AI Tools
Cerebras Inference
Cerebras Inference: Preise, Fähigkeiten, Updates und Alternativen, von den Seiten des Anbieters gelesen.

Auf Englisch
Key facts
- Price
- Paid plans: see pricing Read on cerebras.ai
- Free plan
- No Read on cerebras.ai
- Platforms
- Web · API
- API
- Yes Read on cerebras.ai
- Open source
- Not presented as open source
- Certifications
- SOC 2 Type II · GDPR Read on trust.cerebras.ai
- Last update
- 9 Nov 2026 Read on inference-docs.cerebras.ai
- Prices checked
- 14 Nov 2026 Read on cerebras.ai
Cerebras Inference is a hosted model-serving service. Developers can use its API or web playground to run supported models; the API is compatible with OpenAI client libraries for common workflows. Models and features depend on deployment and availability.
Developer access is pay-as-you-go, with a one-time $5 promotional credit after adding a valid payment method. Enterprise options include production capacity, dedicated support and, by agreement, customized weights and fine-tuning or training services. It is a hosted inference service, not a downloadable open-source model.
- Category
- Developer Tools
- Read from the maker’s pages
- 2026-11-18
Company
Features
- Run supported AI models through a hosted inference API and web playground.
- Use OpenAI-compatible client libraries for common API workflows.
- Pay per token on the Developer tier.
- Choose shared inference or dedicated capacity for production use.
- Enterprise plans offer dedicated account support and higher-priority capacity.
- Enterprise customers can arrange custom model weights, fine-tuning and training services.
- Access Cerebras inference through partner APIs including AWS Marketplace, OpenRouter, Hugging Face and Vercel.
Use cases
- Build interactive AI applications that need fast responses.
- Add model inference to coding tools and developer workflows.
- Run repeated model calls in agent workflows.
- Analyze research materials with hosted models.
- Add AI responses to voice and automation products.
Pricing
Paid plans: see pricing
- Prices checked
- 2026-11-14
OPENAI GPT OSS 120B
$0.35/M tokens
- $0.35/M tokens
- $0.75/M tokens
- ~3000 tokens/s
QWEN Qwen 3.8 27B
$0.99/M tokens
- $0.99/M tokens
- $1.49/M tokens
- ~1,850 tokens/s
Capabilities
Latest updates
- Kimi K3.1 Pro and reasoning guidance
Added Kimi K3.1 Pro to the Dedicated model catalog and documented image inputs, reasoning levels, and request examples.
- Dedicated models and API guidance
Added Kimi K3, GLM 5.3 Flash, Inkling, Reflection AI Beam, and MiMo V2.6 Pro to the Dedicated model catalog.
- Clarified service-tier fallback and response behavior
Responses report the effective tier in service_tier; auto can fall back to flex and priority can retry at the request’s standard priority.
- Temporary increase to Qwen 3.8 27B total token rate limit
The Developer tier total token rate limit for qwen-3.8-27b is temporarily increased from 450K to 750K tokens per minute.
- Gemma 4 31B availability changes on public endpoints
gemma-4-31b is no longer available on Cerebras public endpoints. Gemma 4 31B remains available on Dedicated Endpoints.
Where it works
Web · API
Security
Alternatives to Cerebras Inference
- SambaNova Cloud
SambaCloud is a hosted API platform for running open-source AI models, with OpenAI-compatible endpoints, model integrations, and token-based pricing.
- Together AI
Together AI provides APIs and infrastructure for running, fine-tuning, and training open AI models.
- Azure OpenAI Service
Azure OpenAI provides hosted AI models through Azure for applications that generate or analyze text, images, and audio.
- Baseten
Baseten provides infrastructure to deploy and run AI models, train models, and build agent workflows using managed inference, APIs, training tools, and sandboxes.
- Fireworks AI
Fireworks AI hosts, routes, and trains open and custom models for applications, teams, and research.
- IO Intelligence
IO Intelligence provides a chat interface and API for using AI models, plus tools for retrieval and agents.
Questions about Cerebras Inference
Is Cerebras Inference free?
No. The maker’s pricing page lists no free plan for Cerebras Inference. Prices checked on 14 Nov 2026.
How much does Cerebras Inference cost?
The plans on the maker’s pricing page: OPENAI GPT OSS 120B ($0.35/M tokens) and QWEN Qwen 3.8 27B ($0.99/M tokens). Prices checked on 14 Nov 2026.
Does Cerebras Inference have an API?
Yes. The maker’s pages state that Cerebras Inference has an API. Read on the maker’s pages on 18 Nov 2026.
Which platforms does Cerebras Inference run on?
Cerebras Inference runs on Web and API, as its maker’s pages state. Read on the maker’s pages on 18 Nov 2026.
Is Cerebras Inference open source?
The maker’s pages do not present Cerebras Inference as open source. Read on the maker’s pages on 18 Nov 2026.
Is Cerebras Inference still available?
Yes, as of 18 Nov 2026: its maker’s pages were read that day and carried no notice that Cerebras Inference has ended.
What changed recently in Cerebras Inference?
The latest entry in its maker’s changelog: 9 Nov 2026, “Kimi K3.1 Pro and reasoning guidance”. Before it: 28 Oct 2026, “Dedicated models and API guidance”. Changelog checked on 15 Nov 2026.
Sources
- https://www.cerebras.ai/pricing — Current Developer and Enterprise tiers, model token rates, promotional credit and enterprise terms.
- https://www.cerebras.ai/inference — Product description, API compatibility, web playground, use areas and tier overview.
- https://www.cerebras.ai/blog/cerebras-launches-disaggregated-inference — November 17, 2026 announcement of production disaggregated inference.
Not confirmed
- Latest version
- The product pages do not identify a Cerebras Inference version.
- Platforms
- No native desktop or mobile apps were confirmed on the pages read.