FOURNISSEUR

DeepSeek

Q: Is this an official DeepSeek integration?

RunAPI exposes a managed API surface with transparent pricing, capability, and error behavior.

Q: Do I need a DeepSeek account?

No. Your RunAPI key is enough for managed access.

Q: How is pricing billed?

Per-call or per-unit metered, with failed generations not charged.

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

1 models · 2 variants · à partir de $0.060

Parcourir les modèles Lire la documentation →

SKILLS 1 skills

DeepSeek Text

2 variants · from $0.060

APERÇU

DeepSeek builds reasoning-first large language models. The v4 line spans deepseek-v4-flash (fast, low-cost, optional thinking) and deepseek-v4-pro (frontier reasoning and agentic work). Both are available through RunAPI from the OpenAI and Anthropic SDKs.

Single API key shared across providers
Per-call billing, no commitment
Les générations échouées ne sont pas facturées
Streaming supported where the model supports it

FONCTIONNALITÉS

What stands out

FASTEST

DeepSeek

P50 ~ <1s

One of the most-installed skills from DeepSeek.

FRONTIER

DeepSeek

Frontier tier

One of the most-installed skills from DeepSeek.

CHEAPEST

DeepSeek

from $0.060

Lowest starting price across the DeepSeek catalog.

MODÈLES

All models from DeepSeek

DeepSeek

Text

Reasoning-first LLMs via RunAPI — flash for fast, low-cost work; pro for complex agentic tasks.

à partir de $0.060 / 1K tokens Voir →

INSTALLER

Start with any DeepSeek model.

Pick a model, install the skill, and start calling from any agent.

# 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.

RÉFÉRENCE