per 1M tokens
DeepSeek: DeepSeek V4.1 Flash 1017
deepseek/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...
Price
per 1M tokens
Cheaper on Sail Research (−78.4%) versus the lab price
Providers
Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.
| Provider | Tag | Quant | Input | Output | Context | Uptime | Status | Source |
|---|---|---|---|---|---|---|---|---|
| Sail Research | sail-research/fp4 | fp4 | $0.101/1M | $0.15/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Sail Research | sail-research/fp4/us | fp4 | $0.101/1M | $0.15/1M | 1.0M | 100% | Live | openrouter-endpoints |
| DeepInfra Price differs from the host list |
deepinfra/fp8/flex | fp8 | $0.0784/1M | $0.2352/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Morph | morph/fp8 | fp8 | $0.044/1M | $0.383/1M | 1.0M | 100% | Live | openrouter-endpoints |
| DeepInfra Price differs from the host list |
deepinfra/fp8 | fp8 | $0.098/1M | $0.294/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Wafer | wafer/us | mxfp4 | $0.038/1M | $0.5/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Wafer | wafer/mxfp4 | mxfp4 | $0.066/1M | $0.5/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Relace | relace | — | $0.07/1M | $0.5/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Reka | reka | — | $0.06/1M | $0.6/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Inference.net Price differs from the host list |
inference-net/fp8 | fp8 | $0.08/1M | $0.55/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Inference.net Price differs from the host list |
inference-net/us | fp8 | $0.08/1M | $0.55/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Decart | decart/fp4 | fp4 | $0.123/1M | $0.492/1M | 1.0M | 100% | Live | openrouter-endpoints |
| DeepInfra Price differs from the host list |
deepinfra/fp8/priority | fp8 | $0.147/1M | $0.441/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Cloudflare Price differs from the host list |
cloudflare | — | $0.1/1M | $0.6/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Ionstream | ionstream | — | $0.165/1M | $0.495/1M | 1.0M | 100% | Live | openrouter-endpoints |
| StreamLake | streamlake/fp8 | fp8 | $0.15/1M | $0.6/1M | 1.0M | 100% | Live | openrouter-endpoints |
| ModelRun | modelrun/fp4 | fp4 | $0.17/1M | $0.67/1M | 1.0M | — | Live | openrouter-endpoints |
| DeepInfra Price differs from OpenRouter |
— | — | $0.2/1M | $0.6/1M | 1.0M | — | Listed | deepinfra |
| OpenInference | open-inference/fp4 | fp4 | $0.0339/1M | $1.14/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Cohere | cohere | — | $0.195/1M | $0.66/1M | 1.0M | 100% | Live | openrouter-endpoints |
| DigitalOcean | digitalocean | — | $0.18/1M | $0.72/1M | 1.0M | 100% | Live | openrouter-endpoints |
| GMICloud | gmicloud/fp8 | fp8 | $0.18/1M | $0.72/1M | 1.0M | 100% | Live | openrouter-endpoints |
| AtlasCloud Price differs from the host list |
atlas-cloud/fp8 | fp8 | $0.195/1M | $0.78/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Novita Price differs from the host list |
novita/fp8 | fp8 | $0.195/1M | $0.78/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Makora | makora/fp8 | fp8 | $0.15/1M | $1.2/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Modal | modal | — | $0.25/1M | $1/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Particle AI | particle-ai | — | $0.25/1M | $1/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Phala Price differs from the host list |
phala | — | $0.2/1M | $1.2/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Inference.net Price differs from OpenRouter |
— | — | $0.3/1M | $1/1M | 1.0M | — | Listed | inferencenet |
| Baidu | baidu/fp8 | fp8 | $0.28/1M | $1.13/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Crusoe | crusoe/fp8 | fp8 | $0.29/1M | $1.2/1M | 1.0M | 100% | Live | openrouter-endpoints |
| AtlasCloud Price differs from OpenRouter |
— | fp8 | $0.3/1M | $1.2/1M | 1.0M | — | Listed | atlascloud |
