DeepSeek V4.1 Flash pricing
DeepSeek · API id deepseek-flash · verified 2026-10-18
| Input | $0.30 |
| Cached input (cache hit) | $0.006 |
| Cache write | — |
| Output | $1.20 |
| Batch discount | — |
| Context window | 1,000,000 tokens |
| Max output | 384,000 tokens |
| Off-peak | $0.15 in / $0.60 out |
USD per 1M tokens unless noted. Official source
Estimate your workload on DeepSeek V4.1 Flash →
What DeepSeek V4.1 Flash costs for real workloads
| Workload | DeepSeek V4.1 Flash | Ministral 3 8B | Claude Haiku 5.5 | GPT-6 Luna | Mistral Small 4 |
|---|---|---|---|---|---|
| 10,000 chatbot replies 2,000 input + 400 output tokens each, 50% of the prompt cached | $7.86 | $2.25 | $3.10 | $3.10 | $4.05 |
| One 30-step coding agent run 12K system + tools prompt, 1K output and 3K tool result per step, caching on | $0.09 | $0.05 | $0.12 | $0.05 | $0.07 |
| 1M documents classified (batch) 600 input + 20 output tokens each, batch API where available | $204 | $46.50 | $35.00 | $35.00 | $51.00 |
Compared with the cheapest other small models. Change the numbers in the calculator.
Billing notes
Version DeepSeek-V4.1-Flash-1017; supports vision. Legacy ids deepseek-v4-flash / deepseek-v4-flash-vision-exp route here at this price. Prices shown are PEAK (01:00-04:00 and 06:00-10:00 UTC Mon-Fri, excl. Chinese public holidays). All other hours (most of the week) are off-peak at 50% - see offPeak. No batch API.
Where DeepSeek V4.1 Flash ranks by use case
Position by cost among all models that fit each workload (1 = cheapest).
- Cheapest LLM for coding agents: #4 of 36 (Per run (cached): $0.09)
- Cheapest LLM for RAG chatbots: #8 of 36 (Per 1,000 answers: $1.84)
- Cheapest LLM for batch classification and extraction: #10 of 36 (Classify 1M docs: $204)
- Long-context document analysis (400K tokens): #1 of 29 (10 questions, cached: $0.17)
- Cheapest LLM for high-volume customer support: #7 of 36 (Per 1,000 replies: $0.67)
Counting tokens for a prompt? The token counter estimates DeepSeek V4.1 Flash tokens (xAI, DeepSeek, Mistral tokenizer, estimated) and input cost.
Head-to-head comparisons
- GPT-6 Luna vs DeepSeek V4.1 Flash
- Claude Haiku 5.5 vs DeepSeek V4.1 Flash
- Gemini 3.5 Flash-Lite vs DeepSeek V4.1 Flash
Other DeepSeek models
- DeepSeek V4 Pro: $1.32 / $3.96
FAQ
How much does DeepSeek V4.1 Flash cost per 1M tokens?
DeepSeek V4.1 Flash costs $0.30 per 1M input tokens and $1.20 per 1M output tokens at standard rates (verified 2026-10-18). Off-peak hours bill $0.15 input and $0.60 output.
Does DeepSeek V4.1 Flash support prompt caching?
Yes. Cached input is billed at $0.006 per 1M tokens.
Is there a batch discount for DeepSeek V4.1 Flash?
No batch discount is published for this model.
What is the context window of DeepSeek V4.1 Flash?
1,000,000 tokens, with up to 384,000 output tokens.