DeepSeek
Reasoning-first LLMs via RunAPI — flash for fast, low-cost work; pro for complex agentic tasks.
# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/deepseek -gInstall 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.
DeepSeek is a family of reasoning-first language models. deepseek-v4-flash is the fast, low-cost tier with an optional thinking mode; deepseek-v4-pro targets the hardest reasoning and agentic workloads. Both are available through RunAPI with one key and per-token billing.
- Installable agent skill
- Unified API key
- SDK examples included
- 失敗した生成は課金されません
バリアント
Use this model from your agent
# User prompt to the agent
"Refactor this Python module for readability, explain each change, then add unit tests for the edge cases."// Code generated by the agent via @runapi.ai/deepseek
import { DeepseekClient } from '@runapi.ai/deepseek';
const client = new DeepseekClient();
const result = await client.chatCompletion.run({
model: 'deepseek-v4-flash',
prompt: 'Refactor this Python module for readability, explain each change, then add unit tests for the edge cases.',
});How to call this model
Install the skill
Add the model skill to your agent or install the SDK package.
Authenticate once
Use your RunAPI key for every supported model.
Send a request
Use the unified schema for the endpoint you need.
Receive output
Poll by task ID or handle the callback when the generation completes.
SDK quickstart
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."}]
)Where DeepSeek fits
DeepSeek models are large language models tuned for reasoning, code, and agentic tool use. Through RunAPI they share a single API key with pay-as-you-go token billing, and are callable from both the OpenAI and Anthropic SDKs.
Why use DeepSeek through RunAPI
One API key
Use the same credentials across models and providers.
Agent-ready
Installable skills include docs and schema for tool calls.
Predictable billing
Usage-based pricing is visible before you call.
Frequently asked questions
How do I call this model?
Use the RunAPI SDK, CLI, or REST endpoint shown on this page.
Do failed generations cost money?
失敗した生成は課金されません
Can agents use it directly?
Yes. Install the model skill and your agent gets the docs, schema, and examples.