| BaseTen | baseten | — | $0.3/1M | $1.2/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Cloudflare Price differs from OpenRouter |
— | — | $0.3/1M | $1.2/1M | — | — | Listed | cloudflare-pricing |
| DeepSeek | deepseek | — | $0.3/1M | $1.2/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Mistral AI | mistral/fp8 | fp8 | $0.3/1M | $1.2/1M | 1.0M | 100% | Live | openrouter-endpoints |
| NEAR AI | — | — | $0.3/1M | $1.2/1M | 1.0M | — | Listed | nearai |
| Nebius | nebius/fp8 | fp8 | $0.3/1M | $1.2/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Novita Price differs from OpenRouter |
— | — | $0.3/1M | $1.2/1M | 1.0M | — | Listed | novita |
| Parasail | parasail/fp8 | fp8 | $0.3/1M | $1.2/1M | 1.0M | 100% | Live | openrouter-endpoints |
| PrimeIntellect | primeintellect | — | $0.3/1M | $1.2/1M | 1.0M | 100% | Live | openrouter-endpoints |
| SiliconFlow | siliconflow/fp8 | fp8 | $0.3/1M | $1.2/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Together | — | — | $0.3/1M | $1.2/1M | 1.0M | — | Listed | together |
| Together | together | — | $0.3/1M | $1.2/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Venice | venice/fp8 | fp8 | $0.3/1M | $1.2/1M | 1M | 100% | Live | openrouter-endpoints |
| Alibaba | alibaba | — | $0.33/1M | $1.32/1M | 1M | 100% | Live | openrouter-endpoints |
| Fireworks | fireworks/us | — | $0.45/1M | $1.8/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Phala Price differs from OpenRouter |
— | — | $0.75/1M | $1.6/1M | 1.0M | — | Listed | phala |
| Chutes | — | — | Not published— | Not published— | — | — | Listed | chutes |
| Fireworks | fireworks/spot | — | $0.21/1M | $0.84/1M | 1.0M | 59% | Down | openrouter-endpoints |
| Fireworks | fireworks | — | $0.3/1M | $1.2/1M | 1.0M | 77% | Down | openrouter-endpoints |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$1.50 at list price for this workload
Cache
per 1M tokens
Tiers
- Tier
- in $0.15 · out $0.6 · cache read $0.003
- Tier
- in $0.15 · out $0.6 · cache read $0.003
- Tier
- in $0.3 · out $1.2 · cache read $0.006
- Tier
- in $0.15 · out $0.6 · cache read $0.003
- Tier
- in $0.3 · out $1.2 · cache read $0.006
- Tier
- in $0.15 · out $0.6 · cache read $0.003
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.3/1M | $1.2/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-10-17 | token | $0.15 | $0.6 | Not published— |
| 2026-10-18 | token | $0.15 | $0.6 | Not published— |
| 2026-10-19 | token | $0.15 | $0.6 | Not published— |
| 2026-10-20 | token | $0.15 | $0.6 | Not published— |
| 2026-10-21 | token | $0.15 | $0.6 | Not published— |
| 2026-10-22 | token | $0.15 | $0.6 | Not published— |
| 2026-10-23 | token | $0.15 | $0.6 | Not published— |
| 2026-10-24 | token | $0.15 | $0.6 | Not published— |
| 2026-10-25 | token | $0.15 | $0.6 | Not published— |
| 2026-10-26 | token | $0.15 | $0.6 | Not published— |
| 2026-10-27 | token | $0.15 | $0.6 | Not published— |
| 2026-10-28 | token | $0.15 | $0.6 | Not published— |
| 2026-10-29 | token | $0.15 | $0.6 | Not published— |
| 2026-10-30 | token | $0.3 | $1.2 | Not published— |
Alternatives
- @cf/deepseek-ai/deepseek-v4.1-flash-1017$0.3/1M · Compare
- @cf/moondream/moondream3.1-9B-A2B$0.3/1M · Compare
- Amazon: Nova 2 Lite$0.3/1M · Compare
- Cohere: Command A+$0.3/1M · Compare
- DeepSeek V4.1 Flash$0.3/1M · Compare
- DeepSeek V4.1 Flash$0.3/1M · Compare
Parameters (22)
Call this model
OpenRouter id deepseek/deepseek-v4.1-flash-1017. InferenceList does not send the request.
curl
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek/deepseek-v4.1-flash-1017","messages":[{"role":"user","content":"Hello"}]}'
JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "deepseek/deepseek-v4.1-flash-1017",
messages: [{ role: "user", content: "Hello" }],
}),
});
Python
import os, json, urllib.request
req = urllib.request.Request(
"https://openrouter.ai/api/v1/chat/completions",
data=json.dumps({"model": "deepseek/deepseek-v4.1-flash-1017", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())