Cerebrium by Cerebrium
Serverless AI inference platform that charges per second of compute time.
Price
Free plan
then from $100/mo
Free tier
Yes
Free Hobby plan with compute costs, up to 3 deployed...
SDK downloads
—
no official SDK package
Status
—
no public status page
Pricing
| Free tier | Free Hobby plan with compute costs, up to 3 deployed apps, 5 GPU concurrency |
|---|---|
| Cheapest paid plan | $100 a month |
| Usage price | $0.000164 to $0.00167 per second depending on GPU type |
| Good to know | Added automatically: a well-known API in its category. Prices read from the official pricing page. |
From the official pricing page, checked Oct 10, 2026. Prices change: confirm before you buy.
Use it from an agent
| MCP server | None found |
|---|
Alternatives to Cerebrium
| API | Free | Price | SDK downloads / wk | GitHub stars | MCP |
|---|---|---|---|---|---|
| fal Pay-per-use API access to AI models for video, image, audio, and 3D generation. |
— | Varies by model (e.g., $0.05/second for H3 Max video, $0.08/image... | 1.7M | 187 | |
| Replicate Run and deploy machine learning models with pay-per-use pricing for inference. |
— | Varies by model and hardware; examples: $0.04/output image,... | 574K | 597 | |
| Alibaba Cloud Model Studio DashScope API for Qwen language, vision, audio and image models on Alibaba Cloud. |
— | $2/1M input, $6/1M output (qwen3.8-max, International, ≤1M... | 440K | — | |
| vLLM Open-source engine to self-host LLMs behind an OpenAI-compatible inference server. |
Open source | not published | 439K | 93.5K | |
| Cerebras Inference OpenAI-compatible API for fast LLM inference on open-weight models such as GPT OSS 120B and Qwen. |
— | $0.35/M input, $0.75/M output tokens (GPT OSS 120B); $0.99/M... | 353K | — | |
| Ollama Run cloud and local AI models with pay-as-you-go or subscription pricing. |
Free with starter usage credits and limited... | Free plan · paid from $20/mo | 166K | 340 |