCompute$142.78
2RunInfra$146.60
3DeepSeek · Official$154.44
4Eden AI$154.44
5Ollama Cloud$154.44
6OrcaRouter$154.44

4 more channels offer $0 (SCNet Token Plan, Alibaba Token Plan, Alibaba Token Plan (China) etc.); free tiers usually have rate limits and no SLA, excluded from ranking.

Switch to IteraCompute to save $11.66/mo (8%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$1.98$02026-08-132026-11-15
2026-11-15Input list $0.66Output list $1.98Min blended $0.90

Benchmark11 items

NameConditionsScoreMetricSource
Humanity's Last Examvariant: without tools42.7scoreSource ↗
Humanity's Last Examvariant: with tools60scoreSource ↗
Terminal-Benchharness: DeepSeek Harness minimal mode · variant: max effort · v2.187.9scoreSource ↗
NL2Repoharness: DeepSeek Harness minimal mode · variant: max effort61.5scoreSource ↗
CyberGymharness: DeepSeek Harness minimal mode · variant: max effort83.3scoreSource ↗
DeepSWEharness: DeepSeek Harness minimal mode · variant: max effort62.7scoreSource ↗
Toolathlon-Verified—74.1scoreSource ↗
Agents' Last Exam—25.7scoreSource ↗
AutomationBenchdataset: public31.8scoreSource ↗
DSBench-FullStackdataset: internal71.1scoreSource ↗
DSBench-Harddataset: internal67.2scoreSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Artificial Analysis evaluations21 items

GPQA Diamond92.8%
Humanity's Last Exam41.0%
HLE-Diamond19.5%
CritPt18.0%
CritPt v2 Hard23.5%
SciCode51.0%
FrontierCode38.8%
FrontierCode 2.017.1%
Terminal-Bench 2.178.6%
Terminal-Bench 4.014.1%
Terminal-Bench-Science5.7%
τ³-Bench Banking39.6%
AutomationBench-AA56.7%
EnterpriseOps-Gym-AA49.6%
AA-Briefcase1253
GDPval-AA1457
GDP.pdf11.4%
AA-LCR80.3%
AA-Omniscience Index-6.4
AA-Omniscience Accuracy45.2%
AA-Omniscience Non-Hallucination5.9%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

DeepSeek V4 Prosame series—DeepSeek V4 Pro 0423same series—DeepSeek Reasonersame series—GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60GPT-5.6 Lunacheaper alternative$0.20 / $1.20MiniMax-M3cheaper alternative$0.30 / $1.20DeepSeek V4 Pro (April preview)same lab—
Data partly from models.dev (MIT) · DeepSeek official docs ↗