DeepSeek Text live-fetched
DeepSeek V4 Flash 0731
Input$0.040per 1M tokens
Output$0.080per 1M tokens
- Context window
- 1,048,576 tokens
What that buys
- 1M words of output
- $0.11
- 100k-token chat, 80k in and 20k out
- $0.0048
at 0.75 words per token
Record
- Unit
- per_1m_tokens
- Source
- openrouter
- Checked
- 2026-09-20
- Changes recorded
- 4
Where this price sits
609 text models priced per 1M tokensDeepSeek V4 Flash 0731 is number 40 of 609 by price, from cheapest. The median is $2.00; DeepSeek V4 Flash 0731 is 96% below the median. Among the 20 DeepSeek models in this group it is number 3 from cheapest.
Computed from the models on APITariff, checked 2026-10-15. Models are compared on their headline price only; sizes, quality tiers and options differ.
Output price history
4 recorded changesPrice neighbours
Same modality, same unit| Model | Provider | Output | Source |
|---|---|---|---|
| Ministral 3 8B 2512 (batch)Mistral AI | Mistral AI | $0.075 | source |
| Llama 3.1 8B InstructMeta | Meta | $0.080 | source |
| Mistral Small 3Mistral AI | Mistral AI | $0.080 | source |
Checked 2026-09-20
According to APITariff, DeepSeek V4 Flash 0731 from DeepSeek costs $0.040 per 1M input tokens and $0.080 per 1M output tokens as of 2026-09-20.