ChatModelsComparePricingDocs
CouncilClaude CodeCursorCheapest modelsBest for codingFor agentsFree models
LiveAdded 15 Jul 2026DeepSeek

DeepSeek V4 Pro API

Retired by DeepSeek on 14 Sep 2026. Requests are served by V4.1 Flash from then, and billed at Flash's rate.

Open playgroundView API docs

Model spec

Input
$1.32per 1M tokens
Output
$3.96per 1M tokens
Cached input
$0.044per 1M tokens
Context
1.05M
Max output
393K

Model ID

OpenAI-compatible · api.companyfabric.com/v1

Overview

About DeepSeek V4 Pro

Retired by DeepSeek on 14 Sep 2026. Requests are served by V4.1 Flash from then, and billed at Flash's rate. Every model on CompanyFabric shares the same API key, billing balance, and rate-limit envelope, one integration covers the entire library.

Facts

At a glance

Availability

Live

Added 15 Jul 2026

Pricing

$1.32 in · $3.96 out

Per 1M tokens, metered exactly per call

Context window

1.05M tokens

Up to 393K tokens out

Commercial use

See license

Open weights; commercial use permitted (MIT-style model license).

Variants

All endpoints

DeepSeek V4

Retired$0.3/Mtok in

Open-weight frontier-adjacent reasoning at commodity prices.

Chat Completions

DeepSeek V4.1 Flash

$0.3/Mtok in

DeepSeek's cheapest current model, a million-token window at flash rates.

Chat Completions

DeepSeek V4 Pro

$1.32/Mtok in

Retired by DeepSeek on 14 Sep 2026. Requests are served by V4.1 Flash from then, and billed at Flash's rate.

Chat Completions

DeepSeek V4 Flash

Retired$0.44/Mtok in

The V4 family's speed tier, near-V4 quality on everyday calls at the lowest price in the family.

Chat Completions

Quickstart

How to use the DeepSeek V4 Pro API

  1. 1

    Create a free CompanyFabric account, starter credits are included, no card required.

  2. 2

    Copy your API key from the dashboard. One key covers every model in the library.

  3. 3

    Point any OpenAI SDK at api.companyfabric.com/v1 and set model to "deepseek/deepseek-v4-pro".

  4. 4

    Read the exact metered cost of the call from the response, the same number shown in the playground.

Use cases

What teams build with it

Agents & copilots

Drive agent loops, tool calls, and user-facing assistants over the OpenAI-compatible endpoint.

agentstool useassistants

Content pipelines

Summarization, rewriting, and structured generation at metered per-token cost.

contentsummarization

Extraction & classification

Turn unstructured input into typed JSON with schema-constrained output.

extractionjson mode

Get better output

Prompting tips

  • State the output format before the task, models follow contracts declared early.
  • Few-shot beats description: two worked examples outperform a paragraph of rules.
  • Cap output length explicitly when cost matters; output tokens dominate most bills.

Exact, metered, prepaid

DeepSeek V4 Pro pricing

DeepSeek V4 Pro pricing is per token: $1.32 / M input · $3.96 / M output · $0.044 / M cached input. Output tokens cost 3× input tokens, so long generations, not long prompts, are what actually drive most bills. A typical call with a 2k-token prompt and a 1k-token answer costs about $0.0066.

Every call is metered exactly and attributed to your key, the dashboard, the API usage response, and your invoice all read from the same ledger row. Cap any key's monthly spend with a budget cap, and bring your own provider key (BYOK) at 0% platform fee if you already have a direct contract.

EndpointTypePrice
DeepSeek V4Chat$0.3 / M input · $0.9 / M output
DeepSeek V4.1 FlashChat$0.3 / M input · $1.2 / M output · $0.006 / M cached input
DeepSeek V4 ProChat$1.32 / M input · $3.96 / M output · $0.044 / M cached input
DeepSeek V4 FlashChat$0.44 / M input · $1.32 / M output

Starter credits

Use DeepSeek V4 Pro free

Your CompanyFabric starter credits cover your first DeepSeek V4 Pro calls at no cost, create a free account, no card required, and the credits apply to DeepSeek V4 Pro and every other model on the key. When they run out, prepaid credits or BYOK (0% fee) take over with no plan to pick.

All ways to use AI models free →Run DeepSeek V4 Pro locally (open weights) →

Production-grade

Code samples

import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://api.companyfabric.com/v1",
  apiKey: process.env.COMPANYFABRIC_API_KEY,
})

const res = await client.chat.completions.create({
  model: "deepseek/deepseek-v4-pro",
  max_tokens: 1024,
  temperature: 0.7,
  messages: [{ role: "user", content: "Say hello from the fabric." }],
})

console.log(res.choices[0].message.content)

Playground

Try it in the browser

Playground$1.32 in / $3.96 out per 1M tokens

Comparisons

DeepSeek V4 Pro vs the alternatives

DeepSeek V4 Pro vs Kimi K3

DeepSeek V4 Pro and Kimi K3 compete for the same text workloads. Both run behind the same CompanyFabric key at exact metered prices, A/B them on your real prompts and let the outputs decide, then switch with a one-line change.

Full comparison: DeepSeek V4 Pro vs Kimi K3 →

DeepSeek V4 Pro vs Gemini 3.1 Pro (preview)

DeepSeek V4 Pro and Gemini 3.1 Pro (preview) compete for the same text workloads. Both run behind the same CompanyFabric key at exact metered prices, A/B them on your real prompts and let the outputs decide, then switch with a one-line change.

Full comparison: DeepSeek V4 Pro vs Gemini 3.1 Pro (preview) →

Compare

DeepSeek V4 Pro head to head

DeepSeek V4 ProvsGemini 3.1 Pro (preview)DeepSeek V4 ProvsGLM-5.3DeepSeek V4 ProvsMiMo-V2.6-ProDeepSeek V4 ProvsMistral Large 4

FAQ

Frequently asked questions

How much does the DeepSeek V4 Pro API cost?

$1.32 / M input · $3.96 / M output · $0.044 / M cached input. Every call is metered exactly and shown before you run it.

How do I get a DeepSeek V4 Pro API key?

Create a CompanyFabric account, and one key unlocks DeepSeek V4 Pro and every other model in the library. Free starter credits are included, no subscription, no card required to try it.

Why use DeepSeek V4 Pro on CompanyFabric instead of going direct?

One key, one prepaid balance, and one rate-limit envelope across the whole library, at pricing at parity with or below the direct API. Model switching is a one-line change, and BYOK routing is 0% fee.

Is the API OpenAI-compatible?

Yes, point any OpenAI SDK at api.companyfabric.com/v1 and set model to "deepseek/deepseek-v4-pro".

Can I use the output commercially?

Open weights; commercial use permitted (MIT-style model license).

How does billing work?

Prepaid credits via card, or BYOK with your own provider keys at 0% platform fee. No subscription required; balances never expire.

Provider

About DeepSeek

DeepSeek publishes the deepseek family. Also in this family: DeepSeek V4, DeepSeek V4.1 Flash, DeepSeek V4 Flash. License: Open weights; commercial use permitted (MIT-style model license).

One key. Every model. Exact prices.

Run DeepSeek V4 Pro with free starter credits. Free starter credits included, no subscription required.

Get your API keyBrowse all models