API pricing per million tokens
- Input
- $0.15
- per 1M, list
- Output
- $0.6
- per 1M tokens
- Cached input
- $0.003
- batch $0.112 / $0.336
- Context
- 1M
- 131K max output
Price history
List price since Sep 23, 2026, from daily reads of the OpenRouter catalog.
| Seen | Model | Old price | New price | Change |
|---|---|---|---|---|
| Sep 24, 2026 |  DeepSeek V4.1 FlashInput $0.15 to $0.3, Output $0.6 to $1.2, Cached input $0.003 to $0.006 | Input $0.15Output $0.6Cached input $0.003 | Input $0.3Output $1.2Cached input $0.006 | +100% |
| Sep 24, 2026 | DeepSeek V4.1 FlashInput $0.15 to $0.3, Output $0.6 to $1.2, Cached input $0.015 to $0.03 on qwenon qwen | Input $0.15Output $0.6Cached input $0.015 | Input $0.3Output $1.2Cached input $0.03 | +100% |
| Sep 24, 2026 | DeepSeek V4.1 FlashInput $0.285 to $0.225, Output $1.14 to $0.9, Cached input $0.0057 to $0.0045 on gmicloud/fp8on gmicloud/fp8 | Input $0.285Output $1.14Cached input $0.0057 | Input $0.225Output $0.9Cached input $0.0045 | -21% |
| Sep 24, 2026 | DeepSeek V4.1 FlashInput $0.15 to $0.199, Output $0.6 to $0.794, Cached input $0.003 to $0.004 on streamlake/fp8on streamlake/fp8 | Input $0.15Output $0.6Cached input $0.003 | Input $0.199Output $0.794Cached input $0.004 | +32% |
| Sep 24, 2026 | DeepSeek V4.1 FlashInput $0.169 to $0.099 on waferon wafer | Input $0.169 | Input $0.099 | -41% |
Through a gateway
Your own numbers100M input and 20M output tokens a month: $27.00 direct.
Helicone$27.00+0%
Kong AI Gateway$27.00+0%
LiteLLM$27.00+0%
Vercel AI Gateway$27.00+0%
AWS Bedrock$27.00+0%
Azure AI Foundry$27.00+0%
Google Vertex AI$27.00+0%
Databricks Mosaic AI$27.00+0%
Hugging Face Inference$27.00+0%
Cloudflare AI Gateway$28.35+5%
Requesty$28.35+5%
Eden AI$28.48+5.5%
OpenRouter$28.48+5.5%
Snowflake Cortex AI$32.40+20%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative AIn/a
NVIDIA NIMn/a
Related models
Gemini 3.1 Flash LiteGoogle Gemini API · 1M$0.25 / $1.5in / out per 1M$0.25$1.5$0.0251MMay 7, 2026
GPT-6 LunaOpenAI · 1.05M$0.1 / $0.5in / out per 1M$0.1$0.5$0.011.05MSep 22, 2026
About DeepSeek V4.1 Flash
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.
Takes text, image in and returns text. First listed Sep 23, 2026. Blended price $0.262 per 1M tokens at 3 input to 1 output. Overall score 3 on leadersboard.fru.dev (rank 33).
Questions
How much does DeepSeek V4.1 Flash cost?
$0.15 per million input tokens and $0.6 per million output tokens, with cached input at $0.003, or $0.112 and $0.336 through the Batch API.
What is the context window of DeepSeek V4.1 Flash?
1M tokens, with up to 131K tokens of output.
Where is DeepSeek V4.1 Flash cheapest?
Of 25 routes tracked, Relace is cheapest at $0.05 input and $0.25 output per million tokens.
Has DeepSeek V4.1 Flash's price changed?
Yes. The output price went from $0.6 to $1.2, first seen Sep 24, 2026.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.