per 1M tokens
DeepSeek: DeepSeek V4 Flash 0423
deepseek/deepseek-v4-flash
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
Price
per 1M tokens
Cheaper on StreamLake (−9.2%) versus the OpenRouter list 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 |
|---|---|---|---|---|---|---|---|---|
| StreamLake | streamlake/fp8 | fp8 | $0.0826/1M | $0.1652/1M | 1.0M | 100% | Live | openrouter-endpoints |
| DeepInfra | — | — | $0.09/1M | $0.18/1M | 1.0M | — | Listed | deepinfra |
| DeepInfra | deepinfra/fp8 | fp8 | $0.09/1M | $0.18/1M | 1.0M | 100% | Live | openrouter-endpoints |
| GMICloud | gmicloud/fp8 | fp8 | $0.091/1M | $0.182/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Venice Price differs from the host list |
venice | — | $0.0966/1M | $0.1925/1M | 1M | 100% | Live | openrouter-endpoints |
| DigitalOcean | digitalocean | — | $0.098/1M | $0.196/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Relace | relace/fp4 | fp4 | $0.05/1M | $0.45/1M | 1.0M | 100% | Live | openrouter-endpoints |
| SiliconFlow | siliconflow/fp8 | fp8 | $0.13/1M | $0.28/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Venice Price differs from OpenRouter |
— | — | $0.138/1M | $0.275/1M | 1M | — | Listed | venice |
| AtlasCloud | — | fp4 | $0.14/1M | $0.28/1M | 1.0M | — | Listed | atlascloud |
| AtlasCloud | atlas-cloud/fp4 | fp4 | $0.14/1M | $0.28/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Baidu | baidu/fp8 | fp8 | $0.14/1M | $0.28/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Crusoe | crusoe/fp8 | fp8 | $0.14/1M | $0.28/1M | 1.0M | — | Live | openrouter-endpoints |
| Parasail | parasail/fp8 | fp8 | $0.14/1M | $0.28/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Mancer 2 | mancer/fp8 | fp8 | $0.19/1M | $0.5/1M | 1.0M | 93% | Live | openrouter-endpoints |
| Azure | azure/us | — | $0.21/1M | $0.56/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Inference.net | — | — | $0.23/1M | $0.62/1M | 1M | — | Listed | inferencenet |
| Io Net | — | fp8 | $0.308/1M | $0.526/1M | 33K | — | Listed | ionet |
| Wafer | wafer/mxfp4 | mxfp4 | $0.6/1M | $0.17/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Cloudflare | cloudflare | — | $0.44/1M | $1.32/1M | 384K | 90% | Live | openrouter-endpoints |
| Fireworks | fireworks | — | $0.105/1M | $0.21/1M | 1.0M | 60% | Down | openrouter-endpoints |
| Alibaba | alibaba/fp8/us-east-1 | fp8 | $0.15/1M | $0.3/1M | 1M | 23% | Down | openrouter-endpoints |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$0.27 at list price for this workload
Cache
per 1M tokens
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.091/1M | $0.182/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-09-14 | token | $0.14 | $0.28 | Not published— |
| 2026-09-15 | token | $0.084 | $0.168 | Not published— |
| 2026-09-16 | token | $0.0855 | $0.1711 | Not published— |
| 2026-09-17 | token | $0.07 | $0.14 | Not published— |
| 2026-09-18 | token | $0.0496 | $0.0991 | Not published— |
| 2026-09-19 | token | $0.0409 | $0.0818 | Not published— |
| 2026-09-20 | token | $0.0356 | $0.0711 | Not published— |
| 2026-09-21 | token | $0.0554 | $0.1109 | Not published— |
| 2026-09-22 | token | $0.049 | $0.098 | Not published— |
| 2026-09-23 | token | $0.0825 | $0.1649 | Not published— |
| 2026-09-24 | token | $0.0778 | $0.1557 | Not published— |
| 2026-09-25 | token | $0.047 | $0.0941 | Not published— |
| 2026-09-26 | token | $0.047 | $0.0941 | Not published— |
| 2026-09-27 | token | $0.0469 | $0.0938 | Not published— |
| 2026-09-28 | token | $0.0638 | $0.1277 | Not published— |
| 2026-09-29 | token | $0.0763 | $0.1526 | Not published— |
| 2026-09-30 | token | $0.0785 | $0.1571 | Not published— |
| 2026-10-01 | token | $0.0419 | $0.0837 | Not published— |
| 2026-10-02 | token | $0.028 | $0.056 | Not published— |
| 2026-10-03 | token | $0.028 | $0.056 | Not published— |
| 2026-10-04 | token | $0.0224 | $1.28 | Not published— |
| 2026-10-05 | token | $0.03 | $1.28 | Not published— |
| 2026-10-06 | token | $0.0009 | $1.28 | Not published— |
| 2026-10-07 | token | $0.03 | $1.28 | Not published— |
| 2026-10-08 | token | $0.0075 | $1.28 | Not published— |
| 2026-10-09 | token | $0.0173 | $1.28 | Not published— |
| 2026-10-10 | token | $0.03 | $1.28 | Not published— |
| 2026-10-11 | token | $0.03 | $1.28 | Not published— |
| 2026-10-12 | token | $0.03 | $1.28 | Not published— |
| 2026-10-13 | token | $0.091 | $0.182 | Not published— |
| 2026-10-14 | token | $0.091 | $0.182 | Not published— |
| 2026-10-15 | token | $0.091 | $0.182 | Not published— |
| 2026-10-16 | token | $0.091 | $0.182 | Not published— |
| 2026-10-17 | token | $0.091 | $0.182 | Not published— |
| 2026-10-18 | token | $0.091 | $0.182 | Not published— |
| 2026-10-19 | token | $0.091 | $0.182 | Not published— |
| 2026-10-20 | token | $0.091 | $0.182 | Not published— |
| 2026-10-21 | token | $0.091 | $0.182 | Not published— |
| 2026-10-22 | token | $0.091 | $0.182 | Not published— |
| 2026-10-23 | token | $0.091 | $0.182 | Not published— |
| 2026-10-24 | token | $0.091 | $0.182 | Not published— |
| 2026-10-25 | token | $0.091 | $0.182 | Not published— |
| 2026-10-26 | token | $0.091 | $0.182 | Not published— |
| 2026-10-27 | token | $0.0473 | $0.0946 | Not published— |
| 2026-10-28 | token | $0.091 | $0.182 | Not published— |
| 2026-10-29 | token | $0.091 | $0.182 | Not published— |
| 2026-10-30 | token | $0.091 | $0.182 | Not published— |
Alternatives
- deepseek-ai/DeepSeek-V4-Flash$0.09/1M · Compare
- Gemma 3 12B$0.09/1M · Compare
- Gemma 3 12B$0.09/1M · Compare
- gemma-3-27b-it$0.09/1M · Compare
- google/gemma-4-31B-it-turbo$0.09/1M · Compare
- gpt-oss-120b$0.09/1M · Compare
Parameters (22)
Call this model
OpenRouter id deepseek/deepseek-v4-flash. 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-flash","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-flash",
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-flash", "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())