API Reference

Genfity AI Gateway menyediakan satu endpoint yang kompatibel dengan format chat completions standar (OpenAI) dan Messages API (Anthropic) untuk mengakses semua model AI. Cukup ganti base URL dan gunakan API key Genfity.

BASE URL (OpenAI)	https://ai.genfity.com/v1
BASE URL (Anthropic)	https://ai.genfity.com

Quick start

Quick startcurl

curl https://ai.genfity.com/v1/models \
  -H "Authorization: Bearer genfity_xxxxxxxxxxxx"

Authentication

Semua request memerlukan API key yang dikirim via header Authorization. Dapatkan API key di Dashboard → API Keys.

Header	Type	Description
Authorization	string required	API Key dalam format Bearer <api_key>. Dapatkan di dashboard.

Examplebash

curl https://ai.genfity.com/v1/chat/completions \
  -H "Authorization: Bearer genfity_xxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{"model":"genfity/claude-opus-4.7","messages":[{"role":"user","content":"Hello"}]}'

Endpoints

Kirim request ke model AI manapun melalui endpoint berikut.

POST/v1/chat/completionsOpenAI-compatible chat completion

POST/v1/messagesAnthropic-compatible messages

POST/v1/messages/count_tokensEstimasi token count

POST/v1/embeddingsVector embeddings

GET/v1/modelsDaftar model tersedia

POST

Create Chat Completion (OpenAI)

/v1/chat/completions

Kirim request chat completion OpenAI-compatible ke model AI manapun di catalog Genfity.

Headers

Authorization	string required	API Key dalam format Bearer <api_key>.
Content-Type	string required	Harus application/json.

Request Body

model	string required	ID model dari catalog. Lihat /v1/models.
messages	array required	Array objek pesan dengan role dan content.
stream	boolean	Aktifkan SSE streaming. Default false.
max_tokens	integer	Jumlah maksimum token output.
temperature	number	Sampling temperature (0-2).
top_p	number	Nucleus sampling (0-1).
tools	array	Definisi tool calling format OpenAI.
response_format	object	Format output, mis. { type: json_object }.

Requestcurl

curl -X POST https://ai.genfity.com/v1/chat/completions \
  -H "Authorization: Bearer genfity_xxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "genfity/claude-opus-4.7",
    "messages": [
      { "role": "user", "content": "Apa ibukota Indonesia?" }
    ],
    "temperature": 0.7,
    "max_tokens": 256,
    "stream": false
  }'

Responsejson

{
  "id": "chatcmpl_01Hxx...",
  "object": "chat.completion",
  "created": 1778803200,
  "model": "genfity/claude-opus-4.7",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Ibukota Indonesia adalah Jakarta."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 8,
    "total_tokens": 22
  }
}

POST

Anthropic Messages

/v1/messages

Kirim request Anthropic-compatible ke model AI manapun. Cocok untuk Claude SDK dan tool yang membutuhkan Messages API.

Headers

Authorization	string required	API Key dalam format Bearer <api_key>.
Content-Type	string required	Harus application/json.

Request Body

model	string required	ID model dari catalog.
max_tokens	integer required	Jumlah maksimum token output.
messages	array required	Array pesan dengan role dan content.
system	string	System prompt (opsional).
stream	boolean	Aktifkan SSE streaming.
tools	array	Definisi tools dengan input_schema.
tool_choice	object	Kontrol tool yang dipanggil.

Requestcurl

curl -X POST https://ai.genfity.com/v1/messages \
  -H "Authorization: Bearer genfity_xxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "genfity/claude-opus-4.7",
    "max_tokens": 1024,
    "messages": [
      { "role": "user", "content": "Hello Genfity" }
    ]
  }'

Responsejson

{
  "id": "msg_01Hxx...",
  "type": "message",
  "role": "assistant",
  "model": "genfity/claude-opus-4.7",
  "content": [
    { "type": "text", "text": "Hello! How can I help you today?" }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 25,
    "output_tokens": 12
  }
}

POST

Count Tokens

/v1/messages/count_tokens

Estimasi jumlah token dari prompt sebelum mengirim request generation.

Headers

Authorization

string required

API Key dalam format Bearer <api_key>.

Request Body

model	string required	ID model dari catalog.
messages	array required	Array pesan untuk dihitung.

Requestcurl

curl -X POST https://ai.genfity.com/v1/messages/count_tokens \
  -H "Authorization: Bearer genfity_xxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "genfity/claude-opus-4.7",
    "messages": [{"role":"user","content":"Count this text"}]
  }'

Responsejson

{
  "input_tokens": 12
}

POST

Embeddings

/v1/embeddings

Hasilkan vector embedding dari input text. Hanya tersedia untuk model embedding di catalog.

Headers

Authorization

string required

API Key dalam format Bearer <api_key>.

Request Body

model	string required	ID model embedding dari catalog.
input	string \| array required	Text atau array text untuk di-embed.

Requestcurl

curl -X POST https://ai.genfity.com/v1/embeddings \
  -H "Authorization: Bearer genfity_xxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "genfity/claude-opus-4.7",
    "input": "Genfity AI Gateway makes AI integration simple."
  }'

Responsejson

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0023, -0.0091, 0.0042, ...]
    }
  ],
  "model": "genfity/claude-opus-4.7",
  "usage": { "prompt_tokens": 8, "total_tokens": 8 }
}

POST

Image Generation

/v1/images/generations

Generate gambar dari text prompt menggunakan model image generation seperti GPT Image, FLUX, Stable Diffusion, dan lainnya.

