Cerebras Code
par Cerebras
Best for developers who prioritize iteration speed above all else. Powered by the Cerebras WSE-3 chip, this platform delivers GLM 4.6 at 1,000+ tokens/second—20x faster than competing inference providers—making it ideal for uninterrupted 'vibe coding' sessions and rapid prototyping.
Plans tarifaires
Free
$0 /mois
GLM 4.6 access with limited tokens and requests (coming soon)
Pro
$50 /mois
24M tokens/day, GLM 4.6 at 1,000+ tok/s inference speed
Max
$200 /mois
120M tokens/day, GLM 4.6 for heavy coding workflows
Fonctionnalités clés
✓
Extension IDE ✕
Application autonome ✓
Accès CLI ✓
Flux agentique ✓
Vitesse extrême Plateformes
Cline RooCode OpenCode Any OpenAI-compatible editor API