GitHub Models

Inference13 modelcontext maks 1M

Catatan dari sumber

Free prototyping for all GitHub users. 45+ models. Per-request limits (8K in / 4K out).

Setup dalam 5 menit

Model

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://models.github.ai/inference",
  apiKey: process.env.GITHUB_MODELS_API_KEY,
});

const response = await client.chat.completions.create({
  model: "openai/gpt-4.1",
  messages: [{ role: "user", content: "Halo!" }],
});

console.log(response.choices[0].message.content);

.env

GITHUB_MODELS_API_KEY=your-api-key-here

Belum punya API key? Ambil di halaman resmi GitHub Models ↗.

Cara claim API key gratis

Langkah umum — detail pastinya ikutin halaman resmi GitHub Models.

1.Buka halaman API key GitHub Models ↗
2.Daftar akun baru, atau login kalau udah punya.
3.Generate API key di dashboard / settings.
4.Pakai API key + Base URL https://models.github.ai/inference di SDK atau HTTP client.

Model tersedia (13+)

gpt-4.1

openai/gpt-4.1

Modality: Text
Context: 1M
Output: 32K
Rate limit: 10 RPM, 50 RPD

gpt-4.1-mini

openai/gpt-4.1-mini

Modality: Text
Context: 1M
Output: 32K
Rate limit: 15 RPM, 150 RPD

Llama-4-Scout-17B-16E

meta/Llama-4-Scout-17B-16E

Modality: Text + Vision
Context: 512K
Output: ~4K
Rate limit: 15 RPM, 150 RPD

AI21 Jamba 1.5 Large

ai21-jamba-1-5-large

Modality: text + reasoning
Context: 256K

Llama-4-Maverick-17B-128E

meta/Llama-4-Maverick-17B-128E

Modality: Text + Vision
Context: 256K
Output: ~4K
Rate limit: 10 RPM, 50 RPD

gpt-5

openai/gpt-5

Modality: Text
Context: 200K
Output: 32K
Rate limit: 10 RPM, 50 RPD

o4-mini

openai/o4-mini

Modality: Text (reasoning)
Context: 200K
Output: 100K
Rate limit: 10 RPM, 50 RPD

Meta-Llama-3.3-70B

meta/Meta-Llama-3.3-70B

Modality: Text
Context: 131K
Output: ~4K
Rate limit: 15 RPM, 150 RPD

Model	Modality	Context	Output	Rate limit
gpt-4.1 openai/gpt-4.1	Text	1M	32K	10 RPM, 50 RPD
gpt-4.1-mini openai/gpt-4.1-mini	Text	1M	32K	15 RPM, 150 RPD
Llama-4-Scout-17B-16E meta/Llama-4-Scout-17B-16E	Text + Vision	512K	~4K	15 RPM, 150 RPD
AI21 Jamba 1.5 Large ai21-jamba-1-5-large	text + reasoning	256K
Llama-4-Maverick-17B-128E meta/Llama-4-Maverick-17B-128E	Text + Vision	256K	~4K	10 RPM, 50 RPD
gpt-5 openai/gpt-5	Text	200K	32K	10 RPM, 50 RPD
o4-mini openai/o4-mini	Text (reasoning)	200K	100K	10 RPM, 50 RPD
Meta-Llama-3.3-70B meta/Meta-Llama-3.3-70B	Text	131K	~4K	15 RPM, 150 RPD

+ 35 more models model lainnya — lihat daftar lengkap di sumber.

Model ini di provider lain (4)

Nama model yang sama juga muncul di provider lain menurut sumber masing-masing — versi/kuantisasi bisa beda.

FAQ

Apakah API GitHub Models gratis?

Ya — menurut sumber: "Free prototyping for all GitHub users. 45+ models. Per-request limits (8K in / 4K out)." Data dari mnfst/awesome-free-llm-apis, freellm.net, terakhir di-sync 28 Jul 2026 — cek sumber untuk kondisi terbaru.

Ada berapa model gratis di GitHub Models?

13 model tercantum per 28 Jul 2026, termasuk gpt-4.1, gpt-4.1-mini, Llama-4-Scout-17B-16E.

Berapa rate limit GitHub Models?

Beda-beda per model, contoh: gpt-4.1: 10 RPM, 50 RPD; gpt-4.1-mini: 15 RPM, 150 RPD; Llama-4-Scout-17B-16E: 15 RPM, 150 RPD. Limit lengkap per model, lihat tabel di atas.

Berapa context window maksimal di GitHub Models?

1M (gpt-4.1).