Headers

Authorization	string required	API Key dalam format Bearer <api_key>.
Content-Type	string required	Harus application/json.

Request Body

model	string required	ID model image, mis. openai/gpt-image-2, together/black-forest-labs/FLUX.2-pro, flux-kontext.
prompt	string required	Deskripsi gambar yang ingin di-generate.
n	integer	Jumlah gambar (default 1).
size	string	Ukuran gambar, mis. 1024x1024, 1024x1792.
quality	string	Kualitas: standard atau hd.
response_format	string	Format output: url atau b64_json.

Requestcurl

curl -X POST https://ai.genfity.com/v1/images/generations \
  -H "Authorization: Bearer genfity_xxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-image-2",
    "prompt": "A beautiful sunset over Indonesian rice terraces",
    "n": 1,
    "size": "1024x1024"
  }'

Responsejson

{
  "created": 1778803200,
  "data": [
    {
      "url": "https://...",
      "revised_prompt": "A beautiful sunset over Indonesian rice terraces"
    }
  ]
}

GET

List Models

/v1/models

Dapatkan daftar semua model yang tersedia di akun Anda.

Headers

Authorization

string required

API Key dalam format Bearer <api_key>.

Requestcurl

curl https://ai.genfity.com/v1/models \
  -H "Authorization: Bearer genfity_xxxxxxxxxxxx"

Responsejson

{
  "object": "list",
  "data": [
    { "id": "genfity/claude-opus-4.7", "object": "model", "owned_by": "genfity" }
  ]
}

Model & harga

Daftar model yang didukung gateway dan harga per 1M token. Data diambil langsung dari database catalog aktif.

Memuat model dari database...

Error Codes

Genfity AI Gateway menggunakan HTTP status code standar.

Code	Message	Meaning
400	`invalid_json`	Body bukan JSON valid.
400	`missing_model`	Field model kosong.
400	`model_not_allowed`	Model tidak ada/aktif di catalog.
400	`max_tokens_required`	PAYG/credit butuh batas max_tokens.
401	`missing_api_key`	Authorization header kosong.
401	`invalid_api_key_format`	Header bukan Bearer token.
401	`invalid_api_key`	Key tidak valid atau revoked.
402	`no_active_subscription`	Key tanpa subscription aktif.
402	`subscription_not_covering_model`	Plan tidak cover model ini.
402	`credit_cost_not_configured`	Model belum punya credit cost.
402	`payg_price_not_configured`	Model belum punya PAYG price.
402	`insufficient_credit_balance`	Saldo credit tidak cukup.
402	`insufficient_balance`	Saldo tidak cukup.
403	`forbidden`	Tidak punya akses ke model ini.
429	`rate_limit_exceeded`	RPM/TPM/concurrency limit terlampaui.
429	`quota_exceeded`	Quota token periode habis.
429	`global_rate_limit_exceeded`	IP burst guard terlampaui.
500	`internal_error`	Masalah di sisi gateway.
502	`router_unavailable`	Model/provider sedang high traffic. Coba lagi nanti.
502	`upstream_error`	Model/provider sedang high traffic. Coba lagi nanti.
502	`all_candidates_failed`	Model/provider sedang high traffic. Coba lagi nanti.
503	`service_unavailable`	Layanan sedang maintenance.

Rate Limits

Batas permintaan diatur per API key dari Dashboard → API Keys. Saat batas terlampaui, API mengembalikan 429 Too Many Requests.

Per-key limits

• rate_limit_per_min — Request per menit per key
• quota_tokens_monthly — Quota token bulanan
• concurrent_limit — Request bersamaan

Global IP guard

• Window: 1 minute
• Scope: IP + endpoint path
• Error: global_rate_limit_exceeded

IDE & Editor

Genfity AI Gateway memakai format OpenAI-compatible dan Anthropic-compatible, jadi hampir semua IDE, CLI, dan SDK yang mendukung custom base URL bisa langsung dipakai. Ganti base URL dan gunakan API key dari Dashboard.

Cline

Autonomous coding agent for VS Code

Cline mendukung provider OpenAI Compatible. Cukup isi base URL, API key, dan model ID di panel Settings.

Setup

1Install extension Cline dari VS Code Marketplace.
2Buka panel Cline (sidebar kiri), klik ikon Settings.
3API Provider → pilih OpenAI Compatible.
4Isi field sesuai snippet di kanan, klik Done.

https://cline.bot

Clineini

API Provider   = OpenAI Compatible
Base URL       = https://ai.genfity.com/v1
API Key        = genfity_xxxxxxxxxxxx
Model ID       = genfity/claude-opus-4.7

Roo Code

Cline fork with multi-mode agents

Roo Code (cabang dari Cline) memakai konfigurasi yang sama — pilih OpenAI Compatible lalu isi base URL dan key Genfity.

