LLM7.io

Inference10 modelcontext maks 1M

Catatan dari sumber

API gateway with a free tier. Anonymous access needs no key and reaches the turbo models; a free token from token.llm7.io raises the rate and token limits but reaches the same models.

Setup dalam 5 menit

Model

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.llm7.io/v1",
  apiKey: process.env.LLM7_IO_API_KEY,
});

const response = await client.chat.completions.create({
  model: "deepseek-v4-pro",
  messages: [{ role: "user", content: "Halo!" }],
});

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

.env

LLM7_IO_API_KEY=your-api-key-here

Belum punya API key? Ambil di halaman resmi LLM7.io ↗.

Cara claim API key gratis

Langkah umum — detail pastinya ikutin halaman resmi LLM7.io.

1.Buka halaman API key LLM7.io ↗
2.Daftar akun baru, atau login kalau udah punya.
3.Generate API key di dashboard / settings.
4.Pakai API key + Base URL https://api.llm7.io/v1 di SDK atau HTTP client.

Model tersedia (10)

DeepSeek V4 Pro

deepseek-v4-pro

Modality: reasoning
Context: 1.0M

GLM-5.2

glm-5-2

Modality: reasoning
Context: 1.0M

MiniMax-M3

minimax-m3

Modality: vision + reasoning
Context: 1.0M

nemotron-3-nano:30b

Modality: Text (reasoning)
Context: 1M
Output: 128K
Rate limit: 60 RPM, 250 req/hr (free token)

Gemma 4 31B IT

gemma-4-31b-it

Modality: vision + reasoning
Context: 262K

Nemotron 3 Nano 30B A3B

nemotron-3-nano-30b-a3b

Modality: reasoning
Context: 262K

minimax-m2.7

Modality: Text (reasoning)
Context: 180K
Rate limit: 60 RPM, 250 req/hr (free token)

gpt-oss:20b

Modality: Text
Context: 128K
Output: 32K
Rate limit: 60 RPM, 250 req/hr (free token)

Model	Modality	Context	Output	Rate limit
DeepSeek V4 Pro deepseek-v4-pro	reasoning	1.0M
GLM-5.2 glm-5-2	reasoning	1.0M
MiniMax-M3 minimax-m3	vision + reasoning	1.0M
nemotron-3-nano:30b nemotron-3-nano:30b	Text (reasoning)	1M	128K	60 RPM, 250 req/hr (free token)
Gemma 4 31B IT gemma-4-31b-it	vision + reasoning	262K
Nemotron 3 Nano 30B A3B nemotron-3-nano-30b-a3b	reasoning	262K
minimax-m2.7 minimax-m2.7	Text (reasoning)	180K		60 RPM, 250 req/hr (free token)
gpt-oss:20b gpt-oss:20b	Text	128K	32K	60 RPM, 250 req/hr (free token)

Model ini di provider lain (9)

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

FAQ

Apakah API LLM7.io gratis?

Ya — menurut sumber: "API gateway with a free tier. Anonymous access needs no key and reaches the turbo models; a free token from token.llm7.io raises the rate and token limits but reaches the same models." Data dari mnfst/awesome-free-llm-apis, freellm.net, models.dev, terakhir di-sync 28 Okt 2026 — cek sumber untuk kondisi terbaru.

Ada berapa model gratis di LLM7.io?

10 model tercantum per 28 Okt 2026, termasuk DeepSeek V4 Pro, GLM-5.2, MiniMax-M3.

Berapa rate limit LLM7.io?

Beda-beda per model, contoh: nemotron-3-nano:30b: 60 RPM, 250 req/hr (free token); minimax-m2.7: 60 RPM, 250 req/hr (free token); gpt-oss:20b: 60 RPM, 250 req/hr (free token). Limit lengkap per model, lihat tabel di atas.

Berapa context window maksimal di LLM7.io?

1M (nemotron-3-nano:30b).