DeepSeek V4 API
$0.3/Mtok inDeepSeek · text
Open-weight frontier-adjacent reasoning at commodity prices.
Overview
About DeepSeek V4
Open-weight frontier-adjacent reasoning at commodity prices. 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
Pricing
$0.3/Mtok in
Metered exactly per call
Context window
128k tokens
Commercial use
See license
Open weights; commercial use permitted (MIT-style model license).
Variants
All endpoints
Prompt library
Example runs
Solve and explain: a train leaves at…
Step 1…
This exact run cost $0.001
Quickstart
How to use the DeepSeek V4 API
- 1
Create a free CompanyFabric account — starter credits are included, no card required.
- 2
Copy your API key from the dashboard. One key covers every model in the library.
- 3
Point any OpenAI SDK at api.companyfabric.com/v1 and set model to "deepseek/deepseek-v4".
- 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
Pricing
| Endpoint | Type | Price |
|---|---|---|
| DeepSeek V4 | Chat | $0.3 / M input · $0.9 / M output |
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",
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
Comparisons
DeepSeek V4 vs the alternatives
DeepSeek V4 vs Gemini 3 Flash
DeepSeek V4 and Gemini 3 Flash 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.
DeepSeek V4 vs Claude Haiku 4.5
DeepSeek V4 and Claude Haiku 4.5 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.
FAQ
Frequently asked questions
How much does the DeepSeek V4 API cost?
$0.3 / M input · $0.9 / M output. Every call is metered exactly and shown before you run it.
How do I get a DeepSeek V4 API key?
Create a CompanyFabric account, and one key unlocks DeepSeek V4 and every other model in the library. Free starter credits are included — no subscription, no card required to try it.
Why use DeepSeek V4 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".
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. License: Open weights; commercial use permitted (MIT-style model license).
Explore
Related model APIs
Claude Sonnet 4.5
$3/Mtok inAnthropic
Frontier-quality text and reasoning through one OpenAI-compatible endpoint.
text
Claude Haiku 4.5
$1/Mtok inAnthropic
Fast, cheap frontier-family model for high-volume tasks.
text
Claude Opus 4.6
$15/Mtok inAnthropic
The frontier tier for the hardest reasoning and agentic work.
text
GPT-5.5
$5/Mtok inOpenAI
OpenAI's flagship, one key away.
text
Gemini 3.1 Pro
$2/Mtok inMillion-token context at a mid-tier price.
text
Gemini 3 Flash
$0.3/Mtok inThe cheap long-context workhorse.
text
One key. Every model. Exact prices.
Run DeepSeek V4 with free starter credits. Free starter credits included — no subscription required.