Setup

1Install extension Roo Code dari VS Code Marketplace.
2Buka panel Roo Code, klik ikon Settings atau nama profil.
3API Provider: OpenAI Compatible (bukan OpenAI).
4Simpan profil, pilih mode (Code/Architect/Ask) lalu mulai prompt.

https://roocode.com

Roo Codeini

API Provider   = OpenAI Compatible
Base URL       = https://ai.genfity.com/v1
API Key        = genfity_xxxxxxxxxxxx
Model ID       = genfity/claude-opus-4.7

Continue.dev

Autopilot for VS Code & JetBrains

Continue memakai file ~/.continue/config.yaml untuk deklarasi provider. Tambahkan entry openai-compatible dengan apiBase Genfity.

Setup

1Install extension Continue di VS Code / JetBrains.
2Buka ~/.continue/config.yaml (Continue: Open Config).
3Tambahkan model Genfity pada key models.
4Reload — model akan muncul di dropdown chat Continue.

https://continue.dev

Continue.devyaml

models:
  - name: Genfity Claude Opus
    provider: openai
    model: genfity/claude-opus-4.7
    apiBase: https://ai.genfity.com/v1
    apiKey: genfity_xxxxxxxxxxxx
    roles:
      - chat
      - edit
      - apply

Cursor

AI-native code editor

Cursor mendukung Override OpenAI Base URL di Settings → Models. Aktifkan OpenAI API Key, lalu arahkan base URL ke Genfity.

Setup

1Cursor Settings → Models → scroll ke OpenAI API Key.
2Masukkan API key: genfity_xxxxxxxxxxxx.
3Expand section → enable Override OpenAI Base URL.
4Isi base URL: https://ai.genfity.com/v1. Klik Verify.
5Centang hanya model yang tersedia di Genfity catalog.

https://cursor.com

Cursorini

OpenAI API Key           = genfity_xxxxxxxxxxxx
Override Base URL        = https://ai.genfity.com/v1
Enabled Models           = genfity/claude-opus-4.7, ...

Windsurf (Codeium)

Agentic IDE by Codeium

Windsurf Cascade mendukung custom model endpoint. Tambah provider OpenAI-compatible via Settings → Cascade → Add Custom Model.

Setup

1Settings (Cmd/Ctrl + ,) → Cascade → Models.
2Add Custom Model → pilih protokol OpenAI.
3Isi Base URL + API Key Genfity + Model ID.
4Aktifkan model baru lalu mulai sesi Cascade.

https://windsurf.com

Windsurf (Codeium)ini

Protocol     = OpenAI
Endpoint     = https://ai.genfity.com/v1
API Key      = genfity_xxxxxxxxxxxx
Model ID     = genfity/claude-opus-4.7
Display Name = Genfity Claude Opus

Zed

High-performance collaborative editor

Zed mendukung OpenAI API Compatible provider via settings.json. Tambahkan Genfity sebagai custom provider, lalu simpan API key melalui Agent Panel settings.

Setup

1Zed → Cmd/Ctrl + , → buka settings.json.
2Tambahkan key language_models.openai_compatible seperti snippet.
3Buka Agent Panel settings (Cmd/Ctrl + Shift + P → agent: open settings).
4Cari provider "Genfity AI Gateway", paste API key, tekan Enter.
5Pilih model Genfity di dropdown model Agent Panel.

https://zed.dev

Zedjson

{
  "language_models": {
    "openai_compatible": {
      "Genfity AI Gateway": {
        "api_url": "https://ai.genfity.com/v1",
        "available_models": [
          {
            "name": "genfity/auto",
            "display_name": "Genfity Auto (Combo)",
            "max_tokens": 200000,
            "capabilities": {
              "tools": true,
              "images": true
            }
          },
          {
            "name": "genfity/claude-opus-4.7",
            "display_name": "Genfity Claude Opus 4.7",
            "max_tokens": 200000,
            "capabilities": {
              "tools": true,
              "images": true
            }
          },
          {
            "name": "genfity/claude-haiku-4.5",
            "display_name": "Genfity Claude Haiku 4.5",
            "max_tokens": 200000,
            "capabilities": {
              "tools": true,
              "images": true
            }
          }
        ]
      }
    }
  },
  "agent": {
    "default_model": {
      "provider": "openai_compatible",
      "model": "genfity/auto"
    }
  }
}

Kilo Code

Open-source AI agent for VS Code

Kilo Code mendukung provider OpenAI Compatible. Isi base URL, API key, dan model ID Genfity di panel Settings.

Setup

1Install extension Kilo Code dari VS Code Marketplace.
2Buka panel Kilo Code → Settings.
3API Provider → pilih OpenAI Compatible.
4Isi Base URL + API Key + Model, klik Save lalu Done.

https://kilocode.ai

Kilo Codeini

API Provider   = OpenAI Compatible
Base URL       = https://ai.genfity.com/v1
API Key        = genfity_xxxxxxxxxxxx
Model          = genfity/claude-opus-4.7

TRAE

ByteDance AI-native IDE

TRAE bisa menambah model OpenAI-compatible custom. Gunakan protokol OpenAI dengan base URL dan key Genfity.

