theserverless.dev InferenceList

Models / DeepInfra

deepseek-ai/DeepSeek-V4-Pro

deepinfra/deepseek-ai/DeepSeek-V4-Pro

textContext 1.0M

DeepSeek V4 Pro is an MoE model with 1.6T total parameters (49B active) and a 1M-token context window. It's built for advanced reasoning, coding, and long-running agent tasks, and performs well on knowledge, math, and software engineering benchmarks.

Price

Input$1.3

per 1M tokens

Output$2.6

per 1M tokens

Compare this model

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.

No provider prices yet.

Monthly bill

Token models use the token counts. Image, video, and audio models use units times the flat rate.

$3.90 at list price for this workload

Cache

Cache read$0.1

per 1M tokens

Every rate
UnitInputOutputFlatConfidence
token $1.3/1M $2.6/1M Not published— official

Price history

deepseek-ai/DeepSeek-V4-Pro
3 0 2026-10-08: $1.32026-10-09: $1.32026-10-10: $1.32026-10-11: $1.32026-10-12: $1.32026-10-13: $1.32026-10-14: $1.32026-10-15: $1.32026-10-16: $1.32026-10-17: $1.32026-10-18: $1.32026-10-19: $1.32026-10-20: $1.32026-10-21: $1.32026-10-22: $1.32026-10-23: $1.32026-10-24: $1.32026-10-25: $1.32026-10-26: $1.32026-10-27: $1.32026-10-28: $1.32026-10-29: $1.32026-10-30: $1.3 2026-10-08 2026-10-30

input or flat output

Daily snapshots
UTC dateUnitInputOutputFlat
2026-10-08 token $1.3 $2.6 Not published—
2026-10-09 token $1.3 $2.6 Not published—
2026-10-10 token $1.3 $2.6 Not published—
2026-10-11 token $1.3 $2.6 Not published—
2026-10-12 token $1.3 $2.6 Not published—
2026-10-13 token $1.3 $2.6 Not published—
2026-10-14 token $1.3 $2.6 Not published—
2026-10-15 token $1.3 $2.6 Not published—
2026-10-16 token $1.3 $2.6 Not published—
2026-10-17 token $1.3 $2.6 Not published—
2026-10-18 token $1.3 $2.6 Not published—
2026-10-19 token $1.3 $2.6 Not published—
2026-10-20 token $1.3 $2.6 Not published—
2026-10-21 token $1.3 $2.6 Not published—
2026-10-22 token $1.3 $2.6 Not published—
2026-10-23 token $1.3 $2.6 Not published—
2026-10-24 token $1.3 $2.6 Not published—
2026-10-25 token $1.3 $2.6 Not published—
2026-10-26 token $1.3 $2.6 Not published—
2026-10-27 token $1.3 $2.6 Not published—
2026-10-28 token $1.3 $2.6 Not published—
2026-10-29 token $1.3 $2.6 Not published—
2026-10-30 token $1.3 $2.6 Not published—

Alternatives

Parameters (2)
chatprompt_cache
Call this model

OpenRouter id deepinfra/deepseek-ai/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":"deepinfra/deepseek-ai/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: "deepinfra/deepseek-ai/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": "deepinfra/deepseek-ai/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())

JSON · History JSON