DeepSeek · live price
DeepSeek V4.1 Flash API pricing
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
Small and cheap (under $1 per 1M)Tool callingReasoningimage input
- Input
- $0.05
- per 1M tokens
- Output
- $0.199
- per 1M tokens
- Cached input
- $0.0010
- per 1M tokens
- Context
- 1.0M
- 393K max output
List price from OpenRouter, which passes DeepSeek's price through without markup. Refreshed hourly. Released September 10, 2026. Model id deepseek/deepseek-v4.1-flash.
What DeepSeek V4.1 Flash costs in practice
At list price, before any batch or caching discount.
1,000 chat messages
$0.15
1,000 input + 500 output tokens each
1,000 RAG questions
$0.50
8,000 input + 500 output tokens each
100 coding-agent steps
$0.19
30,000 input + 2,000 output tokens each, no caching
DeepSeek V4.1 Flash price history
Price last changed on 2026-11-21. We record prices daily since 2026-10-01.
DeepSeek V4.1 Flash price by host
28 hosts serve this model. Prices are the same or higher than list; the cheapest are first.
- Baidu$0.05 in · $0.199 out · 1.0M ctx · 100.0% uptime 24h
- DeepInfra$0.112 in · $0.336 out · 1.0M ctx · 100.0% uptime 24h
- Alibaba$0.09 in · $0.36 out · 1M ctx · 100.0% uptime 24h
- River$0.12 in · $0.48 out · 1.0M ctx · 100.0% uptime 24h
- Wafer$0.051 in · $0.567 out · 1.0M ctx · 100.0% uptime 24h
- Relace$0.12 in · $0.5 out · 1.0M ctx · 100.0% uptime 24h
- InferenceNet$0.103 in · $0.6 out · 1.0M ctx · 100.0% uptime 24h
- StreamLake$0.147 in · $0.588 out · 1.0M ctx · 100.0% uptime 24h
- Fireworks$0.15 in · $0.6 out · 1.0M ctx · 98.3% uptime 24h
- Novita$0.15 in · $0.6 out · 1.0M ctx · 100.0% uptime 24h
- Reka$0.12 in · $0.64 out · 1.0M ctx · 100.0% uptime 24h
- CoreWeave$0.13 in · $0.65 out · 1.0M ctx · 96.9% uptime 24h
- OpenInference$0.05 in · $0.8 out · 1.0M ctx · 100.0% uptime 24h
- Cohere$0.195 in · $0.66 out · 1.0M ctx · 100.0% uptime 24h
- Ionstream$0.2 in · $0.7 out · 1.0M ctx · 100.0% uptime 24h
- Mancer 2$0.212 in · $0.75 out · 1.0M ctx · 99.0% uptime 24h
- DigitalOcean$0.195 in · $0.78 out · 1.0M ctx · 100.0% uptime 24h
- Cloudflare$0.1 in · $0.9 out · 1.0M ctx · 100.0% uptime 24h
- Makora$0.26 in · $1.17 out · 1.0M ctx · 100.0% uptime 24h
- Crusoe$0.29 in · $1.20 out · 1.0M ctx · 100.0% uptime 24h
- Nebius$0.3 in · $1.20 out · 1.0M ctx · 100.0% uptime 24h
- Google$0.3 in · $1.20 out · 1.0M ctx · 99.8% uptime 24h
- BaseTen$0.3 in · $1.20 out · 1.0M ctx · 100.0% uptime 24h
- Together$0.3 in · $1.20 out · 1.0M ctx · 100.0% uptime 24h
- SiliconFlow$0.3 in · $1.20 out · 1.0M ctx · 100.0% uptime 24h
- Modal$0.3 in · $1.20 out · 1.0M ctx · 100.0% uptime 24h
- Parasail$0.3 in · $1.20 out · 1.0M ctx · 100.0% uptime 24h
- Venice$0.3 in · $1.20 out · 1M ctx · 100.0% uptime 24h
Where to buy DeepSeek credits for less
DeepSeek V4.1 Flash costs the same per token everywhere it's sold through OpenRouter. What changes is the price of the credits. Live quotes for $100 of usage:
DeepSeek V4.1 Flash cost calculator
Enter your monthly tokens to price your own usage.
Usage at list price$4.48/ month(quotes below are for $5.00: purchases run from $5.00 to $10,000.00)
Cheaper alternatives to DeepSeek V4.1 Flash
Other labs' models in the same price range or the one below, cheaper per token.
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Z.ai: GLM 5.3 Flash | $0.04 | $0.078 |
| Qwen: Qwen3.7 Flash | $0.03 | $0.13 |
| OpenAI: gpt-oss-20b | $0.03 | $0.13 |
| Google: Gemma 3 4B | $0.04 | $0.05 |
| Google: Gemma 3 12B | $0.05 | $0.15 |
| Mistral: Mistral Small 3 | $0.05 | $0.08 |
Other DeepSeek models
| Model | Input / 1M | Output / 1M |
|---|---|---|
| DeepSeek V4 Flash Vision Exp | $0.216 | $0.647 |
| DeepSeek V4 Pro 0813 | $1.32 | $3.96 |
| DeepSeek V4.1 Flash 1017 | $0.15 | $0.6 |
| DeepSeek V4 Flash 0731 | $0.044 | $0.3 |
| DeepSeek V4 Pro 0423 | $0.9 | $1.50 |
| DeepSeek V4 Flash 0423 | $0.09 | $0.18 |