Setup

1Buka Settings (ikon di kanan atas chat) → Models.
2Klik + Add Model → pilih protokol/Provider OpenAI Compatible.
3Isi Base URL = https://ai.genfity.com/v1, API Key, dan Model = genfity/claude-opus-4.7.
4Klik Add Model lalu pilih model tersebut di chat.

https://trae.ai

TRAEini

Provider   = OpenAI Compatible
Base URL   = https://ai.genfity.com/v1
API Key    = genfity_xxxxxxxxxxxx
Model      = genfity/claude-opus-4.7

Xcode

Apple's IDE with Coding Intelligence

Xcode 26+ mendukung Internet Hosted model provider. Pakai host Genfity dengan header Authorization: Bearer.

Setup

1Xcode → Settings → Intelligence → Add a Model Provider.
2Pilih tab Internet Hosted.
3URL = https://ai.genfity.com (bare host, tanpa /v1). API Key Header = Authorization.
4API Key = Bearer genfity_xxxxxxxxxxxx (kata Bearer, spasi, lalu key).
5Klik Add, aktifkan model genfity/claude-opus-4.7, tekan Cmd+0 untuk mulai.

https://developer.apple.com/xcode/

Xcodeini

URL             = https://ai.genfity.com
API Key Header  = Authorization
API Key         = Bearer genfity_xxxxxxxxxxxx
Description      = Genfity AI Gateway
Model            = genfity/claude-opus-4.7

CLI & Terminal

Claude Code

Anthropic's official CLI

Claude Code memakai Anthropic-compatible endpoint. Cara paling stabil adalah menaruh blok env di ~/.claude/settings.json (bukan export sekali pakai). Kosongkan dulu ANTHROPIC_AUTH_TOKEN & ANTHROPIC_BASE_URL yang lama karena environment variable menimpa settings.json.

Prasyarat: Node.js 18+. Windows sebaiknya lewat WSL atau Git for Windows; macOS pakai nvm (hindari install package langsung agar tidak kena masalah permission).

Setup

1PENTING — bersihkan env lama: environment variable menimpa settings.json. macOS/Linux: unset ANTHROPIC_AUTH_TOKEN ANTHROPIC_BASE_URL lalu hapus baris export di ~/.bashrc atau ~/.zshrc. Windows PowerShell: [Environment]::SetEnvironmentVariable('ANTHROPIC_BASE_URL',$null,'User').
2Edit atau buat ~/.claude/settings.json (Windows: C:\Users\<user>\.claude\settings.json), isi blok env di panel Konfigurasi.
3(Opsional) Skip login Anthropic: set "hasCompletedOnboarding": true di ~/.claude.json agar tidak mencoba konek ke api.anthropic.com.
4Buka terminal BARU (agar config terbaca), cd ke project, jalankan claude, pilih Trust This Folder. Cek dengan /status bahwa ANTHROPIC_BASE_URL menunjuk ke Genfity.

https://claude.com/claude-code

Install

bash

npm install -g @anthropic-ai/claude-code
claude --version

Konfigurasi

Claude Codejson

{
  "env": {
    "ANTHROPIC_BASE_URL": "https://ai.genfity.com",
    "ANTHROPIC_AUTH_TOKEN": "genfity_xxxxxxxxxxxx",
    "ANTHROPIC_MODEL": "genfity/claude-opus-4.7",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "genfity/claude-opus-4.7",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "genfity/claude-opus-4.7",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "genfity/claude-haiku-4.5",
    "ANTHROPIC_SMALL_FAST_MODEL": "genfity/claude-haiku-4.5",
    "API_TIMEOUT_MS": "3000000"
  }
}

opencode

AI coding agent in your terminal (SST)

opencode adalah agent coding open source berbasis TUI. Tambahkan Genfity sebagai provider OpenAI-compatible.

Setup

1Buat ~/.config/opencode/opencode.json (global) atau opencode.json di root project (Windows: %USERPROFILE%\.config\opencode\opencode.json).
2Set API key sebagai env GENFITY_KEY. macOS/Linux: export GENFITY_KEY="KEY" di ~/.zshrc/~/.bashrc. Windows PowerShell: [Environment]::SetEnvironmentVariable('GENFITY_KEY','KEY','User').
3Jalankan opencode di terminal, pilih provider Genfity dari daftar model.

https://opencode.ai

Install

bash

curl -fsSL https://opencode.ai/install | bash

Konfigurasi

opencodejson

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "genfity": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Genfity",
      "options": {
        "baseURL": "https://ai.genfity.com/v1",
        "apiKey": "{env:GENFITY_KEY}"
      },
      "models": {
        "genfity/claude-opus-4.7": { "name": "Claude Opus 4.7" }
      }
    }
  }
}

Codex CLI

OpenAI Codex CLI agent

Codex CLI mendukung provider OpenAI-compatible melalui ~/.codex/config.toml. Gateway Genfity memakai Chat/Completions, jadi wajib wire_api = "chat" — versi Codex terbaru default ke Responses API yang belum didukung gateway.

Prasyarat: Node.js 18+. Gateway Genfity hanya serve Chat/Completions, jadi wire_api = "chat" WAJIB — Codex terbaru default ke Responses API yang belum didukung.

