Skip to contentOceanToken

DeepSeek V4 Pro

deepseek/deepseek-v4-pro

A mixture-of-experts model built for reasoning and coding. Bring large documents and projects into a million-token context, with tool calling and structured output support. Good for reasoning, software development and document analysis.

Our discountYour discount

−20%off the official price−30%off the official priceUp to −40%off the official priceTier 3

  • Tier 1−20%
  • Tier 2−30%
  • Tier 3−40%

Official $1.32 / $3.96Our price $1.056 / $3.168$0.924 / $2.772$0.792 / $2.376 Per 1M tokensTier 3: up to −40%

  • InputtextOutput: text
  • Context1.05M tokensUp to 384K output per reply
  • ReleasedApril 24, 2026In the OceanToken catalog

01 · Learn

What is DeepSeek V4 Pro?

DeepSeek V4 Pro is a language model from DeepSeek on the OceanToken API, with a 1.05M-token context window and reasoning, tool calling and structured outputs.

  • −40%Our price vs official$0.792 / $2.376 Per 1M tokens · Official: $1.32 / $3.96
  • 1.05MContext windowUp to 384K output per reply
  • textInputOutput: text
  • Up to 60% offEnterprise rate vs officialUp to, by quote

What DeepSeek V4 Pro can do.

  • Reasoning
  • Software development
  • Document analysis

02 · Compare

Is DeepSeek V4 Pro cheaper than similar models?

The official price, then our price, for DeepSeek V4 Pro and the models most like it.

OfficialOur price

Per 1M tokens, half input and half output. Prices as of November 18, 2026. Enterprise rate: quote by email, we activate it for you.

DeepSeek V4 Pro benchmarks.

  • 1,465LMArena TextHuman preference rating, LMArena

Scores from independent leaderboards, as of October 27, 2026. We did not run these tests ourselves.

DeepSeek V4 Pro specs.

Context window
1.05M tokens (1,048,576)
Max output
384K tokens (384,000)
Input
text
Output
text
Reasoning
Yes, reasoning_effort
Tool calling
Yes, tool_choice
Structured outputs
Yes, response_format
Prompt caching
Yes, at the official price
Released
April 24, 2026

Model ID and endpoint

OceanToken model ID
deepseek/deepseek-v4-pro
OpenAI-compatible base URL
https://api.oceantoken.ai/v1
Endpoint
POST /v1/chat/completions

03 · Buy and build

How much does the DeepSeek V4 Pro API cost?

DeepSeek V4 Pro costs $1.056 per 1M input tokens and $3.168 per 1M output tokens. Cached input costs $0.044 per 1M tokens. The official price is $1.32 per 1M input tokens and $3.96 per 1M output tokens. At the top cumulative top-up tier it costs $0.792 per 1M input tokens and $2.376 per 1M output tokens. Blended (50% input / 50% output): official $2.64 → top tier $1.584 (−40%). These are OceanToken starting prices as of November 18, 2026, charged per use to your prepaid balance. The console always shows the current price.

RateInputOutputOff
Official$1.32$3.96
Tier 1From sign-up$1.056$3.168−20%
Tier 2$1,000 total$0.924$2.772−30%
Tier 3$10,000 total$0.792$2.376−40%
Enterprise rateBy quoteup to −60%

Thinking tokens are billed at the output price.

Per 1M tokens. Half input, half output: official $2.64, ours $1.584. Prompt cache and web search are billed at the official price, at every tier.

How tiers work

  1. Self-serveTier 1From sign-up
  2. Self-serveTier 2$1,000 total
  3. Self-serveTier 3$10,000 total
  4. By quoteEnterprise rateUp to 60% off, by quote

You pay per use from a prepaid balance, with no subscription. Official price: the model maker’s list price. Tier 1 to 3 are standing rates by total top-up.

How to use DeepSeek V4 Pro on OceanToken.

Three steps from no account to a working request. The same key and balance work for every model in the catalog.

  1. Create an account and get an API key

    One key works for every model your account can use.

    Get API Key
  2. Add credits

    OceanToken is prepaid: add credits, and each request is billed from that balance.

    Add credits
  3. Call DeepSeek V4 Pro from your code

    Point an OpenAI SDK at https://api.oceantoken.ai/v1 and use the model ID deepseek/deepseek-v4-pro.

    See the API request in docs
client.pyPython
from openai import OpenAI
# Your API Key from the OceanToken console
client = OpenAI(base_url="https://api.oceantoken.ai/v1",
                api_key="YOUR_API_KEY")
reply = client.chat.completions.create(
    model="deepseek/deepseek-v4-pro",
    messages=[{"role": "user", "content": "Hello"}])
print(reply.choices[0].message.content)

DeepSeek V4 Pro API: frequently asked questions.

What is DeepSeek V4 Pro?

A mixture-of-experts model built for reasoning and coding. Bring large documents and projects into a million-token context, with tool calling and structured output support.

How much does DeepSeek V4 Pro cost?

DeepSeek V4 Pro costs $1.056 per 1M input tokens and $3.168 per 1M output tokens. Cached input costs $0.044 per 1M tokens. The official price is $1.32 per 1M input tokens and $3.96 per 1M output tokens. At the top cumulative top-up tier it costs $0.792 per 1M input tokens and $2.376 per 1M output tokens. Blended (50% input / 50% output): official $2.64 → top tier $1.584 (−40%). These are OceanToken starting prices as of November 18, 2026, charged per use to your prepaid balance. The console always shows the current price.

What is the context length of DeepSeek V4 Pro?

DeepSeek V4 Pro has a context window of 1.05M tokens (1,048,576 tokens).

Does DeepSeek V4 Pro support tool calling, vision and reasoning?

DeepSeek V4 Pro supports tool calling, structured outputs and reasoning. It takes text input and returns text. The catalog does not list image input (vision) for it.

How do I call DeepSeek V4 Pro through the API?

Send requests to https://api.oceantoken.ai/v1/chat/completions with the model ID deepseek/deepseek-v4-pro and your OceanToken API key. The API is OpenAI-compatible, so an OpenAI SDK needs only the base URL https://api.oceantoken.ai/v1 and your key. The Responses API and the Anthropic Messages API (/v1/messages) work too. The same OceanToken API key works for every model your account can use. Full reference: docs.oceantoken.ai.

How do I top up?

OceanToken is prepaid. Open Credits in the console, choose an amount and pay by card on Stripe's hosted checkout page (Link works too). Your balance updates a few seconds after payment. Have a trial code? Redeem it on the same page.

Do credits expire, and can I get a refund?

Purchased credits are valid for 12 months from the date of purchase. Credits from trial codes, promotions or gifts may have a shorter validity. All purchases are final and non-refundable, except where the law requires a refund. Section 6 of the Terms of Service has the details.

Am I charged for failed requests?

No. If a request fails, you are not charged: that covers a request refused for an insufficient balance or by a safety check, one whose provider fails before returning any output, and a video job that fails or is refused by a safety check, whose held amount goes back to your balance. The one exception: if a request breaks off after the model has started producing output, for example a stream cut off part-way, you pay for the tokens that were processed and generated for it.

Related articles

More from DeepSeek

Similar language models

Compare DeepSeek V4 Pro with other models.

Keep exploring

Sources

Whatever you want.

OceanToken is All You Need.