per 1M tokens
DeepSeek: DeepSeek V4 Pro 0423
deepseek/deepseek-v4-pro
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
Price
per 1M tokens
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 | $0.8162/1M | $1.632/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Relace | relace/fp4 | fp4 | $0.9/1M | $1.5/1M | 1.0M | 100% | Live | openrouter-endpoints |
| GMICloud | gmicloud/fp8 | fp8 | $0.957/1M | $1.914/1M | 1.0M | 100% | Live | openrouter-endpoints |
| DigitalOcean | digitalocean | — | $1.044/1M | $2.088/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Cloudflare | cloudflare | — | $1.15/1M | $2.55/1M | 1.0M | 100% | Live | openrouter-endpoints |
| SiliconFlow | siliconflow/fp8 | fp8 | $1/1M | $3.135/1M | 1.0M | 100% | Live | openrouter-endpoints |
| DeepInfra | — | — | $1.3/1M | $2.6/1M | 1.0M | — | Listed | deepinfra |
| DeepInfra | deepinfra/fp8 | fp8 | $1.3/1M | $2.6/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Alibaba | alibaba/fp8 | fp8 | $1.416/1M | $2.832/1M | 1M | 100% | Live | openrouter-endpoints |
| Io Net | — | — | $1.49/1M | $2.922/1M | 1.0M | — | Listed | ionet |
| Alibaba | alibaba/fp8/us-east-1 | fp8 | $1.56/1M | $3.12/1M | 1M | 100% | Live | openrouter-endpoints |
| Novita | — | — | $1.6/1M | $3.2/1M | 1.0M | — | Listed | novita |
| Novita | novita/fp8 | fp8 | $1.6/1M | $3.2/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Venice | — | — | $1.65/1M | $3.301/1M | 1M | — | Listed | venice |
| Venice | venice | — | $1.65/1M | $3.301/1M | 1M | 100% | Live | openrouter-endpoints |
| AtlasCloud | — | fp4 | $1.68/1M | $3.38/1M | 1.0M | — | Listed | atlascloud |
| AtlasCloud | atlas-cloud/fp4 | fp4 | $1.68/1M | $3.38/1M | 1.0M | 96% | Live | openrouter-endpoints |
| Baidu | baidu/fp8 | fp8 | $1.69/1M | $3.38/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Crusoe | crusoe/fp8 | fp8 | $1.74/1M | $3.48/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Azure | azure/us | — | $1.91/1M | $3.83/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Inference.net | — | — | $2.1/1M | $4.2/1M | 1.0M | — | Listed | inferencenet |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$2.45 at list price for this workload
Cache
per 1M tokens
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.8162/1M | $1.632/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-09-14 | token | $0.66 | $1.98 | Not published— |
| 2026-09-15 | token | $1.6 | $3.2 | Not published— |
| 2026-09-16 | token | $1.6 | $3.2 | Not published— |
| 2026-09-17 | token | $1.6 | $3.2 | Not published— |
| 2026-09-18 | token | $1.6 | $3.2 | Not published— |
| 2026-09-19 | token | $0.4223 | $0.8446 | Not published— |
| 2026-09-20 | token | $0.4223 | $0.8446 | Not published— |
| 2026-09-21 | token | $0.9245 | $1.849 | Not published— |
| 2026-09-22 | token | $0.9074 | $1.815 | Not published— |
| 2026-09-23 | token | $0.9481 | $1.896 | Not published— |
| 2026-09-24 | token | $0.8956 | $1.791 | Not published— |
| 2026-09-25 | token | $0.6622 | $1.324 | Not published— |
| 2026-09-26 | token | $0.348 | $0.696 | Not published— |
| 2026-09-27 | token | $0.348 | $0.696 | Not published— |
| 2026-09-28 | token | $0.783 | $1.566 | Not published— |
| 2026-09-29 | token | $0.9278 | $1.856 | Not published— |
| 2026-09-30 | token | $0.783 | $1.566 | Not published— |
| 2026-10-01 | token | $0.2088 | $0.4176 | Not published— |
| 2026-10-02 | token | $0.2088 | $0.4176 | Not published— |
| 2026-10-03 | token | $0.2088 | $0.4176 | Not published— |
| 2026-10-04 | token | $0.2088 | $0.4176 | Not published— |
| 2026-10-05 | token | $0.2088 | $0.4176 | Not published— |
| 2026-10-06 | token | $0.2088 | $0.4176 | Not published— |
| 2026-10-07 | token | $0.2088 | $0.4176 | Not published— |
| 2026-10-08 | token | $0.2873 | $0.5745 | Not published— |
| 2026-10-09 | token | $0.2088 | $0.4176 | Not published— |
| 2026-10-10 | token | $0.2088 | $0.4176 | Not published— |
| 2026-10-11 | token | $0.2088 | $0.4176 | Not published— |
| 2026-10-12 | token | $0.4124 | $0.8248 | Not published— |
| 2026-10-13 | token | $0.4343 | $0.8686 | Not published— |
| 2026-10-14 | token | $0.3988 | $0.7976 | Not published— |
| 2026-10-15 | token | $0.4039 | $0.8077 | Not published— |
| 2026-10-16 | token | $0.2972 | $0.5944 | Not published— |
| 2026-10-17 | token | $0.2088 | $0.4176 | Not published— |
| 2026-10-18 | token | $0.2088 | $0.4176 | Not published— |
| 2026-10-19 | token | $0.4039 | $0.8077 | Not published— |
| 2026-10-20 | token | $0.3835 | $0.767 | Not published— |
| 2026-10-21 | token | $0.419 | $0.838 | Not published— |
| 2026-10-22 | token | $0.4427 | $0.8853 | Not published— |
| 2026-10-23 | token | $0.8244 | $1.649 | Not published— |
| 2026-10-24 | token | $0.2088 | $0.4176 | Not published— |
| 2026-10-25 | token | $0.2088 | $0.4176 | Not published— |
| 2026-10-26 | token | $0.752 | $1.504 | Not published— |
| 2026-10-27 | token | $0.8804 | $1.761 | Not published— |
| 2026-10-28 | token | $0.889 | $1.778 | Not published— |
| 2026-10-29 | token | $0.8653 | $1.731 | Not published— |
| 2026-10-30 | token | $0.8162 | $1.632 | Not published— |
Alternatives
- Kimi K2.6$0.81/1M · Compare
- Google: Gemini 3.8 Flash$0.825/1M · Compare
- Macaron V1 Venti$0.825/1M · Compare
- MoonshotAI: Kimi K2.7 Code$0.802/1M · Compare
- AionLabs: Aion-2.0$0.8/1M · Compare
- AionLabs: Aion-RP 1.0 (8B)$0.8/1M · Compare
Parameters (21)
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Call this model
OpenRouter id deepseek/deepseek-v4-pro. 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-pro","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-pro",
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-pro", "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())