Setup

1Set API key sebagai environment variable GENFITY_KEY (lihat panel Set API key).
2Edit ~/.codex/config.toml (Windows: C:\Users\<user>\.codex\config.toml) — tambah blok di panel Konfigurasi. wire_api = "chat" WAJIB.
3Kalau muncul error "wire_api = chat is no longer supported" di Codex terbaru, downgrade: npm install -g @openai/[email protected].
4Restart Codex, lalu jalankan codex di root project (model & provider terbaca otomatis dari config).

https://github.com/openai/codex

Install

bash

npm i -g @openai/codex
codex --version

Konfigurasi

Codex CLItoml

model = "genfity/claude-opus-4.7"
model_provider = "genfity"
model_context_window = 200000

[model_providers.genfity]
name = "Genfity"
base_url = "https://ai.genfity.com/v1"
env_key = "GENFITY_KEY"
wire_api = "chat"

Set API key (GENFITY_KEY)

Set API key (GENFITY_KEY)bash

# macOS / Linux (zsh)
echo 'export GENFITY_KEY="genfity_xxxxxxxxxxxx"' >> ~/.zshrc
source ~/.zshrc

# Windows PowerShell
[Environment]::SetEnvironmentVariable('GENFITY_KEY','genfity_xxxxxxxxxxxx','User')

Windows: buka PowerShell baru setelah set env agar terbaca.

Aider

AI pair programming in your terminal

Aider membaca variable environment OpenAI-style. Override OPENAI_API_BASE dan OPENAI_API_KEY untuk Genfity.

Prasyarat: Python 3.8+. Prefix model openai/ wajib agar Aider mengarahkan ke endpoint OpenAI-compatible.

Setup

1Set env OpenAI-style (lihat panel Konfigurasi). Atau taruh di .aider.conf.yml / .env. Windows PowerShell: [Environment]::SetEnvironmentVariable('OPENAI_API_BASE','...','User') dan sama untuk OPENAI_API_KEY.
2Jalankan di root project: aider --model openai/genfity/claude-opus-4.7.

https://aider.chat

Install

bash

pipx install aider-chat

Konfigurasi

Aiderbash

export OPENAI_API_BASE="https://ai.genfity.com/v1"
export OPENAI_API_KEY="genfity_xxxxxxxxxxxx"

aider --model openai/genfity/claude-opus-4.7

LLM (Simon Willison)

Versatile CLI + Python library for any LLM

LLM CLI memakai plugin llm-openai-plugin untuk provider OpenAI-compatible. Daftarkan Genfity sebagai model baru.

Prasyarat: Python 3.8+.

Setup

1Simpan API key: llm keys set genfity lalu tempel genfity_xxxxxxxxxxxx.
2Cari lokasi config: dirname "$(llm logs path)". Edit extra-openai-models.yaml di folder itu (buat kalau belum ada), isi seperti panel Konfigurasi.
3Test: llm -m genfity/claude-opus 'hello'.

https://llm.datasette.io

Install

bash

pipx install llm
llm install llm-openai-plugin

Konfigurasi

LLM (Simon Willison)yaml

- model_id: genfity/claude-opus
  model_name: genfity/claude-opus-4.7
  api_base: "https://ai.genfity.com/v1"
  api_key_name: genfity
  can_stream: true

Goose

Block's agentic CLI + desktop

Goose mendukung provider Anthropic Compatible. Arahkan Base URL ke endpoint Anthropic Genfity (tanpa /v1).

Setup

1Buka Goose → Create New Provider → pilih Anthropic Compatible.
2Isi Base URL = https://ai.genfity.com (tanpa /v1), API Key = genfity_xxxxxxxxxxxx, Model = genfity/claude-opus-4.7.
3Simpan, lalu Switch Models di layar utama dan pilih provider Genfity.

https://block.github.io/goose/

Install

bash

curl -fsSL https://github.com/block/goose/releases/download/stable/download_cli.sh | bash

Konfigurasi

Gooseini

Provider  = Anthropic Compatible
Base URL  = https://ai.genfity.com
API Key   = genfity_xxxxxxxxxxxx
Model     = genfity/claude-opus-4.7

Crush

Charm's terminal coding agent (CLI + TUI)

Crush memakai ~/.config/crush/crush.json untuk deklarasi provider OpenAI-compatible. Tambahkan Genfity di key providers.

Setup

1Edit ~/.config/crush/crush.json (Windows: %USERPROFILE%\.config\crush\crush.json). Buat foldernya kalau belum ada.
2Tambah blok providers.genfity seperti panel Konfigurasi.
3Restart crush, tekan Ctrl+P → Switch Model → pilih model Genfity.

https://github.com/charmbracelet/crush

Install

bash

brew install charmbracelet/tap/crush

Konfigurasi

Crushjson

{
  "providers": {
    "genfity": {
      "id": "genfity",
      "name": "Genfity AI Gateway",
      "base_url": "https://ai.genfity.com/v1",
      "type": "openai",
      "api_key": "genfity_xxxxxxxxxxxx",
      "models": [
        { "id": "genfity/claude-opus-4.7", "name": "Genfity Claude Opus 4.7" }
      ]
    }
  }
}

Droid (Factory)

Factory's terminal coding agent

Droid memakai ~/.factory/config.json untuk custom model. Pakai provider anthropic dengan base URL Genfity.

