Lewati ke konten
Kembali ke direktori
Logo Groq

Groq

Inference23 modelcontext maks 262K

Catatan dari sumber

Free tier, no credit card. Ultra-fast LPU inference.

Cara claim API key gratis

Langkah umum โ€” detail pastinya ikutin halaman resmi Groq.

  1. 1.Buka halaman API key Groq โ†—
  2. 2.Daftar akun baru, atau login kalau udah punya.
  3. 3.Generate API key di dashboard / settings.
  4. 4.Pakai API key + Base URL https://api.groq.com/openai/v1 di SDK atau HTTP client.

Model tersedia (23)

kimi-k2-instruct
kimi-k2-instruct
Modality
Text
Context
262K
Output
262K
Rate limit
30 RPM, 14,400 RPD
deepseek-r1-distill-70b
deepseek-r1-distill-70b
Modality
Text
Context
131K
Output
8K
Rate limit
30 RPM, 14,400 RPD
GPT-OSS 20B
gpt-oss-20b
Modality
text
Context
131K
Output
โ€”
Rate limit
1,000 requests/day, 8,000 tokens/minute
GPT-OSS Safeguard 20B
gpt-oss-safeguard-20b
Modality
text
Context
131K
Output
โ€”
Rate limit
1,000 requests/day, 8,000 tokens/minute
gpt-oss-120b
gpt-oss-120b
Modality
Text
Context
131K
Output
32K
Rate limit
30 RPM, 14,400 RPD
llama-3.1-8b-instant
llama-3.1-8b-instant
Modality
Text
Context
131K
Output
131K
Rate limit
30 RPM, 14,400 RPD
llama-3.3-70b-versatile
llama-3.3-70b-versatile
Modality
Text
Context
131K
Output
32K
Rate limit
30 RPM, 14,400 RPD
llama-4-maverick-17b-128e-instruct
llama-4-maverick-17b-128e-instruct
Modality
Text + Vision
Context
131K
Output
8K
Rate limit
15 RPM, 500 RPD