Free credit to start. Top up from $5. Create a key
LLM Gateway
DeepSeek · Text · Coding ready

DeepSeek V4 Pro API pricing

Call DeepSeek V4 Pro through one OpenAI-compatible endpoint, billed $0.53 per 1M input tokens, 45% below DeepSeek’s list price. Routes are verified before they serve you and re-checked continuously.

Get an API key Try it in the playground
Context window
1M tokens
Type
Text
Capabilities
tools · reasoning
Availability
Callable now
Model id
deepseek/deepseek-v4-pro
What you paySave 45%
Input, per 1M tokens
$0.53was $0.96
Output, per 1M tokens
$1.05was $1.91
vendor listyou pay

Same model, same tokens, less to pay. Billed per request from prepaid credits; every response reports the cost.

Use it

Point the OpenAI SDK at OSMEXO and use deepseek/deepseek-v4-pro

The base URL and the key are the only changes. Streaming, tool calls, structured output and vision behave as they do upstream, and every response carries the billed cost beside the list price.

Python · openai sdk
from openai import OpenAI

client = OpenAI(
    base_url="https://api.osmexo.com/v1",   # was the vendor's URL
    api_key="osm-...",
)
r = client.chat.completions.create(
    model="deepseek/deepseek-v4-pro",
    messages=[{"role": "user", "content": "Hello"}],
)
Trust

Check it is the real DeepSeek V4 Pro, with your own key

The same battery we run before a route goes live: tokenizer fingerprint, knowledge cutoff, hidden-prompt probe and exact-output tasks, scored 0 to 100 against the vendor’s own API. One OpenRouter key verifies any text model; a direct DeepSeek key works too. Exit code 0 means the same model.

bash · verify with your own vendor key
curl -fsSLO https://dashboard.osmexo.com/verify.mjs
OSMEXO_API_KEY=osm-... VENDOR_API_KEY=sk-or-... node verify.mjs --model deepseek/deepseek-v4-pro --vendor openrouter
How the score worksCoding readystreamed tool callsparallel toolstool round tripfiles written via toolslong file (15k tokens)
Questions

About DeepSeek V4 Pro on OSMEXO

How much does DeepSeek V4 Pro cost through OSMEXO?
$0.53 per 1M input tokens and $1.05 per 1M output tokens, billed per request from prepaid credits. That is 45% below DeepSeek’s list price of $0.96 / $1.91. The price on this page refreshes from the catalog every few minutes.
Is this the same DeepSeek V4 Pro as calling DeepSeek directly?
Yes. Every route for DeepSeek V4 Pro is probed against the vendor’s own API before it serves anyone: tokenizer fingerprint, knowledge cutoff, a hidden-prompt probe and exact-output tasks, scored 0 to 100 with 85 as the approval threshold. You can run the same check from your machine with your own vendor key; the command is on this page.
How do I call DeepSeek V4 Pro with the OpenAI SDK?
Point the official OpenAI SDK at https://api.osmexo.com/v1 with your OSMEXO key and use the model id deepseek/deepseek-v4-pro. Streaming, tool calls, structured output and vision work as they do upstream. Coding agents such as OpenCode, Cline, Roo Code, Continue and Aider take the same base URL and key.
What happens if a provider for DeepSeek V4 Pro goes down?
The gateway retries and falls back to the next verified route for DeepSeek V4 Pro before the first token is sent, so your users see a slower answer instead of an error. Every response reports which route answered, what it cost, and what the same tokens would have cost at list price.
More from the catalog

Related models

All models and prices →

Start in five minutes

Same models. Same code. Smaller bill.

Create a key, change the base URL, and see on the very first response what you saved.

Get an API key Read the docs