Models / DeepSeek / DeepSeek V4 Pro

DeepSeek · deepseek-thinking

DeepSeek V4 Pro

Open MoE flagship with million-token context for coding and long agent runs

$1.32 in · $3.96 out

per 1M tokens · provider rate closest to the median. No first-party DeepSeek price was listed. The reference price is LLM Gateway's rate, the provider closest to the median.

Provider input prices run from $0.35 to $1.91 per 1M tokens. Output prices run from $0.70 to $4.05.

Context
1,000,000
Max output
384,000
Cache read
$0.042
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
No
Open weights
Yes
License
—
Released
Apr 24, 2026
Updated in source
Apr 24, 2026
Knowledge
2025-05
Providers
58

Hugging Face weights

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. Where a provider lists the model more than once, the row is the listing whose id is closest to the canonical model id.
ProviderInputOutputCache readCache writeStatus
routing.run$0.35$0.70———
CrofAI$0.35$0.80$0.003——
OpenRouter$0.41$0.81$0.034——
EBCloud$0.43$0.86———
Alibaba$0.44$0.87$0.004——
Auriko$0.44$0.87$0.004——
DevPass$0.44$0.87$0.004——
Hugging Face$0.44$0.87$0.004——
Modelis$0.44$0.87———
Nvidia$0.44$0.87$0.004—deprecated
Pioneer$0.44$0.87$0.004$0.44—
TokenGo$0.44$0.87———
Vivgrid$0.44$0.87$0.004——
ZenMux$0.44$0.87$0.004——
OrcaRouter$0.44$0.88$0.06——
Eden AI$0.66$1.98$0.022——
Vercel AI Gateway$0.66$1.98$0.022——
UnoRouter$0.90$1.80———
ai&$1.00$2.50$0.25——
Neuralwatt$1.00$3.00$0.10—deprecated
NanoGPT$1.10$2.20$0.11——
AI/ML API$1.17$3.51$0.039——
Deep Infra$1.30$2.60$0.10——
LLM Gatewayreference$1.32$3.96$0.042——
Ofox$1.32$3.96$0.044——
Requesty$1.32$3.96$0.044——
CrossModel$1.35$4.05$0.045$1.35—
GMI Cloud$1.39$2.78$0.12——
SiliconFlow$1.50$3.14$0.14——
Jalapeno Cloud$1.60$3.38———
Kilo Gateway$1.60$3.20$0.14——
Novita AI$1.60$3.20$0.14——
EmpirioLabs AI$1.65$3.30$1.65——
Venice AI$1.65$3.30$0.33——
Cortecs$1.70$3.40$0.15——
Abacus$1.74$3.48$0.15——
Arcee$1.74$3.48$0.20—beta
Azure$1.74$3.48———
Baseten$1.74$3.48$0.15——
ClinePass$1.74$3.48$0.015——
Cloudflare AI Gateway$1.74$3.48$0.15——
FastRouter$1.74$3.48———
HPC-AI$1.74$3.48$0.15——
Impossibl$1.74$3.48$0.15——
Merge Gateway$1.74$3.48$0.15——
OpenCode$1.74$3.84$0.15——
Nebius Token Factory$1.75$3.50$0.15——
TensorX$1.75$3.50$0.44$2.19—
Opper$1.79$3.58———
Moark$1.80$3.60———
Prime Inference$1.91$3.83———
Alibaba Token Plan$0$0$0$0—
Alibaba Token Plan$0$0$0$0—
AnyAPI—————
Kenari$0$0———
Model Oracle AI—————
SCNet Token Plan$0$0$0——
Volcengine Ark Coding Plan$0$0$0——

Jobs this model qualifies for

Comparisons