SiliconFlow

Inference2 modelcontext maks 131KGratis: Free (permanen)

Catatan dari sumber

Permanently free models, no credit card required. 200+ paid models also available.

Setup dalam 5 menit

Model

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.siliconflow.cn/v1",
  apiKey: process.env.SILICONFLOW_API_KEY,
});

const response = await client.chat.completions.create({
  model: "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
  messages: [{ role: "user", content: "Halo!" }],
});

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

.env

SILICONFLOW_API_KEY=your-api-key-here

Belum punya API key? Ambil di halaman resmi SiliconFlow ↗.

Cara claim API key gratis

Langkah umum — detail pastinya ikutin halaman resmi SiliconFlow.

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

Model tersedia (2)

deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

Modality: Text (reasoning)
Context: 131K
Output: Configurable
Rate limit: 30 RPM, 60K TPM

Qwen/Qwen3-8B

Modality: Text
Context: 131K
Output: 131K
Rate limit: 30 RPM, 60K TPM

Model	Modality	Context	Output	Rate limit
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B deepseek-ai/DeepSeek-R1-Distill-Qwen-7B	Text (reasoning)	131K	Configurable	30 RPM, 60K TPM
Qwen/Qwen3-8B Qwen/Qwen3-8B	Text	131K	131K	30 RPM, 60K TPM

Model ini di provider lain (1)

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

Qwen/Qwen3-8B· 2 provider

FAQ

Apakah API SiliconFlow gratis?

Ya — Free (permanen). 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 SiliconFlow?

2 model tercantum per 28 Jul 2026, termasuk deepseek-ai/DeepSeek-R1-Distill-Qwen-7B, Qwen/Qwen3-8B.

Berapa rate limit SiliconFlow?

Beda-beda per model, contoh: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B: 30 RPM, 60K TPM; Qwen/Qwen3-8B: 30 RPM, 60K TPM. Limit lengkap per model, lihat tabel di atas.

Berapa context window maksimal di SiliconFlow?

131K (deepseek-ai/DeepSeek-R1-Distill-Qwen-7B).