DeepSeek V4.1 Flash 1017 pricing & benchmarks
DeepSeek V4.1 Flash 1017 is available from DeepSeek at $0.300 per million input tokens and $1.20 per million output tokens ($0.525 blended at 3:1). It accepts up to 1,048,576 tokens of context. 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...
Pricing
Per million tokens · OpenRouter
Input$0.300
Output$1.20
Blended (3:1)$0.525
Specification
deepseek/deepseek-v4.1-flash-1017
Context window1.0M
Max output393K
ReleasedOct 2026
LicenceOpen weights
Modalitiesin:text, in:image, out:text
No independently-run benchmark scores are published for DeepSeek V4.1 Flash 1017 yet. We show nothing rather than reprinting an unverified figure.
Where to run DeepSeek V4.1 Flash 1017
29 options across 25 providers · 7.1× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| OpenInference | $0.081 | $0.025 / $0.250 | 1.0M | fp4 | 97.2% |
| Relace | $0.081 | $0.025 / $0.250 | 1.0M | — | 100.0% |
| Decart | $0.113 | $0.090 / $0.180 | 1.0M | fp4 | 100.0% |
| Sail Research (fp4/us) | $0.113 | $0.101 / $0.150 | 1.0M | fp4 | 100.0% |
| Sail Research | $0.113 | $0.101 / $0.150 | 1.0M | fp4 | 99.8% |
| DeepInfra (fp8/flex) | $0.118 | $0.078 / $0.235 | 1.0M | fp8 | 77.1% |
| DeepInfra | $0.147 | $0.098 / $0.294 | 1.0M | fp8 | 100.0% |
| InferenceNet (us) | $0.185 | $0.080 / $0.500 | 1.0M | fp8 | 100.0% |
| InferenceNet | $0.185 | $0.080 / $0.500 | 1.0M | fp8 | 100.0% |
| DeepInfra (fp8/priority) | $0.221 | $0.147 / $0.441 | 1.0M | fp8 | 100.0% |
| Cloudflare | $0.225 | $0.100 / $0.600 | 1.0M | — | 100.0% |
| Wafer | $0.245 | $0.160 / $0.500 | 1.0M | mxfp4 | 100.0% |
| Reka | $0.262 | $0.150 / $0.600 | 1.0M | — | 99.5% |
| Ionstream | $0.315 | $0.220 / $0.600 | 1.0M | — | 99.9% |
| Morph | $0.340 | $0.253 / $0.600 | 1.0M | fp8 | 99.9% |
| AtlasCloud | $0.341 | $0.195 / $0.780 | 1.0M | fp8 | 100.0% |
| Crusoe | $0.517 | $0.290 / $1.20 | 1.0M | fp8 | 100.0% |
| Makora | $0.525 | $0.300 / $1.20 | 1.0M | fp8 | 99.8% |
| Phala | $0.525 | $0.300 / $1.20 | 1.0M | — | 97.6% |
| SiliconFlow | $0.525 | $0.300 / $1.20 | 1.0M | fp8 | 97.1% |
| GMICloud | $0.525 | $0.300 / $1.20 | 1.0M | fp8 | 99.8% |
| Novita | $0.525 | $0.300 / $1.20 | 1.0M | fp8 | 100.0% |
| Together | $0.525 | $0.300 / $1.20 | 1.0M | — | 99.9% |
| Fireworks | $0.525 | $0.300 / $1.20 | 1.0M | — | 100.0% |
| PrimeIntellect | $0.525 | $0.300 / $1.20 | 1.0M | — | 99.9% |
| BaseTen | $0.525 | $0.300 / $1.20 | 1.0M | — | 100.0% |
| Parasail | $0.525 | $0.300 / $1.20 | 1.0M | fp8 | 100.0% |
| DeepSeek | $0.525 | $0.300 / $1.20 | 1.0M | — | 100.0% |
| Alibaba | $0.578 | $0.330 / $1.32 | 1M | — | 99.7% |
Host prices and uptime from OpenRouter, synced 2026-10-22. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 vs Gemini 3.7 Flash
DeepSeek V4.1 Flash 1017 vs Grok 4.6
DeepSeek V4.1 Flash 1017 vs Inkling Small
DeepSeek V4.1 Flash 1017 vs Qwen3.7 Flash
DeepSeek V4.1 Flash 1017 vs Claude Opus 5
DeepSeek V4.1 Flash 1017 vs Gemini 3.6 Flash
DeepSeek V4.1 Flash 1017 vs Gemini 3.5 Flash Lite
DeepSeek V4.1 Flash 1017 vs Inkling
FAQ
How much does DeepSeek V4.1 Flash 1017 cost?
DeepSeek V4.1 Flash 1017 costs $0.300 per million input tokens and $1.20 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.525 per million tokens.
What is DeepSeek V4.1 Flash 1017's context window?
DeepSeek V4.1 Flash 1017 accepts up to 1,048,576 tokens of context, and can generate up to 393,216 output tokens.