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. It activates 8B parameters on input and 16B on...
DeepSeek V4.1 Flash costs $0.09 per 1M input tokens and $0.18 per 1M output tokens at the standard tier, the lowest default-region price among the 30 providers SF·SIX tracks, from Decart (fp4). On DeepSeek’s own API it costs $0.15 / $0.60. Cached input reads cost $0.018 per 1M tokens. Updated ; prices checked .
- Developer
- DeepSeek
- Input modalities
- text, image
- Output modalities
- text
- Context tokens
- 1,048,576
- Latest price observation
- 2026-10-17
- Lowest paired standard token quote
- $0.09 input / $0.18 output per 1M tokens
Dated price and provider records
| Provider and channel | Input | Output or native rate | Unit and status | Source and observation |
|---|---|---|---|---|
| DecartOpenRouter | $0.09 | $0.18 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Sail ResearchOpenRouter | $0.09 | $0.30 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| MorphOpenRouter | $0.088 | $0.55 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| DeepInfraOpenRouter | $0.14 | $0.42 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| AtlasCloudOpenRouter | $0.135 | $0.54 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| WaferOpenRouter | $0.10 | $0.65 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| InferenceNetOpenRouter | $0.103 | $0.715 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| StreamLakeOpenRouter | $0.1497 | $0.5988 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| DeepSeekOpenRouter | $0.15 | $0.60 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| CoreWeaveOpenRouter | $0.15 | $0.65 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| CloudflareOpenRouter | $0.10 | $0.90 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| OpenInferenceOpenRouter | $0.20 | $0.60 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| RelaceOpenRouter | $0.20 | $0.60 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| GMI CloudOpenRouter | $0.18 | $0.72 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| DigitalOceanOpenRouter | $0.195 | $0.78 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Novita AIOpenRouter | $0.195 | $0.78 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| PhalaOpenRouter | $0.21 | $0.84 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| IonstreamOpenRouter | $0.27 | $1.10 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| CrusoeOpenRouter | $0.29 | $1.20 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| AlibabaOpenRouter | $0.30 | $1.20 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| BaiduOpenRouter | $0.30 | $1.20 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| BasetenOpenRouter | $0.30 | $1.20 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Fireworks AIOpenRouter | $0.30 | $1.20 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| ModalOpenRouter | $0.30 | $1.20 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Nebius AI StudioOpenRouter | $0.30 | $1.20 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| ParasailOpenRouter | $0.30 | $1.20 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| PrimeIntellectOpenRouter | $0.30 | $1.20 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| SiliconFlowOpenRouter | $0.30 | $1.20 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Together AIOpenRouter | $0.30 | $1.20 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Venice AIOpenRouter | $0.30 | $1.20 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| BasetenOpenRouter · US region | $0.30 | $1.20 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Fireworks AIOpenRouter · US region | $0.45 | $1.80 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| DeepInfraOpenRouter · Priority tier | $0.21 | $0.63 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| BasetenOpenRouter · Fast tier | $0.60 | $2.40 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| DeepInfraOpenRouter · Flex tier | $0.112 | $0.336 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
Batch and free variants
- DeepSeek V4.1 Flash (batch) · from $0.05 input / $0.15 output per 1M tokens
Prices by service tier
| Tier | Input / 1M | Output / 1M | Cache read / 1M | Cheapest provider | vs standard (blended) |
|---|---|---|---|---|---|
| Standard | $0.09 | $0.18 | $0.018 | Decart | 100% |
| BatchBatch endpoint | $0.05 | $0.15 | $0.004 | OpenRouter (auto-routed) | 67% |
| Flex | $0.112 | $0.336 | $0.00336 | DeepInfra | 149% |
| Priority | $0.21 | $0.63 | $0.0063 | DeepInfra | 280% |
| Fast | $0.60 | $2.40 | $0.014 | Baseten | 933% |
Each tier’s cheapest endpoint. Standard is the default-region headline; flex and batch trade speed or latency for a lower price, priority and fast cost more for faster service.