Prasyarat: Kosongkan ANTHROPIC_AUTH_TOKEN — env itu menimpa api_key di config.json. macOS/Linux: unset ANTHROPIC_AUTH_TOKEN. Windows PowerShell: [Environment]::SetEnvironmentVariable('ANTHROPIC_AUTH_TOKEN',$null,'User').

Setup

1Edit ~/.factory/config.json (bukan settings.json; Windows: C:\Users\<user>\.factory\config.json) — tambah entry custom_models di panel Konfigurasi.
2Jalankan droid, ketik /model lalu pilih Genfity.

https://factory.ai

Install

bash

curl -fsSL https://app.factory.ai/cli | sh

Konfigurasi

Droid (Factory)json

{
  "custom_models": [
    {
      "model_display_name": "Genfity Claude Opus 4.7",
      "model": "genfity/claude-opus-4.7",
      "base_url": "https://ai.genfity.com",
      "api_key": "genfity_xxxxxxxxxxxx",
      "provider": "anthropic",
      "max_tokens": 64000
    }
  ]
}

Qwen Code

Alibaba's terminal coding agent

Qwen Code membaca variable environment OpenAI-style. Override OPENAI_BASE_URL, OPENAI_API_KEY, dan OPENAI_MODEL untuk Genfity.

Prasyarat: Node.js 20+.

Setup

1Set env OpenAI-style (lihat panel Konfigurasi). Windows PowerShell: [Environment]::SetEnvironmentVariable('OPENAI_BASE_URL','...','User') dan sama untuk OPENAI_API_KEY / OPENAI_MODEL.
2Buka terminal baru, jalankan qwen di root project. Kalau ditanya provider, pilih OpenAI-compatible dan konfirmasi model ID.

https://github.com/QwenLM/qwen-code

Install

bash

npm i -g @qwen-code/qwen-code

Konfigurasi

Qwen Codebash

export OPENAI_BASE_URL="https://ai.genfity.com/v1"
export OPENAI_API_KEY="genfity_xxxxxxxxxxxx"
export OPENAI_MODEL="genfity/claude-opus-4.7"

qwen

Grok CLI

Terminal agent (OpenAI-compatible)

Grok CLI memakai variable GROK_BASE_URL dan GROK_API_KEY. Arahkan ke endpoint OpenAI-compatible Genfity.

Prasyarat: Node.js 18+. Kosongkan OPENAI_API_KEY & OPENAI_BASE_URL agar tidak bentrok. macOS/Linux: unset OPENAI_API_KEY OPENAI_BASE_URL. Windows PowerShell: [Environment]::SetEnvironmentVariable('OPENAI_API_KEY',$null,'User').

Setup

1Set env Grok (lihat panel Konfigurasi). Windows PowerShell: [Environment]::SetEnvironmentVariable('GROK_BASE_URL','...','User') dan sama untuk GROK_API_KEY.
2Buka terminal baru, jalankan grok --model genfity/claude-opus-4.7.

https://github.com/superagent-ai/grok-cli

Install

bash

npm i -g @vibe-kit/grok-cli

Konfigurasi

Grok CLIbash

export GROK_BASE_URL="https://ai.genfity.com/v1"
export GROK_API_KEY="genfity_xxxxxxxxxxxx"

grok --model genfity/claude-opus-4.7

OpenHands

Open-source AI software agent

OpenHands memakai prefix openai/ untuk endpoint OpenAI-compatible. Set llm_base_url ke Genfity.

Prasyarat: Python 3.12+. Model WAJIB berprefix openai/. Di Windows disarankan lewat WSL.

Setup

1Konfigurasi LLM lewat env (LLM_MODEL/LLM_BASE_URL/LLM_API_KEY) atau config.toml — lihat panel Konfigurasi.
2Jalankan openhands lalu buka UI di http://localhost:3000.

https://github.com/All-Hands-AI/OpenHands

Install

bash

pipx install openhands

Konfigurasi

OpenHandsini

llm_model="openai/genfity/claude-opus-4.7"
llm_base_url="https://ai.genfity.com/v1"
llm_api_key="genfity_xxxxxxxxxxxx"

openhands

OpenClaw

Open-source personal AI assistant (WA/Telegram/Discord)

OpenClaw memakai provider anthropic-messages di ~/.openclaw/openclaw.json. Daftarkan Genfity sebagai provider lalu restart gateway.

Prasyarat: Node.js 22.19+. auth.mode none hanya untuk lokal 1 mesin; untuk akses remote jalankan openclaw doctor --fix.

Setup

1Jalankan wizard: openclaw onboard. Untuk provider pilih Skip for now (didaftarkan manual di langkah berikut).
2Edit ~/.openclaw/openclaw.json (Windows: %USERPROFILE%\.openclaw\openclaw.json) — tambah provider genfity dari panel Konfigurasi. Pakai mode: merge agar config lain aman; jangan timpa seluruh file.
3Set agents.defaults.model.primary ke genfity/claude-opus-4.7.
4Terapkan: openclaw gateway restart. Channel WhatsApp/Telegram/Discord dikonfigurasi terpisah setelah gateway jalan.

https://openclaw.ai

Install

bash

curl -fsSL https://openclaw.ai/install.sh | bash

Konfigurasi

OpenClawjson

{
  "models": {
    "mode": "merge",
    "providers": {
      "genfity": {
        "baseUrl": "https://ai.genfity.com",
        "apiKey": "genfity_xxxxxxxxxxxx",
        "api": "anthropic-messages",
        "models": [
          {
            "id": "genfity/claude-opus-4.7",
            "name": "Genfity Claude Opus 4.7",
            "input": ["text", "image"],
            "contextWindow": 200000,
            "maxTokens": 64000
          }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "model": { "primary": "genfity/claude-opus-4.7" }
    }
  }
}

Desktop & Web UI

LibreChat

Self-hosted multi-model chat UI

LibreChat memakai librechat.yaml untuk mendaftarkan endpoint custom. Tambah Genfity sebagai custom endpoint.

