AI Calculator Pro

DeepSeek V4 Pro

DeepSeek · DeepSeek V4 · context window 1,000,000 tokens.

Pricing (per 1M tokens)

Input$0.6600
Output$1.98
Cache read$0.0220

Specifications

Context window1,000,000 tokens
Max output8,192 tokens
Modalitiestext
VisionNo
Tool useYes
ReasoningYes
Prompt cachingYes

DeepSeek V4 Pro has had 3 tracked price changes since we began monitoring. Most recent: cached input $0.00363 → $0.0220 on 3 October 2026. All-time low input rate: $0.4350/1M.

Input price over time ($/1M tokens)
Low $0.435High $0.660

Recorded from our daily pricing checks. See the full LLM price tracker.

Intelligence & value

Measured
Overall1445 · #44
Coding1448 · #57
Math & reasoning1395 · #13
Agentic / tool use1380 · #12

Worth it? DeepSeek V4.1 Flash matches or beats DeepSeek V4 Pro on the overall Arena and costs about $10.50/month versus $198.00/month at 100,000 calls — roughly $187.50/month cheaper.

Intelligence scores are community Arena ratings from LMArena / arena.ai, used under CC BY 4.0. Snapshot last refreshed 10 November 2026. Scores are a relative signal, not an absolute measure of capability. A Measured score was voted on directly; an Estimated score is inherited from an identical base model (a regional/creator-prefixed hosting duplicate). See our methodology.

Where else you can run DeepSeek V4 Pro

The same model is resold by 58 providers we track. The typical one charges 4.6× what the cheapest does — $1.98 against $0.4350 per 1M tokens, blended 3:1. Routing the same workload to a different host is often a bigger saving than switching model.

ProviderInput / 1MOutput / 1MBlended
Routing RUN$0.3480$0.6960$0.4350
Ebcloud$0.4290$0.8570$0.5360
Huggingface$0.4350$0.8700$0.5440
Modelis$0.4350$0.8700$0.5440
Tokengo$0.4350$0.8700$0.5440
Kenari$0.5710$1.14$0.7140
NanoGPT$0.7000$1.40$0.8750
Cline Pass$0.6600$1.98$0.9900
Commandcode$0.6600$1.98$0.9900
DeepSeek$0.6600$1.98$0.9900

Showing the 10 cheapest of 58. The full list for every model is in the open endpoint dataset.

Third-party listings via models.dev, not rates we verify with each host the way we do first-party pricing. Treat them as a shortlist to check, not a quote — and confirm quantisation, context limits and rate limits before switching, since a cheaper host is not always serving the same thing.

Estimate cost with DeepSeek V4 Pro

DeepSeek V4 Pro is pre-selected below. Enter your token counts and volume to see the cost per request, per day and per month — then switch models to compare.

Results update automatically as you type.

Result
$0.00165 per request
~$49.50/month at 1,000 requests/day
Input cost
$0.000660
Output cost
$0.000990
Per request
$0.00165
Per day
$1.65
Per month
$49.50

Compare DeepSeek V4 Pro with

Source: DeepSeek API pricing. Prices are re-checked daily against the provider’s official pricing; this rate was last changed on 10 November 2026. A recent date here just means the price is still current, not that it moved.