RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

DeepSeek: DeepSeek V3 API pricing

$0.257 per 1M input tokens and $1.029 per 1M output tokens on OpenRouter. Context window: 163,840 tokens.

$0.257input / 1M tokens
$1.029output / 1M tokens
160Kcontext
text->textmodality

What it costs in practice

WorkloadCost
Chatbot: 10,000 messages (1,500 in / 400 out tokens each)$7.98
RAG: 1,000 queries (8,000 in / 600 out each)$2.68
Summarize 100 long documents (50,000 in / 1,000 out each)$1.39

Cross-check against the provider's list price

LiteLLM's price map lists deepseek-chat (deepseek) at $0.28 in / $0.42 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 V3 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
OpenAI: GPT-5.6 Luna Pro$0.20$1.201.0013580322265625M
OpenAI: GPT-5.6 Luna$0.20$1.201.0013580322265625M
Z.ai: GLM 4.6V$0.30$0.90128K
Mistral: Codestral 2508$0.30$0.90250K
StepFun: Step 3.7 Flash$0.20$1.15256K
Google: Gemini 3.5 Flash Lite (batch)$0.15$1.251M
DeepSeek: DeepSeek V3.1$0.25$0.95160K
Qwen: Qwen3.6 Flash$0.188$1.125977K

Source: OpenRouter listing via the public models API · LiteLLM price map (MIT). Prices checked Nov 17, 2026. Model ID deepseek/deepseek-chat, listed Dec 26, 2024. Report an error.