per 1M tokens
DeepSeek: DeepSeek V4 Pro 0813
deepseek/deepseek-v4-pro-0813
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
Price
per 1M tokens
Cheaper on Sail Research (−59.3%) 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 | $0.675/1M | $1.2/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Sail Research | sail-research/us | fp4 | $0.675/1M | $1.2/1M | 1.0M | 100% | Live | openrouter-endpoints |
| StreamLake | streamlake | — | $0.66/1M | $1.98/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Ionstream | ionstream | — | $0.37/1M | $2.93/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Relace | relace/fp4 | fp4 | $0.1035/1M | $4/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Wafer | wafer/us | mxfp4 | $0.115/1M | $4.3/1M | 1.0M | 96% | Live | openrouter-endpoints |
| Wafer | wafer/mxfp4 | mxfp4 | $0.285/1M | $4.3/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Novita Price differs from the host list |
novita/fp8 | fp8 | $0.99/1M | $2.97/1M | 1.0M | 100% | Live | openrouter-endpoints |
| GMICloud | gmicloud/fp8 | fp8 | $1.056/1M | $3.168/1M | 1.0M | 100% | Live | openrouter-endpoints |
| DekaLLM | dekallm | — | $0.88/1M | $3.8/1M | 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 |
| Io Net | — | fp8 | $1.079/1M | $4.028/1M | 1.0M | — | Listed | ionet |
| CoreWeave | coreweave/fp8 | fp8 | $1.31/1M | $3.96/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Alibaba | alibaba/us-east-1 | — | $1.32/1M | $3.96/1M | 1M | 100% | Live | openrouter-endpoints |
| AtlasCloud | — | fp8 | $1.32/1M | $3.96/1M | 1.0M | — | Listed | atlascloud |
| AtlasCloud | atlas-cloud/fp8 | fp8 | $1.32/1M | $3.96/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Baidu | baidu/fp8 | fp8 | $1.32/1M | $3.96/1M | 1.0M | 100% | Live | openrouter-endpoints |
| BaseTen | baseten/fp4 | fp4 | $1.32/1M | $3.96/1M | 1.0M | — | Live | openrouter-endpoints |
| Cloudflare | — | — | $1.32/1M | $3.96/1M | — | — | Listed | cloudflare-pricing |
| Cloudflare | cloudflare | — | $1.32/1M | $3.96/1M | 1.0M | 100% | Live | openrouter-endpoints |
| DeepSeek | deepseek | — | $1.32/1M | $3.96/1M | 1.0M | 100% | Live | openrouter-endpoints |
| DigitalOcean | digitalocean | — | $1.32/1M | $3.96/1M | 1.0M | — | Live | openrouter-endpoints |
| Inference.net | — | — | $1.32/1M | $3.96/1M | 1.0M | — | Listed | inferencenet |
| Nebius | nebius/fp8 | fp8 | $1.32/1M | $3.96/1M | 979K | 100% | Live | openrouter-endpoints |
| Novita Price differs from OpenRouter |
— | — | $1.32/1M | $3.96/1M | 1.0M | — | Listed | novita |
| Parasail | parasail/fp8 | fp8 | $1.32/1M | $3.96/1M | 1.0M | 93% | Live | openrouter-endpoints |
| SiliconFlow | siliconflow/fp8 | fp8 | $1.32/1M | $3.96/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Together | — | — | $1.32/1M | $3.96/1M | 1.0M | — | Listed | together |
| Together | together | — | $1.32/1M | $3.96/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Phala | — | — | $1.45/1M | $4.36/1M | 1.0M | — | Listed | phala |
| Phala | phala | — | $1.45/1M | $4.36/1M | 1.0M | — | Live | openrouter-endpoints |
| Venice | — | — | $1.65/1M | $4.95/1M | 1M | — | Listed | venice |
| Venice | venice | — | $1.65/1M | $4.95/1M | 1M | — | Live | openrouter-endpoints |
| Chutes | — | — | Not published— | Not published— | — | — | Listed | chutes |
| Alibaba | alibaba | — | $1.122/1M | $3.366/1M | 1M | 100% | Down | openrouter-endpoints |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$5.28 at list price for this workload
Cache
per 1M tokens
Tiers
- Tier
- in $0.66 · out $1.98 · cache read $0.022
- Tier
