DeepSeek: DeepSeek V4.1 Flash 1017
by DeepSeekDeepSeek: DeepSeek V4.1 Flash 1017 is a large language model from DeepSeek. It costs $0.150 per million input tokens and $0.600 per million output tokens. Its context window is 1.0M tokens.
- Input / 1M tokens
- $0.150
- Output / 1M tokens
- $0.600
- Cached input / 1M
- $0.0030
- Context window
- 1.0M
On repeated prefixes
tokens
Who serves it cheapest
35 hosts serve DeepSeek V4.1 Flash 1017. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| Sail ResearchCheapestfp4 | $0.101 | $0.150 | 1.0M | - | 100.0% |
| DeepInfrafp8 | $0.078 | $0.235 | 1.0M | - | 92.4% |
| Morphfp8 | $0.044 | $0.383 | 1.0M | - | 99.9% |
| Wafermxfp4 | $0.038 | $0.500 | 1.0M | - | 100.0% |
| Relace | $0.070 | $0.500 | 1.0M | - | 100.0% |
| Decartfp4 | $0.103 | $0.414 | 1.0M | - | 92.0% |
| Reka | $0.060 | $0.600 | 1.0M | - | 94.4% |
| InferenceNetfp8 | $0.080 | $0.550 | 1.0M | - | 100.0% |
| Cloudflare | $0.100 | $0.600 | 1.0M | - | 100.0% |
| Ionstream | $0.150 | $0.450 | 1.0M | - | 100.0% |
| StreamLakefp8 | $0.150 | $0.600 | 1.0M | - | 100.0% |
| DeepSeek | $0.150 | $0.600 | 1.0M | - | 100.0% |
| Baidufp8 | $0.150 | $0.605 | 1.0M | - | 100.0% |
| Alibaba | $0.165 | $0.660 | 1M | - | 94.4% |
| ModelRunfp4 | $0.170 | $0.670 | 1.0M | - | 99.6% |
| Cohere | $0.195 | $0.660 | 1.0M | - | 100.0% |
| DigitalOcean | $0.180 | $0.720 | 1.0M | - | 100.0% |
| GMICloudfp8 | $0.180 | $0.720 | 1.0M | - | 99.9% |
| AtlasCloudfp8 | $0.195 | $0.780 | 1.0M | - | 98.4% |
| Novitafp8 | $0.195 | $0.780 | 1.0M | - | 100.0% |
| Fireworks | $0.210 | $0.840 | 1.0M | - | 100.0% |
| Makorafp8 | $0.150 | $1.20 | 1.0M | - | 99.9% |
| Particle AI | $0.250 | $1.00 | 1.0M | - | 100.0% |
| Modal | $0.250 | $1.00 | 1.0M | - | 100.0% |
| OpenInferencefp4 | $0.037 | $1.64 | 1.0M | - | 100.0% |
| Phala | $0.200 | $1.20 | 1.0M | - | 94.6% |
| Crusoefp8 | $0.290 | $1.20 | 1.0M | - | 100.0% |
| Venicefp8 | $0.300 | $1.20 | 1M | - | 100.0% |
| Mistralfp8 | $0.300 | $1.20 | 1.0M | - | 97.9% |
| Nebiusfp8 | $0.300 | $1.20 | 1.0M | - | 100.0% |
| SiliconFlowfp8 | $0.300 | $1.20 | 1.0M | - | 99.9% |
| Together | $0.300 | $1.20 | 1.0M | - | 100.0% |
| PrimeIntellect | $0.300 | $1.20 | 1.0M | - | 100.0% |
| BaseTen | $0.300 | $1.20 | 1.0M | - | 100.0% |
| Parasailfp8 | $0.300 | $1.20 | 1.0M | - | 100.0% |
The spread between Sail Research and Parasail is 4.6× for identical weights. Quantization and context limits differ, so check both columns before switching.
About DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...
Specifications
| Model ID | deepseek/deepseek-v4.1-flash-1017 |
|---|---|
| Provider | DeepSeek |
| Context window | 1.0M tokens |
| Max output | 393K tokens |
| Input modalities | text, image |
| Output modalities | text |
| Knowledge cutoff | - |
| Open weights | Yes - deepseek-ai/DeepSeek-V4.1-Flash-1017 |
| Released | October 17, 2026 |
Cheaper alternatives
Models that cost less than DeepSeek V4.1 Flash 1017 while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does DeepSeek: DeepSeek V4.1 Flash 1017 cost?
$0.150 per million input tokens and $0.600 per million output tokens. Cached input reads cost $0.0030 per million tokens.
What is the context window of DeepSeek: DeepSeek V4.1 Flash 1017?
1.0M tokens, with up to 393K tokens of output per request.
Which provider serves DeepSeek: DeepSeek V4.1 Flash 1017 cheapest?
Sail Research at $0.101 per million input tokens - 4.6× cheaper than Parasail, the most expensive of the 35 hosts serving it.
Confirm against the source: DeepSeek official pricing.