Skip to content
LLM Pricing Calc
Pricing last verified

DeepSeek V4 Pro (open weights) pricing calculator

DeepSeek's 1.6T-parameter open-weight flagship, served by third-party hosts. Pricing shown is DeepInfra's serverless rate.

Input
$1.30 / 1M
Cached input
$0.10 / 1M
Output
$2.60 / 1M
Context window
1.05M
Batch API
No
Reasoning
Yes

Official pricing ↗

Workload

Quick presets

1,000 tokens ≈ 750 English words.

Pro / Agent mode

Caching, batch, multi-turn loops, reasoning tokens

Cost comparison

Cheapest / month

$8.46

Llama 3.3 70B Instruct

Most expensive / month

$90.96

DeepSeek V4 Pro (open weights)

Tokens / request

1.5K in

400 out (cheapest model)

Estimated cost per model
Remove
Llama 3.3 70B InstructCheapestMeta via DeepInfra · $0.10 / $0.32$0.00028$0.278$8.46$101.47
gpt-oss-120bOpenAI via Together · $0.15 / $0.60$0.00047$0.465$14.15$169.73
Qwen3.5-397B-A17BAlibaba via DeepInfra · $0.45 / $3.00$0.00187$1.88$57.04$684.38
DeepSeek V4 Pro (open weights)DeepSeek via DeepInfra · $1.30 / $2.60$0.00299$2.99$90.96$1,091

Monthly = daily × 30.42. Prices are list prices for the standard context tier. Long-context surcharges, regional pricing and taxes are not included.Official pricing: DeepInfra ↗ · Together ↗

What DeepSeek V4 Pro (open weights) costs for common workloads

Monthly estimates using the presets above, at list price.

WorkloadPer request / sessionMonthlyYearly
Small Chatbot1K chats/day, short prompts$0.00156$47.46$569.40
RAG App5K queries/day, 4K-token retrieved context$0.00432$657.07$7,884
Coding Agent200 sessions/day × 25 turns$0.4224$2,570$30,835
Enterprise Scale250K requests/day, batched$0.00311$23,652$283,788

Official pricing ↗ (DeepSeek via DeepInfra) · API model ID deepseek-ai/DeepSeek-V4-Pro

DeepSeek V4 Pro (open weights) pricing FAQ

How much does DeepSeek V4 Pro (open weights) cost per 1M tokens?

DeepSeek V4 Pro (open weights) via DeepInfra costs $1.30 per 1M input tokens and $2.60 per 1M output tokens. Cached input is $0.10 per 1M. Prices were last verified on Nov 21, 2026.

How much does one DeepSeek V4 Pro (open weights) request cost?

A typical request with 1,000 input tokens and 500 output tokens costs about $0.0026. At 1,000 such requests per day that is $79.09 per month.

Does DeepSeek V4 Pro (open weights) support prompt caching?

Yes. Cached input tokens cost $0.10 per 1M, 92% less than regular input. Turn on Pro mode above to model your cache hit rate.

Is there a Batch API discount for DeepSeek V4 Pro (open weights)?

No 50% batch discount is listed for DeepSeek V4 Pro (open weights) via DeepInfra.

What is the context window of DeepSeek V4 Pro (open weights)?

DeepSeek V4 Pro (open weights) supports up to 1.05M tokens of context.

Is DeepSeek V4 Pro (open weights) cheaper than Qwen3.5-397B-A17B?

For a 1,000-in / 500-out request, DeepSeek V4 Pro (open weights) costs $0.0026 and Qwen3.5-397B-A17B costs $0.00195, so Qwen3.5-397B-A17B is 25% cheaper. Quality, speed and caching behaviour differ, so compare on your own workload above.

More AI cost tools