DeepSeek: DeepSeek V3.2 API pricing
$0.26 per 1M input tokens and $0.38 per 1M output tokens on OpenRouter. Context window: 163,840 tokens.
What it costs in practice
| Workload | Cost |
|---|---|
| Chatbot: 10,000 messages (1,500 in / 400 out tokens each) | $5.42 |
| RAG: 1,000 queries (8,000 in / 600 out each) | $2.31 |
| Summarize 100 long documents (50,000 in / 1,000 out each) | $1.34 |
Cross-check against the provider's list price
LiteLLM's price map lists deepseek/deepseek-v3.2 (deepseek) at $0.28 in / $0.40 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 V3.2 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.
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| Tencent: Hy3 preview | $0.18 | $0.60 | 256K |
| Google: Gemini 3.1 Flash Lite (batch) | $0.125 | $0.75 | 1M |
| MiniMax: MiniMax M3.1 Flash | $0.15 | $0.60 | 1M |
| Upstage: Solar Pro 4 | $0.15 | $0.60 | 512K |
| Mistral: Mistral Small 4 | $0.15 | $0.60 | 256K |
| Qwen: Qwen3 VL 30B A3B Instruct | $0.15 | $0.60 | 256K |
| OpenAI: gpt-oss-120b | $0.15 | $0.60 | 128K |
| Qwen: Qwen3 Coder 30B A3B Instruct | $0.15 | $0.60 | 256K |
Source: OpenRouter listing via the public models API · LiteLLM price map (MIT). Prices checked Nov 17, 2026. Model ID deepseek/deepseek-v3.2, listed Dec 1, 2025. Report an error.