{"slug":"cerebras","name":"Cerebras Inference","owner":null,"repo":null,"category":"llm-gateways","lang":"","blurb":"The fastest LLM inference in 2026 (1,800+ tokens/sec) on wafer-scale CS-3 chips, for open models like Llama and Qwen.","use_cases":"[]","alternatives":[],"stars":0,"pushed_at":null,"synced_at":null,"kind":"api","one_liner":"The fastest LLM inference in 2026 (1,800+ tokens/sec) on wafer-scale CS-3 chips, for open models like Llama and Qwen.","website":"https://www.cerebras.ai","docs_url":"https://inference-docs.cerebras.ai/","signup_url":"https://cloud.cerebras.ai/","pricing_model":"freemium","pricing_note":"Free tier (no CC/waitlist); Developer tier 10x higher limits; per-token ~$0.60-$3.90 /M; add $10 to start dev tier","auth_type":"api-key","agent_signup":"self-serve-instant-key","agent_signup_note":"Zero-friction email signup at cloud.cerebras.ai, no credit card or waitlist; instant key + free tier access","mcp_server":"","sdks":["Python","TypeScript","REST","OpenAI-compatible"],"code_sample":"{\"lang\":\"python\",\"code\":\"from cerebras.cloud.sdk import Cerebras\\nclient = Cerebras(api_key=\\\"CEREBRAS_API_KEY\\\")\\nr = client.chat.completions.create(\\n    model=\\\"llama-3.3-70b\\\",\\n    messages=[{\\\"role\\\": \\\"user\\\", \\\"content\\\": \\\"Hello\\\"}])\\nprint(r.choices[0].message.content)\"}","tags":["fast-inference","wafer-scale","open-models"],"useCases":[],"codeSample":{"lang":"python","code":"from cerebras.cloud.sdk import Cerebras\nclient = Cerebras(api_key=\"CEREBRAS_API_KEY\")\nr = client.chat.completions.create(\n    model=\"llama-3.3-70b\",\n    messages=[{\"role\": \"user\", \"content\": \"Hello\"}])\nprint(r.choices[0].message.content)"},"oneLiner":"The fastest LLM inference in 2026 (1,800+ tokens/sec) on wafer-scale CS-3 chips, for open models like Llama and Qwen.","docsUrl":"https://inference-docs.cerebras.ai/","signupUrl":"https://cloud.cerebras.ai/","pricingModel":"freemium","pricingNote":"Free tier (no CC/waitlist); Developer tier 10x higher limits; per-token ~$0.60-$3.90 /M; add $10 to start dev tier","authType":"api-key","agentSignup":"self-serve-instant-key","agentSignupNote":"Zero-friction email signup at cloud.cerebras.ai, no credit card or waitlist; instant key + free tier access","mcpServer":""}