Regional endpoints
| Provider and region | Input / 1M | Output / 1M |
|---|---|---|
| BasetenUS region | $0.30 | $1.20 |
| Fireworks AIUS region | $0.45 | $1.80 |
Data-residency endpoints in a named region; they are never used as the headline while a default-region price exists.
Speed by provider
| Provider and terms | Throughput | Latency | Uptime | Input / 1M |
|---|---|---|---|---|
| Fireworks AIUS region | 272 tok/s | 515 ms | 100.0% | $0.45 |
| CoreWeavefp8 | 244 tok/s | 366 ms | 100.0% | $0.15 |
| Baseten | 221 tok/s | 368 ms | 100.0% | $0.30 |
| BasetenFast tier | 220 tok/s | 324 ms | 100.0% | $0.60 |
| Together AI | 214 tok/s | 348 ms | 100.0% | $0.30 |
| BasetenUS region | 212 tok/s | 217 ms | 100.0% | $0.30 |
| DigitalOcean | 186 tok/s | 834 ms | 100.0% | $0.195 |
| PrimeIntellect | 171 tok/s | 497 ms | 100.0% | $0.30 |
| Morphfp8 | 157 tok/s | 282 ms | 100.0% | $0.088 |
| Crusoefp8 | 137 tok/s | 608 ms | 100.0% | $0.29 |
| Parasailfp8 | 133 tok/s | 684 ms | 100.0% | $0.30 |
| Nebius AI Studiofp8 | 131 tok/s | 1.30 s | 100.0% | $0.30 |
Previous 30 minutes; reported by OpenRouter. Fastest first.
Usage on OpenRouter
| UTC day | Tokens |
|---|---|
| 2026-10-10 | 5,022,780,525,937 |
| 2026-10-11 | 5,679,385,293,681 |
| 2026-10-12 | 6,020,046,730,509 |
| 2026-10-13 | 5,046,621,695,407 |
| 2026-10-14 | 4,474,714,742,293 |
| 2026-10-15 | 5,167,300,442,116 |
| 2026-10-16 | 5,413,760,580,051 |
OpenRouter rankings (CC BY 4.0), named daily rows. Most-used AI models
Benchmarks
Artificial Analysis Intelligence Index 39.5, coding index Not reported, agentic index Not reported (Artificial Analysis via OpenRouter, CC BY 4.0; not an SF·SIX measurement).
Prediction markets
DeepSeek V4.1 Flash meets the rule for SF·SIX price and usage ladders; the current average standard input price across qualifying OpenRouter endpoints is $0.2304 per 1M tokens. Open DeepSeek V4.1 Flash markets (Hedera testnet, test funds only) · How AI prediction markets work
Compare and estimate
Sources and method
Prices are USD per 1M tokens at the standard service tier in the default region: the cheapest qualifying provider per model, with flex, batch, priority and fast endpoints and unusually low outliers never used as the headline. “Blended” weights input and output 3:1. Prices from OpenRouter; each row below links its source and observation date. Methodology and editorial policy.
Frequently asked questions
How much does DeepSeek V4.1 Flash cost per 1M tokens?
$0.09 per 1M input tokens and $0.18 per 1M output tokens at the standard tier, the lowest default-region price SF·SIX tracks, from Decart (fp4). On DeepSeek’s own API it costs $0.15 / $0.60. The cheapest batch price is $0.05 input and $0.15 output per 1M tokens.
Which providers offer DeepSeek V4.1 Flash?
30 providers with 35 priced endpoints: Alibaba, AtlasCloud, Baidu, Baseten, Cloudflare, CoreWeave, Crusoe, Decart and others.
What is the context window of DeepSeek V4.1 Flash?
1,048,576 tokens.
How fast is DeepSeek V4.1 Flash?
The fastest measured endpoint is Fireworks AI (US region) at 272 tok/s, as reported by OpenRouter for the previous 30 minutes.
How much is DeepSeek V4.1 Flash used?
5,413,760,580,051 tokens on 2026-10-16 (UTC) through OpenRouter, per OpenRouter’s public rankings. This is OpenRouter traffic only, not all usage.
These are dated, non-executable observations. Verify the exact endpoint, price and terms with the source before use. Unknown values are not free.