Setup

1Salin librechat.example.yaml → librechat.yaml (root deploy).
2Tambah blok endpoints.custom seperti di kanan.
3Set GENFITY_KEY di .env (di-mount ke container).
4Restart container: docker compose up -d.

https://librechat.ai

LibreChatyaml

version: 1.0.9
endpoints:
  custom:
    - name: "Genfity"
      apiKey: "${GENFITY_KEY}"
      baseURL: "https://ai.genfity.com/v1"
      models:
        default: ["genfity/claude-opus-4.7"]
        fetch: true
      titleModel: "genfity/claude-haiku-4.5"
      summarize: false
      forcePrompt: false

Open WebUI

Extensible ChatGPT-style web UI

Open WebUI bisa menambah multiple OpenAI-compatible connection di Admin Settings.

Setup

1Login sebagai admin → Admin Panel → Settings → Connections.
2OpenAI API → klik + untuk tambah koneksi baru.
3Isi: API Base URL = https://ai.genfity.com/v1, API Key = genfity_xxxxxxxxxxxx.
4Save → model Genfity muncul di dropdown Workspace.

https://openwebui.com

Open WebUIini

API Base URL = https://ai.genfity.com/v1
API Key      = genfity_xxxxxxxxxxxx
Prefix ID    = genfity (optional)

Chatbox

Cross-platform desktop AI client

Chatbox mendukung custom OpenAI host. Buka Settings → AI Model → pilih OpenAI API dan isi host + key Genfity.

Setup

1Download Chatbox (macOS/Windows/Linux) atau pakai versi web.
2Settings → Model → AI Provider = OpenAI API.
3Isi API Key + API Host = https://ai.genfity.com/v1.
4Pilih Model = genfity/claude-opus-4.7 → Save.

https://chatboxai.app

Chatboxini

AI Provider = OpenAI API
API Key     = genfity_xxxxxxxxxxxx
API Host    = https://ai.genfity.com/v1
Model       = genfity/claude-opus-4.7

Jan

Offline-first personal AI

Jan mendukung remote provider via Settings → Model Providers → OpenAI.

Setup

1Settings → Model Providers → OpenAI.
2Isi API Key = genfity_xxxxxxxxxxxx, Base URL = https://ai.genfity.com/v1.
3Tab Models → import model dengan ID genfity/claude-opus-4.7.
4Mulai thread baru dan pilih model Genfity.

https://jan.ai

Janini

Provider  = OpenAI (compatible)
Base URL  = https://ai.genfity.com/v1
API Key   = genfity_xxxxxxxxxxxx
Model ID  = genfity/claude-opus-4.7

LM Studio

Desktop UI for local + remote LLMs

LM Studio mendukung remote OpenAI-compatible endpoint lewat fitur Connect to a server.

Setup

1LM Studio → ikon Chat → klik Select a model.
2Dropdown → Server settings → Add remote endpoint.
3Base URL = https://ai.genfity.com/v1, API Key = genfity_xxxxxxxxxxxx.
4Klik Load → pilih model genfity/claude-opus-4.7.

https://lmstudio.ai

LM Studioini

Base URL = https://ai.genfity.com/v1
API Key  = genfity_xxxxxxxxxxxx
Model    = genfity/claude-opus-4.7

Cherry Studio

Multi-provider desktop AI client

Cherry Studio bisa menambah provider OpenAI-compatible custom. Isi API host + key Genfity lalu tambah model.

Setup

1Settings → Model Providers → Add Provider → pilih tipe OpenAI.
2Isi API Host = https://ai.genfity.com/v1, API Key = genfity_xxxxxxxxxxxx.
3Klik Check untuk verifikasi, lalu Add Model = genfity/claude-opus-4.7.
4Pilih model Genfity di dropdown chat.

https://cherry-ai.com

Cherry Studioini

Provider  = OpenAI (compatible)
API Host  = https://ai.genfity.com/v1
API Key   = genfity_xxxxxxxxxxxx
Model     = genfity/claude-opus-4.7

SDK & Framework

OpenAI Python SDK

Official Python client

OpenAI Python SDK menerima argument base_url. Cukup ganti base URL dan API key.

Setup

1Install: pip install openai.
2Instansiasi client dengan base URL Genfity.
3Panggil chat.completions.create(...) seperti biasa.

https://github.com/openai/openai-python

OpenAI Python SDKpython

from openai import OpenAI

client = OpenAI(
    api_key="genfity_xxxxxxxxxxxx",
    base_url="https://ai.genfity.com/v1",
)

res = client.chat.completions.create(
    model="genfity/claude-opus-4.7",
    messages=[{"role": "user", "content": "Hello Genfity"}],
)
print(res.choices[0].message.content)

OpenAI Node SDK

Official TypeScript / Node client

OpenAI Node SDK menerima baseURL saat instansiasi. Kompatibel penuh dengan chat completions Genfity.

