A guide to using an account's text, image and video generation API from code. An API is a programmable service that scripts, apps or other agents can call, rather than a person using a chat screen.

Use it when writing a script, app or agent that sends requests to the service, or when answering questions about API keys, balances and charges.

It explains the difference between calling the service from code and operating the same account through a conversation. It also covers the account's API keys, balances and billing setup.

sapiens-api — Skill for Claude Code by inhabitants/sapiens-mcp

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add inhabitants/sapiens-mcp --skill sapiens-api

Clone the repo

git clone --depth 1 https://github.com/inhabitants/sapiens-mcp

Made for: Claude Code.

Or install sapiens-sinteticos, the plugin that ships this one along with the rest of its 18 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/sapiens-api/github.svg)](https://agentmods.dev/skills/inhabitants/sapiens-mcp/sapiens-api)

Your own site

<a href="https://agentmods.dev/skills/inhabitants/sapiens-mcp/sapiens-api"><img src="https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/sapiens-api/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/inhabitants/sapiens-mcp/sapiens-api"><img src="https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/sapiens-api.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,648 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00080	$0.01648
Opus 5.5	$0.00032	$0.00659
Sonnet 5.5	$0.00016	$0.00330
Haiku 4.5	$0.00008	$0.00165

Measured 4d ago against content hash a1294b61e7af, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sapiens-api scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/sapiens-sinteticos/skills/sapiens-api/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

API da conta: texto, imagem e vídeo em código

API ou MCP

Este connector opera a conta pela conversa. A API é outra porta: a pessoa chama os motores de texto, imagem e vídeo de dentro do código dela, no formato da OpenAI, e paga do saldo em DÓLAR da conta. As duas portas são da MESMA conta e se enxergam:

O que a API gera entra no acervo da conta. Imagem e vídeo viram peça marcada source: api (ache com sapiens_gallery e use como qualquer peça: referência, vídeo, publicar). Música e efeito sonoro viram faixa da conta (ache com sapiens_musicator action=list).
O saldo em dólar também paga peça por aqui: sapiens_image e sapiens_video action=create com pagarCom: "dolar" (detalhe nas skills imagem e video). Sinapse não vira dólar nem o contrário: são duas carteiras, e a pessoa escolhe de qual sai.

Use a API quando a pessoa quer automatizar fora da conversa (script, app, agente dela, lote). Pra operar a conta aqui, siga com as tools.

Onde fica

Tudo mora em Developers, no fim do menu do site: criar e revogar chave, teto de gasto por dia de cada chave, recarga (cartão ou USDC da carteira dela) e o extrato. Se a seção API não aparece lá, ela ainda não abriu pra conta.

A chave aparece UMA vez, na criação. Peça pra ela guardar numa variável de ambiente (SAPIENS_API_KEY). Nunca peça a chave no chat e nunca escreva a chave em código, commit ou log.

O manual inteiro

O manual de uso, com os campos, o vídeo e a tabela de erros, é servido pela própria API, sem chave:

GET https://www.sapiensinteticos.com/api/v1/skill

Baixe e leia ANTES de escrever o código. Num agente com pasta de skills, ele entra como .claude/skills/sapiens-api/SKILL.md. O manual de lá manda sobre este resumo quando os dois divergirem.

O que vale saber já

Base: https://www.sapiensinteticos.com/api/v1, com Authorization: Bearer <chave>. No SDK da OpenAI, só troque o baseURL.
Preço: o de cada modelo está em GET /models; vídeo cota de graça em POST /videos/quote. O valor de uma chamada pode variar um pouco com a oferta da hora. O valor de cada chamada volta no header x-sapiens-charge-usd. Pra pôr o preço da API ao lado de outro provedor (fal.ai, WaveSpeed): sapiens_meta action=precos, parte api.
Vídeo cota de graça antes (POST /videos/quote), aceita webhook_url pra avisar quando termina e devolve a url do mp4 guardado. Falha do motor volta pro saldo sozinha.
Saldo que acabou volta 402 insufficient_balance com recharge_url no erro: o código da pessoa deve mostrar esse link (recarga no cartão ou em stablecoin) em vez de só falhar.
Uma chamada de teste antes de qualquer lote. Nunca vídeo em laço.

Read the full file on GitHub · 67 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

4d ago First seen · 67 lines · 80 tokens per session scan A a1294b61e7af

Subscribe to this mod's changes

sapiens-api is a skill published in the GitHub repository inhabitants/sapiens-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 80 tokens to every session and 1,648 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-20.

Building agents Data and AI Prompting ai-studio brazil claude mcp model-context-protocol sapiens-sinteticos

opik-optimize

Improve a prompt with the Opik Agent Optimizer — resolve the prompt, a dataset, and a metric, pick the algorithm, run a bounded optimization, check the gain on held-out data, and save the winner as a new prompt version with the optimization run link. Runs via the opik-optimizer package; reads prompts and datasets via…

comet-ml/opik-mcp · 143 tokens

octave-ultra-mythic

Ultra-high density compression using mythological atoms and semantic shorthand. Preserves soul and constraints at 60% compression for identity transmission, binding protocols, and extreme token scarcity. REQUIRES octave-mastery and octave-compression.

elevanaltd/octave-mcp · 53 tokens

gigachat-chat

A chat command that sends a user prompt to GigaChat, an AI text-generation service, through MCP, a way for tools to connect to an agent. It can pass a model and temperature and reports the model and token counts.

theYahia/WWmcp · 21 tokens

mistral-router

Choose an available Mistral tool and model for document extraction, chat, code, vision, audio, or deployed workflows. Use when the user asks which Mistral capability fits a task or needs help routing it.

Swih/mistral-mcp · 49 tokens

model-context

MCP (Model Context Protocol) - Build AI-native servers with tools, resources, and prompts. TypeScript/Python SDKs for Claude Desktop integration.

bobmatnyc/claude-mpm-skills · 34 tokens

local-delegation

Regla y catálogo para delegar pasos mecánicos (resumir, clasificar, extraer, boilerplate, mensaje de commit desde un diff, traducir texto o archivo, resumir salida de lint/tests/CI, explicar código, describir una imagen, verificar si el backend local está disponible) a modelos locales vía las tools local del MCP…

ZahiriNatZuke/local-delegate · 138 tokens