GetPost AI and LLM Gateway

Access 24+ LLM chat models and 16+ image/video generation models via one API.

Security Scan

The skill is an instruction-only wrapper for the getpost.dev API (sending prompts to a third-party service), but its registry metadata omits the API key requirement and has no provenance — verify the provider and key handling before installing.

Purpose & Capability

The name/description (LLM + image/video gateway) matches the SKILL.md which shows curl examples against getpost.dev endpoints. That capability is coherent. However, the registry metadata declares no required credentials while the instructions explicitly require a gp_live_* API key, which is an inconsistency.

Instruction Scope

The SKILL.md limits runtime actions to curl calls against getpost.dev (signup, chat, generate, jobs). Those calls will transmit user prompts and any included content to an external provider — acceptable for an API client but a privacy/data-exfiltration concern. The instructions do not reference local files, system config, or other environment variables, but they also do not specify how the agent should securely store or reference the API key.

Install Mechanism

Instruction-only skill with no install spec and no code files; nothing is written to disk by the skill itself. This minimizes installation risk.

Credentials

Registry lists no required env vars or primary credential, yet SKILL.md requires an API key (Authorization: Bearer gp_live_YOUR_KEY). The skill should declare a primaryEnv or required env var so users and the agent know where to store the key. Because the skill will send data to an external endpoint, the lack of declared credential handling is a material omission.

Persistence & Privilege

always is false and the skill is user-invocable; it does not request persistent or system-level privileges and does not modify other skill configs.

What to consider before installing

This skill is basically a set of curl examples for the getpost.dev API. Before installing: (1) confirm getpost.dev is a legitimate/trusted provider and review its privacy/TOS and pricing, (2) assume everything you send (prompts, images, files) will be stored/processed by that third party — do not send secrets or PII, (3) do not reuse high-privilege API keys — create a dedicated key/account and limit its scope, (4) ask the skill author to declare the required env var (e.g., GETPOST_API_KEY) or otherwise document how the agent should securely store the key, and (5) if you need stronger guarantees about data handling, prefer an officially supported provider with clear docs and provenance. If you cannot verify the provider or the skill's provenance, treat it as risky.

GetPost AI API

Access 24+ LLM chat models and 16+ image/video generation models through a single API. OpenAI, Anthropic, Google, Grok, DeepSeek, Moonshot, Midjourney, and more.

Quick Start

# Sign up (no verification needed)
curl -X POST https://getpost.dev/api/auth/signup \
  -H "Content-Type: application/json" \
  -d '{"name": "YOUR_NAME", "bio": "What your agent does"}'
# Save the api_key from the response

Authentication

Authorization: Bearer gp_live_YOUR_KEY

Chat Completion

curl -X POST https://getpost.dev/api/ai/chat \
  -H "Authorization: Bearer gp_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-4.1-nano", "messages": [{"role": "user", "content": "Hello"}], "max_tokens": 100}'

Available Chat Models

gpt-5.4, gpt-4.1, gpt-4.1-nano, claude-opus-4-6, claude-sonnet-4-6, gemini-2.5-flash, grok-4, deepseek-chat, kimi-k2.5, and more. See all: GET /api/ai/models

Image Generation

curl -X POST https://getpost.dev/api/ai/generate \
  -H "Authorization: Bearer gp_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-image-1", "prompt": "A cat in space", "n": 1}'

Models: gpt-image-1, dall-e-3, midjourney, imagen-4, grok-imagine-image, stable-diffusion-3.5

Video Generation

curl -X POST https://getpost.dev/api/ai/generate \
  -H "Authorization: Bearer gp_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "sora-2", "prompt": "A timelapse of a flower blooming"}'

Models: sora-2, grok-imagine-video, veo-3.1. Returns job_id — poll GET /api/ai/jobs/{id} for result.

Full Docs

https://getpost.dev/docs/api-reference#ai