Setup

1Install: npm i openai.
2Set env GENFITY_KEY, lalu pakai seperti snippet.

https://github.com/openai/openai-node

OpenAI Node SDKtypescript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.GENFITY_KEY,
  baseURL: "https://ai.genfity.com/v1",
});

const res = await client.chat.completions.create({
  model: "genfity/claude-opus-4.7",
  messages: [{ role: "user", content: "Hello Genfity" }],
});
console.log(res.choices[0].message.content);

Anthropic Python SDK

Official Anthropic Python client

Anthropic Python SDK menerima argument base_url. Pakai endpoint /v1/messages Genfity.

Setup

1Install: pip install anthropic.
2Instansiasi client dengan base URL Genfity (tanpa /v1).
3Panggil messages.create(...) seperti biasa.

https://github.com/anthropics/anthropic-sdk-python

Anthropic Python SDKpython

import anthropic

client = anthropic.Anthropic(
    api_key="genfity_xxxxxxxxxxxx",
    base_url="https://ai.genfity.com",
)

message = client.messages.create(
    model="genfity/claude-opus-4.7",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello Genfity"}],
)
print(message.content[0].text)

Anthropic Node SDK

Official Anthropic TypeScript client

Anthropic Node SDK menerima baseURL saat instansiasi. Pakai endpoint /v1/messages Genfity.

Setup

1Install: npm i @anthropic-ai/sdk.
2Instansiasi client dengan base URL Genfity (tanpa /v1).
3Panggil messages.create(...) seperti biasa.

https://github.com/anthropics/anthropic-sdk-typescript

Anthropic Node SDKtypescript

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: process.env.GENFITY_KEY,
  baseURL: "https://ai.genfity.com",
});

const message = await client.messages.create({
  model: "genfity/claude-opus-4.7",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello Genfity" }],
});
console.log(message.content[0].text);

LangChain

LLM orchestration framework

Gunakan ChatOpenAI dengan base_url Genfity — pola identik dengan OpenAI langsung.

Setup

1Install: pip install langchain-openai.
2Instansiasi ChatOpenAI dengan base_url + api_key.

https://python.langchain.com

LangChainpython

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="genfity/claude-opus-4.7",
    api_key="genfity_xxxxxxxxxxxx",
    base_url="https://ai.genfity.com/v1",
    temperature=0.2,
)

print(llm.invoke("Hello Genfity").content)

Vercel AI SDK

TypeScript toolkit for AI apps

Gunakan @ai-sdk/openai dengan helper createOpenAI({ baseURL }).

Setup

1Install: npm i ai @ai-sdk/openai.
2Panggil createOpenAI dengan baseURL Genfity.

https://sdk.vercel.ai

Vercel AI SDKtypescript

import { createOpenAI } from "@ai-sdk/openai";
import { generateText } from "ai";

const genfity = createOpenAI({
  apiKey: process.env.GENFITY_KEY!,
  baseURL: "https://ai.genfity.com/v1",
});

const { text } = await generateText({
  model: genfity("genfity/claude-opus-4.7"),
  prompt: "Hello Genfity",
});
console.log(text);

Laravel (PHP)

PHP HTTP client integration

Pakai Http::withToken untuk request ke Genfity AI Gateway dari Laravel.

Setup

1Set GENFITY_KEY di .env.
2Pakai Illuminate\Support\Facades\Http untuk POST request.
3Parse response dengan ->json().

https://laravel.com

Laravel (PHP)php

use Illuminate\Support\Facades\Http;

$response = Http::withToken(env('GENFITY_KEY'))
    ->post('https://ai.genfity.com/v1/chat/completions', [
        'model' => 'genfity/claude-opus-4.7',
        'messages' => [
            ['role' => 'user', 'content' => 'Hello Genfity'],
        ],
    ]);

return $response->json();

API Reference

Quick start

Authentication

Endpoints

Create Chat Completion (OpenAI)

Headers

Request Body

Anthropic Messages

Headers

Request Body

Count Tokens

Headers

Request Body

Embeddings

Headers

Request Body

Image Generation

Headers

Request Body

List Models

Headers

Model & harga

Error Codes

Rate Limits

IDE & Editor

Cline

Roo Code

Continue.dev

Cursor

Windsurf (Codeium)

Zed

Kilo Code

TRAE

Xcode

CLI & Terminal

Claude Code

opencode

Codex CLI

Aider

LLM (Simon Willison)

Goose

Crush

Droid (Factory)

Qwen Code

Grok CLI

OpenHands

OpenClaw

Desktop & Web UI

LibreChat

Open WebUI

Chatbox

Jan

LM Studio

Cherry Studio

SDK & Framework

OpenAI Python SDK

OpenAI Node SDK

Anthropic Python SDK

Anthropic Node SDK

LangChain

Vercel AI SDK

Laravel (PHP)

Jadwalkan Diskusi Proyek Sekarang!

Jadwalkan Diskusi Proyek Sekarang!

Jadwalkan Diskusi Proyek Sekarang!