LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

DeepSeek V3 0324

deepseek·deepseek/deepseek-v3-0324·Deprecated·Open weights·deepseek series
March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding

DeepSeek V3 0324 is offered by 13 providers on this page. Public prices are shown for 12 of them. Its reference price is $0.50 per 1M input tokens and $1.50 per 1M output tokens. The lowest paid channel is NanoGPT at $0.20 / $0.77 per 1M, about 2.5× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

Artificial Analysis rates it 9.7 on the Intelligence Index, with 21.2 for coding and 0.8 for agentic tasks. Against its lowest blended price of $0.343 per 1M, that is roughly 28 index points per dollar, which is the value ratio the leaderboards rank on. Running one task of the Artificial Analysis suite costs about $0.0202, which reflects how many tokens its reasoning consumes rather than the unit price alone.

The context window is 163,840 tokens at the reference host, but hosts report different limits, from 75,000 to 163,840, so the usable window depends on the provider you pick. It supports tool use and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-07.

Specs & pricing

Input / output per 1M tokens
Reference price·Crusoe
$0.50 / $1.50
Blended $0.75 · Cache read $0.25
Lowest paid·NanoGPTGateway
$0.20 / $0.77
Blended $0.34 · 2.5× spread
Context
163,840
Output limit
163,840
Knowledge cutoff
2024-07
Released / updated
2025-03-24 / 2025-03-24
Capabilities
Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Weights
Model weightssafetensors

Quality & performanceArtificial Analysis · Intelligence Index v4.3

Intelligence9.7
Value28
Coding21.2
Agentic0.8
Output speed—
TTFT—
Cost per task$0.02
Value formulaIQ 9.7 ÷ min blended $0.343 = 28

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

Available at 13 providers12 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NanoGPTGateway$0.20$0.77$0.14—128,000 ⚠8,192
submodel
deepseek-ai/DeepSeek-V3-0324
Gateway$0.20$0.80——75,000 ⚠—
Deep Infra
deepseek-ai/DeepSeek-V3-0324
Cloud$0.24$0.90$0.14—163,840163,840deprecated
Eden AI
deepinfra/deepseek-ai/DeepSeek-V3-0324
Gateway$0.24$0.90$0.14—163,840163,840
Meganova
deepseek-ai/DeepSeek-V3-0324
Gateway$0.25$0.88——163,840163,840
Alibaba (China)First-party$0.25$1.00——163,840163,840
NovitaAIGateway$0.27$1.12$0.14—163,840163,840
Hugging Face
deepseek-ai/DeepSeek-V3-0324
Cloud$0.27$1.12——163,840163,840
Jiekou.AIGateway$0.28$1.14——163,840163,840
OpenRouter
deepseek/deepseek-chat-v3-0324
Gateway$0.29$1.14$0.11—163,840115,200

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.

Your usage cost

1NanoGPT$70.70
2submodel$80.00
3Deep Infra$80.40
4Eden AI$80.40
5OpenRouter$93.40
6Kilo Gateway$93.40
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$1.50$02026-08-052026-09-032026-08-05 · Input list $0.202026-08-06 · Input list $0.202026-08-07 · Input list $0.202026-08-08 · Input list $0.202026-08-09 · Input list $0.202026-08-10 · Input list $0.202026-08-11 · Input list $0.202026-08-12 · Input list $0.202026-08-13 · Input list $0.282026-08-14 · Input list $0.502026-09-03 · Input list $0.502026-08-05 · Output list $0.772026-08-06 · Output list $0.772026-08-07 · Output list $0.772026-08-08 · Output list $0.772026-08-09 · Output list $0.772026-08-10 · Output list $0.772026-08-11 · Output list $0.772026-08-12 · Output list $0.772026-08-13 · Output list $1.142026-08-14 · Output list $1.502026-09-03 · Output list $1.502026-08-05 · Min blended $0.342026-08-06 · Min blended $0.342026-08-07 · Min blended $0.342026-08-08 · Min blended $0.342026-08-09 · Min blended $0.342026-08-10 · Min blended $0.342026-08-11 · Min blended $0.342026-08-12 · Min blended $0.342026-08-13 · Min blended $0.352026-08-14 · Min blended $0.352026-09-03 · Min blended $0.34

Artificial Analysis evaluations14 items

GPQA Diamond65.5%
Humanity's Last Exam4.7%
MMLU-Pro81.9%
SciCode39.0%
LiveCodeBench40.5%
Terminal-Bench Hard15.2%
Terminal-Bench 2.113.9%
AIME 202541.0%
AIME52.0%
MATH-50094.2%
τ²-Bench Telecom47.1%
τ³-Bench Banking4.7%
AA-LCR40.7%
IFBench41.0%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.

Related models

DeepSeek: DeepSeek Pro Latestsame series$0.19 / $4.20DeepSeek V4 Flash Latestsame series$0.015 / $1.28DeepSeek Latestsame series$1.10 / $2.50Command Rcheaper alternative$0.15 / $0.60Gemma 3 12B ITcheaper alternative$0.27 / $0.27Qwen3 30B A3B Instruct 2507cheaper alternative$0.30 / $0.50DeepSeek V3.2 Expcheaper alternative$0.29 / $0.43
Data partly from models.dev (MIT) · Crusoe official docs ↗