VARIANT · DeepSeek / DeepSeek

DeepSeek deepseek-v4-pro API

Same API, same SDK — switch variants by changing one parameter.

Operational · text · Commercial OK
# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/deepseek -g
The -g flag installs globally so every project picks it up.
Or paste this prompt to your AI agent:
Install the DeepSeek skill for me:

1. Clone https://github.com/runapi-ai/deepseek
2. Copy the skills/deepseek/ directory into your
   user-level skills directory (e.g. ~/.claude/skills/
   for Claude Code, ~/.codex/skills/ for Codex).
3. Verify that SKILL.md is present.
4. Confirm the install path when done.
Switch variant
deepseek-v4-flash
OVERVIEW

deepseek-v4-pro targets the sweet spot of quality and cost within the DeepSeek family.

  • Pay-per-call pricing in USD
  • Failed generations not charged
  • Streaming when supported by the model
  • Schema-validated tool calls
PRICING

Pricing

Failed generations are not charged
Messages API
Input $3.48 / 1M tokens
Output $6.96 / 1M tokens
Cache read $0.03
Chat completion
Input $3.48 / 1M tokens
Output $6.96 / 1M tokens
Cache read $0.03
SPEC SHEET

Technical details

Model ID deepseek-v4-pro
Provider DeepSeek
Modality text
Task type synchronous
Billing unit 1K tokens
API endpoint /v1/messages
Commercial license Yes — included via API
Status Operational
QUICKSTART

Quickstart — deepseek-v4-pro

runapi.ai
curl -X POST https://runapi.ai/v1/messages \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek-v4-pro",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Refactor this Python module for readability, explain each change, then add unit tests for the edge cases."
    }
  ]
}'
import { DeepseekClient } from "@runapi.ai/deepseek";

const client = new DeepseekClient();
const result = await client.message.run({
    model: "deepseek-v4-pro",
    max_tokens: 1024,
    messages: [{"role":"user","content":"Refactor this Python module for readability, explain each change, then add unit tests for the edge cases."}],
});
require "runapi/deepseek"

client = RunApi::Deepseek::Client.new
result = client.message.run(
    model: "deepseek-v4-pro",
    max_tokens: 1024,
    messages: [{role: "user", content: "Refactor this Python module for readability, explain each change, then add unit tests for the edge cases."}]
)
@runapi.ai/deepseek v1
HOW IT WORKS

Use deepseek-v4-pro in four steps

01

Install

Install the model SDK or agent skill for this model line.

02

Configure

Set the model field to the full model ID shown on this page.

03

Call

Send a typed request with your prompt, inputs, and callback settings.

04

Receive

Read the task response, webhook callback, or cached output URL from RunAPI.

DIFFERENCES

What's different about deepseek-v4-pro

VS DEEPSEEK-V4-FLASH

Flagship reasoning and analysis for complex agentic work

Fast, low-cost reasoning; toggle thinking per request

USE CASES

Best for

Customer support

Answer customer questions from a private knowledge base, reducing ticket volume.

Document analysis

Draft contract summaries and flag key clauses for attorney review.

Code generation

Auto-generate unit tests, code reviews, and refactoring suggestions in CI.

FAQ

Frequently asked questions about deepseek-v4-pro

Is the model ID stable across versions?

RunAPI keeps the model ID stable and handles compatible version refreshes without changing your request shape.

What's the rate limit on this variant?

Per-key rate limits scale with usage tier. See pricing page for current limits.

Can I switch variants later?

Yes — variant is a flag. Switch by changing the model parameter.

Does it stream?

Where streaming is available, RunAPI streams end-to-end.

Where do I report quality issues?

Open an issue on the public GitHub repo or email support.

START NOW

Start building with DeepSeek.