DeepSeek: DeepSeek V3
DeepSeekOpen weights
DeepSeek: DeepSeek V3 by DeepSeek costs $0.14 per 1M input tokens and $0.28 per 1M output tokens, with a 164K-token context window.
Pricing
Input (per 1M tokens)
$0.14
Output (per 1M tokens)
$0.28
Cached input (per 1M)
$0.00
| Provider | Input / 1M | Output / 1M |
|---|---|---|
| DeepSeek | $0.14 | $0.28 |
| openrouter | $0.32 | $0.89 |
Specifications
- Provider
- DeepSeek
- Context window
- 164K tokens
- Parameters
- 671B
- Released
- Dec 2025
- Open weights
- Yes
- Frontier model
- No
- Hugging Face
- deepseek-ai/DeepSeek-V3
Benchmarks
- FrontierMath
- 1.7
- GPQA Diamond
- 67.6
Speed & latency
Time to first token
0.54s
Output speed
26 tok/s
Fastest host: deepinfra (via hf-router).
Compare DeepSeek: DeepSeek V3 with…
FAQ
How much does DeepSeek: DeepSeek V3 cost?
DeepSeek: DeepSeek V3 is priced at $0.14 per 1M input tokens and $0.28 per 1M output tokens. Output tokens cost more than input.
What is DeepSeek: DeepSeek V3's context window?
DeepSeek: DeepSeek V3 supports a context window of 164K tokens — the maximum prompt plus response length it can handle in a single request.
Is DeepSeek: DeepSeek V3 open weight?
Yes — DeepSeek: DeepSeek V3 has openly available weights.
Data as of 2026-10-15. Source: Pricing via OpenRouter API, openrouter.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.