DeepSeek deepseek-v4-flash API
A model variant exposed through RunAPI's unified AI API.
Operational
·
text
·
Commercial use supported
# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/deepseek -g
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
개요
DeepSeek deepseek-v4-flash is available through the same RunAPI auth, SDKs, and agent skill workflow.
- Unified endpoint
- SDK snippets
- Agent install path
- 실패한 생성은 과금되지 않습니다
요금
요금
실패한 생성은 과금되지 않습니다
Chat completion
Input
$0.28
/ 1M tokens
Output
$0.56
/ 1M tokens
Cache read
$0.01
Messages API
Input
$0.28
/ 1M tokens
Output
$0.56
/ 1M tokens
Cache read
$0.01
스펙
스펙
| Model ID | deepseek-v4-flash |
| 제공사 | DeepSeek |
| 모달리티 | text |
| Task type | synchronous |
| 과금 | 1K tokens |
| Endpoint | /v1/chat/completions |
| Commercial | Yes |
| Status | Operational |
빠른 시작
Quickstart — deepseek-v4-flash
curl -X POST https://runapi.ai/v1/chat/completions \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-flash",
"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.chatCompletion.run({
model: "deepseek-v4-flash",
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.chat_completion.run(
model: "deepseek-v4-flash",
messages: [{role: "user", content: "Refactor this Python module for readability, explain each change, then add unit tests for the edge cases."}]
)
작동 방식
How to use deepseek-v4-flash
01
Choose endpoint
Pick the endpoint and copy the SDK snippet.
02
Pass model ID
Use this variant ID in the request body.
03
Run task
Submit the request and store the returned task ID.
04
Collect output
Poll or receive the callback when the task finishes.
차이
How deepseek-v4-flash compares
VS DEEPSEEK-V4-PRO
Fast, low-cost reasoning; toggle thinking per request
Flagship reasoning and analysis for complex agentic work
사용 사례
Where to use this variant
Chat
Use LLMs for chat and reasoning.
Code
Generate and review implementation work.
Automation
Connect models into backend tasks.
FAQ
Frequently asked questions about deepseek-v4-flash
How do I select deepseek-v4-flash?
Pass the model ID shown in the quickstart.
Is pricing usage-based?
Yes. Pricing is metered per call or unit.
Other DeepSeek variants
Related models
지금 시작