Cerebras

Inference5 modelcontext maks 128K (8K on free)Gratis: 1M token/hari

Catatan dari sumber

Free tier, no credit card. Ultra-fast inference (~2,600 tok/s). 1M tokens/day cap. 8K context cap on free tier.

Cara claim API key gratis

Langkah umum — detail pastinya ikutin halaman resmi Cerebras.

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

Model tersedia (5)

gpt-oss-120b

Modality: Text
Context: 128K (8K on free)
Output: 8K
Rate limit: 30 RPM, 14,400 RPD, 1M TPD

zai-glm-4.7

Modality: Text
Context: 128K (8K on free)
Output: 8K
Rate limit: 10 RPM, 100 RPD, 1M TPD

Gemma 4 31B IT

gemma-4-31b-it

Modality: vision + reasoning
Context: 42
Output: 262K

Llama 3.1 70B

llama-3-1-70b

Modality: text
Context: 41
Output: 131K

Llama 3.1 8B

llama-3-1-8b

Modality: —
Context: —
Output: —
Rate limit: 30 requests/minute, 60,000 tokens/minute, 900 requests/hour, 1,000,000 tokens/hour, 14,400 requests/day, 1,000,000 tokens/day

Model	Modality	Context	Output	Rate limit
gpt-oss-120b gpt-oss-120b	Text	128K (8K on free)	8K	30 RPM, 14,400 RPD, 1M TPD
zai-glm-4.7 zai-glm-4.7	Text	128K (8K on free)	8K	10 RPM, 100 RPD, 1M TPD
Gemma 4 31B IT gemma-4-31b-it	vision + reasoning	42	262K	—
Llama 3.1 70B llama-3-1-70b	text	41	131K	—
Llama 3.1 8B llama-3-1-8b	—	—	—	30 requests/minute, 60,000 tokens/minute, 900 requests/hour, 1,000,000 tokens/hour, 14,400 requests/day, 1,000,000 tokens/day

FAQ

Apakah API Cerebras gratis?

Ya — 1M token/hari. Data dari mnfst/awesome-free-llm-apis, freellm.net, cheahjs/free-llm-api-resources, terakhir di-sync 19 Jul 2026 — cek sumber untuk kondisi terbaru.

Ada berapa model gratis di Cerebras?

5 model tercantum per 19 Jul 2026, termasuk gpt-oss-120b, zai-glm-4.7, Gemma 4 31B IT.

Berapa rate limit Cerebras?

Beda-beda per model, contoh: gpt-oss-120b: 30 RPM, 14,400 RPD, 1M TPD; zai-glm-4.7: 10 RPM, 100 RPD, 1M TPD; Llama 3.1 8B: 30 requests/minute, 60,000 tokens/minute, 900 requests/hour, 1,000,000 tokens/hour, 14,400 requests/day, 1,000,000 tokens/day. Limit lengkap per model, lihat tabel di atas.

Berapa context window maksimal di Cerebras?

128K (8K on free) (gpt-oss-120b).