DeepSeek

DeepSeek's reasoning-first LLMs — flash for fast, low-cost work and pro for complex agentic tasks, via one RunAPI key.

2
MODELS
LLM · Utility
MODALITIES
Get API Key

What you get through RunAPI

Full Model Access

Browse every model currently listed for this provider in the RunAPI catalog.

Transparent Pricing

Review each model's published RunAPI price before sending a request.

No Account Required

Use your RunAPI key without creating a separate provider account.

Unified Billing

Keep this provider and other supported models on one RunAPI balance.

HOW IT WORKS

Call DeepSeek models in 3 steps

  1. Get Your Key

    Sign up for free and create a RunAPI key — no DeepSeek account needed.

  2. Send a Request

    Call the model's RunAPI endpoint with your key and the DeepSeek model ID.

  3. Get Results

    Stream the response or receive a webhook when the task completes.

MODELS

DeepSeek Models on RunAPI

Text

DeepSeek

DeepSeek API access via RunAPI — flash for fast, low-cost work; pro for complex agentic tasks.

$0.24 / 1M tokens View →
Utility

DeepSeek Search

Synchronous web search with structured results

$0.0011 / call View →

Why use DeepSeek via RunAPI

Published Pricing

Check each DeepSeek model's RunAPI price and billing unit before you send a request.

No Account Needed

Use your RunAPI API key for managed DeepSeek access without a separate provider account or credential.

Unified Billing

Keep DeepSeek and every other supported model on one RunAPI balance and monthly USD invoice.

RunAPI vs Direct DeepSeek

Feature Direct DeepSeek Via RunAPI
Account Required DeepSeek account + billing RunAPI account only
API Format DeepSeek API One RunAPI request format across providers
Pricing Provider-published rates Published per-model RunAPI pricing
Other Models DeepSeek only 255+ models, all providers
Billing Per-provider invoices One unified credit balance
Support Provider-specific support RunAPI support
Playground

Try DeepSeek Models

Estimated: Input $0.24 / 1M tokens | Output $0.96 / 1M tokens

Sign in to generate with RunAPI.

Sign in to generate

Sign in to start generating with your available language models.

Response will appear here

QUICKSTART

Call DeepSeek Models via RunAPI

Python
from openai import OpenAI

client = OpenAI(
    base_url="https://runapi.ai/v1",
    api_key="your-runapi-key"
)

response = client.chat.completions.create(
    model="deepseek-flash",
    messages=[{"role": "user", "content": "Refactor this Python module for readability, explain each change, then add unit tests for the edge cases."}]
)

What teams build with DeepSeek models

Conversational AI

Build chatbots and assistants with DeepSeek models.

Content Generation

Generate marketing copy, code, and creative writing at scale.

Image Creation

Create product shots, illustrations, and design assets with DeepSeek models.

Data Analysis

Extract insights from documents, spreadsheets, and structured data.

Provider questions

Which model name should I use for DeepSeek Flash?

Use deepseek-flash for new code. DeepSeek documents that its official direct API serves the retired names deepseek-v4-flash and deepseek-v4-flash-vision-exp with DeepSeek-V4.1-Flash-1017 at the Flash price. Third-party mappings to 1017 remain unconfirmed.

Which DeepSeek models can I call through RunAPI?

Use deepseek-flash for everyday work and deepseek-v4-pro for complex reasoning. DeepSeek documents the official direct API as DeepSeek-V4.1-Flash-1017, updated on 2026-10-17. Third-party service options may use older versions; their 1017 status is unverified. DeepSeek officially lists image input, a 1M-token context and up to 384K output tokens for V4.1 Flash. On RunAPI, use deepseek-flash; image input and these context and output limits have not been tested across all service options.

Does DeepSeek work with the OpenAI and Anthropic SDKs?

Yes — DeepSeek is exposed on both the OpenAI Chat Completions and Anthropic Messages surfaces; use either SDK with your RunAPI key.

How is thinking mode controlled?

Thinking is a per-request parameter on deepseek-flash rather than a separate model id.

How does prompt caching affect cost?

Cached prompt tokens bill at a reduced cache-read rate; hits are detected automatically and shown in usage.

Do I need a DeepSeek account?

No. Your RunAPI API key is enough to access the DeepSeek models listed in the catalog.

Which DeepSeek models are available?

The model cards above reflect the DeepSeek models currently available through RunAPI.

How does billing work?

Usage is charged to your RunAPI balance using the price shown for the selected model.

Can I switch to another model?

Yes. Choose another supported model and use its model ID in the same RunAPI workflow.

Where can I find request details?

Open a model page to review its current endpoints, parameters, pricing, and examples.

Start building on one key.

Building with a team?

We're here to help with enterprise setup, integrations, and technical questions.

Contact Us