DeepSeek · Listed Oct 17, 2026 · 8 providers
DeepSeek V4.1 Flash 1017
Tool UseReasoningCachingStructured Output
Official pricing
$0.15 / $0.60
Input / Output · DeepSeek
Lowest input
$0.08
InferenceNet
Context
1M
Off-peak$0.003
Peak$0.006
DeepSeek V4.1 Flash 1017 · Published pricing
| Period | Input / 1M | Cache read / 1M | Output / 1M |
|---|---|---|---|
| Off-peak | $0.15 | $0.003 | $0.60 |
| Peak | $0.30 | $0.006 | $1.20 |
DeepSeek V4.1 Flash 1017 · Specifications
| Field | Official API |
|---|---|
| Snapshot | DeepSeek-V4.1-Flash-1017 · October 17, 2026 |
| API alias | deepseek-flash |
| Context / maximum output | 1M / 384K tokens |
| Input | Text and images |
| Features | JSON output, tool calls, Responses API, Anthropic API |
| Weights / license | Open weights · MIT |
| Item | Value |
|---|---|
| Backbone parameters | 552B; additional Engram memory is separate |
| Active parameters per token | 8B prefill / 16B decode |
| Engram conditional memory | 196B, sparsely accessed through token-based lookup |
| Weights / license | Open weights / MIT; commercial use allowed with notices |
| Official checkpoint | deepseek-ai/DeepSeek-V4.1-Flash-1017 |
DeepSeek V4.1 Flash 1017 · Weight license
| Model weights | License |
|---|---|
| Open weights | MIT |
DeepSeek V4.1 Flash 1017 · Peer comparison
| Provider | Input / 1M | Output / 1M | Cache read / 1M | Scope |
|---|---|---|---|---|
| DeepSeek | $0.15 | $0.60 | $0.003 | Publisher endpoint via OpenRouter; direct API peak schedule is separate |
| inference.net | $0.10 | $0.50 | $0.002 | Hosted endpoint; not the DeepSeek official tariff |
| DeepInfra | $0.14 | $0.42 | $0.0042 | Listed 30% promotional discount; regular $0.20 / $0.60 / $0.006 |
DeepSeek V4.1 Flash 1017 · Cost examples
| Input type | Off-peak total | Peak total |
|---|---|---|
| Uncached input | $0.21 | $0.42 |
| All input cached | $0.063 | $0.126 |
DeepSeek V4.1 Flash 1017 · Benchmarks
| Evaluated model | Rating | Score interval | Overall rank | Open model rank | Votes | Overall rank spread |
|---|---|---|---|---|---|---|
| DeepSeek-V4.1-Flash-20261017 (Max) | 1670 | 1653–1687 | 12 / 146 | 1 | 1,417 | 7–16 |
Cache and processing modes
Peak hours are Monday–Friday 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays.
Dated prices
DeepSeek V4.1 Flash 1017 keeps the previous API token prices.
Compare provider pricing
Compare provider pricing per 1 million tokens: input on the horizontal axis and output on the vertical axis. Dashed lines show official pricing. A point down and to the left is cheaper on both.
Base pricing
8Newest pricing check Oct 18, 2026.
Questions about DeepSeek V4.1 Flash 1017 pricing
It is the October 17, 2026 snapshot replacing the September 10 version. DeepSeek kept the deepseek-flash API alias and token prices unchanged.
Per million tokens, official off-peak prices are $0.15 uncached input, $0.003 cache hits and $0.60 output. Peak prices are $0.30, $0.006 and $1.20. Peak hours are Monday–Friday 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays.
No. DeepSeek lists 1M context and up to 384K output on its API. Hosted endpoints can publish different output limits and tariffs. Check the selected provider instead of applying the publisher limit to every channel.
DeepSeek publishes the 1017 model weights on Hugging Face under the MIT license. Self-hosting hardware and running costs are separate from hosted API token prices.
One million uncached input tokens plus 100,000 output tokens cost $0.21 off-peak or $0.42 at peak using the official tariff. These are arithmetic examples; token use, cache eligibility and provider-specific rates change the actual bill.