RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

DeepSeek: DeepSeek V4 Pro 0423 API pricing

$0.90 per 1M input tokens and $1.50 per 1M output tokens on OpenRouter. Context window: 1,048,576 tokens.

$0.90input / 1M tokens
$1.50output / 1M tokens
$0.25cached input / 1M
1Mcontext
text->textmodality

What it costs in practice

WorkloadCost
Chatbot: 10,000 messages (1,500 in / 400 out tokens each)$19.50
RAG: 1,000 queries (8,000 in / 600 out each)$8.10
Summarize 100 long documents (50,000 in / 1,000 out each)$4.65

Cross-check against the provider's list price

LiteLLM's price map lists deepseek-v4-pro (deepseek) at $1.32 in / $3.96 out per 1M tokens. Differs from OpenRouter OpenRouter routes to several hosts and may list a different provider's price than the model maker's own API.

Price history

No price change recorded since we started tracking on Nov 17, 2026. We check every 6 hours and log every change.

Run it yourself instead

The open weights are on Hugging Face. See the VRAM DeepSeek V4 Pro needs and which GPUs fit it →

Cheaper alternatives with similar context

Text models with at least 125K context and a lower blended price (75% input, 25% output). Price only, not a quality ranking.

ModelInput / 1MOutput / 1MContext
Mistral: Mistral Large 4$0.70$2.101M
Qwen: Qwen3.6 27B$0.32$3.20256K
MoonshotAI: Kimi K2 0711$0.57$2.30128K
OpenAI: GPT-6.1 Terra Pro (batch)$0.50$2.501.0013580322265625M
OpenAI: GPT-6.1 Terra (batch)$0.50$2.501.0013580322265625M
ByteDance Seed: Seed 2.1 Turbo$0.50$2.50256K
AionLabs: Aion-2.0$0.80$1.60128K
MoonshotAI: Kimi K2.5$0.50$2.50256K

Source: OpenRouter listing via the public models API · LiteLLM price map (MIT). Prices checked Nov 17, 2026. Model ID deepseek/deepseek-v4-pro, listed Apr 24, 2026. Report an error.