- in $0.66 · out $1.98 · cache read $0.022
- Tier
- in $1.32 · out $3.96 · cache read $0.044
- Tier
- in $0.66 · out $1.98 · cache read $0.022
- Tier
- in $1.32 · out $3.96 · cache read $0.044
- Tier
- in $0.66 · out $1.98 · cache read $0.022
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $1.32/1M | $3.96/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-09-15 | token | $0.5795 | $1.738 | Not published— |
| 2026-09-16 | token | $0.5795 | $1.738 | Not published— |
| 2026-09-17 | token | $0.5795 | $1.738 | Not published— |
| 2026-09-18 | token | $0.5782 | $1.734 | Not published— |
| 2026-09-19 | token | $0.5782 | $1.734 | Not published— |
| 2026-09-20 | token | $0.5346 | $1.604 | Not published— |
| 2026-09-21 | token | $0.5676 | $1.703 | Not published— |
| 2026-09-22 | token | $0.66 | $1.98 | Not published— |
| 2026-09-23 | token | $0.462 | $1.386 | Not published— |
| 2026-09-24 | token | $0.462 | $1.386 | Not published— |
| 2026-09-25 | token | $0.3458 | $1.038 | Not published— |
| 2026-09-26 | token | $0.264 | $0.792 | Not published— |
| 2026-09-27 | token | $0.245 | $3.5 | Not published— |
| 2026-09-28 | token | $0.3995 | $4.2 | Not published— |
| 2026-09-29 | token | $0.3999 | $3.49 | Not published— |
| 2026-09-30 | token | $0.66 | $1.98 | Not published— |
| 2026-10-01 | token | $0.66 | $1.98 | Not published— |
| 2026-10-02 | token | $0.66 | $1.98 | Not published— |
| 2026-10-03 | token | $0.22 | $4.2 | Not published— |
| 2026-10-04 | token | $0.85 | $5 | Not published— |
| 2026-10-05 | token | $0.4 | $5 | Not published— |
| 2026-10-06 | token | $0.66 | $1.98 | Not published— |
| 2026-10-07 | token | $0.66 | $1.98 | Not published— |
| 2026-10-08 | token | $0.66 | $1.98 | Not published— |
| 2026-10-09 | token | $0.66 | $1.98 | Not published— |
| 2026-10-10 | token | $0.66 | $1.98 | Not published— |
| 2026-10-11 | token | $0.66 | $1.98 | Not published— |
| 2026-10-12 | token | $0.66 | $1.98 | Not published— |
| 2026-10-13 | token | $0.66 | $1.98 | Not published— |
| 2026-10-14 | token | $0.66 | $1.98 | Not published— |
| 2026-10-15 | token | $0.66 | $1.98 | Not published— |
| 2026-10-16 | token | $0.66 | $1.98 | Not published— |
| 2026-10-17 | token | $0.66 | $1.98 | Not published— |
| 2026-10-18 | token | $0.66 | $1.98 | Not published— |
| 2026-10-19 | token | $0.66 | $1.98 | Not published— |
| 2026-10-20 | token | $0.66 | $1.98 | Not published— |
| 2026-10-21 | token | $0.66 | $1.98 | Not published— |
| 2026-10-22 | token | $0.66 | $1.98 | Not published— |
| 2026-10-23 | token | $0.66 | $1.98 | Not published— |
| 2026-10-24 | token | $0.66 | $1.98 | Not published— |
| 2026-10-25 | token | $0.66 | $1.98 | Not published— |
| 2026-10-26 | token | $0.66 | $1.98 | Not published— |
| 2026-10-27 | token | $0.66 | $1.98 | Not published— |
| 2026-10-28 | token | $0.66 | $1.98 | Not published— |
| 2026-10-29 | token | $0.66 | $1.98 | Not published— |
| 2026-10-30 | token | $1.32 | $3.96 | Not published— |
Alternatives
- @cf/deepseek-ai/deepseek-v4-pro-0813$1.32/1M · Compare
- DeepSeek V4 Pro 0813$1.32/1M · Compare
- DeepSeek V4 Pro 0813$1.32/1M · Compare
- DeepSeek V4 Pro 0813$1.32/1M · Compare
- deepseek-v4-pro-0813$1.32/1M · Compare
- deepseek-v4.1-pro$1.32/1M · Compare
Parameters (20)
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Call this model
OpenRouter id deepseek/deepseek-v4-pro-0813. 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-0813","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-0813",
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-0813", "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())