ChatModelsComparePricingDocs
CouncilClaude CodeCursorCheapest modelsBest for codingFor agentsFree models

Models / DeepSeek

DeepSeek V4

$0.3/Mtok in

Open-weight frontier-adjacent reasoning at commodity prices.

Playground

Try it in the browser

Playground$0.3 in / $0.9 out per 1M tokens

Facts

At a glance

Availability

Retired 2026-09-01

Pricing

$0.3 / M input · $0.9 / M output

Endpoint

Chat Completions

/v1/chat/completions

Context window

128k tokens

API

Call it from code

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",
  max_tokens: 1024,
  temperature: 0.7,
  messages: [{ role: "user", content: "Say hello from the fabric." }],
})

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

Prompt library

Example runs

Solve and explain: a train leaves at…

This exact run cost $0.001

FAQ

Frequently asked questions

How much does DeepSeek V4 cost?

$0.3 / M input · $0.9 / M output. The exact cost of each call is shown before you run it and metered to your prepaid balance, no subscription required.

Why use DeepSeek V4 on CompanyFabric instead of going direct?

One key and one balance across every model in the library, at pricing at parity with or below the direct API. Switching models is a one-line change.

Is DeepSeek V4 available through the OpenAI SDK?

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

Variants

Same family

DeepSeek V4.1 Flash

$0.3/Mtok in

DeepSeek

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

Added 10 Sep 2026 · text

DeepSeek V4 Pro

$1.32/Mtok in

DeepSeek

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

Added 15 Jul 2026 · text

DeepSeek V4 Flash

Retired

DeepSeek

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

Added 10 Aug 2026 · text

Explore

Related model APIs

Claude Sonnet 4.5

Retiring

Anthropic

Frontier-quality text and reasoning through one OpenAI-compatible endpoint.

Added 1 Jun 2026 · text

Claude Haiku 4.5

$1/Mtok in

Anthropic

Fast, cheap frontier-family model for high-volume tasks.

Added 1 Jun 2026 · text

Claude Opus 4.6

$5/Mtok in

Anthropic

The frontier tier for the hardest reasoning and agentic work.

Added 1 Jun 2026 · text

GPT-5.5

$5/Mtok in

OpenAI

OpenAI's flagship, one key away.

Added 1 Jun 2026 · text

GPT-6 Astra

$10/Mtok in

OpenAI

OpenAI's GPT-6 flagship, a million-token window one key away.

Added 3 Sep 2026 · text

Gemini 4 Argon

Coming soon

Google

Google DeepMind's new frontier model for long-horizon software engineering, legal and finance work, and cybersecurity defence, with a 1M-token output limit. Trusted testers only for now.

Announced 30 Sep 2026 · text

One key. Every model. Exact prices.

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

Get your API keyBrowse all models