Automate Cerebras for free on Stepper
Cerebras provides ultra-fast AI inference powered by custom wafer-scale chips, capable of 2,600+ tokens/sec. Access state-of-the-art language models including Llama, Qwen, and partner models via an OpenAI-compatible API.
Actions available for Cerebras on Stepper
Generate Chat Completion
Generate an AI response using a chat conversation format with system, user, and assistant messages. Supports tool calling, structured output, and reasoning models.
- 15 parameters
- Model
- System Prompt
- User Message
- Temperature
- Max Completion Tokens
- Top P
- Stop Sequence
- Seed
- Response Format
- JSON Schema
- Tools (JSON)
- Tool Choice
- Reasoning Effort
- Frequency Penalty
- Presence Penalty
Generate Text Completion
Generate a text continuation from a single prompt string. Best for simple text generation, autocomplete, and single-turn tasks.
- 9 parameters
- Model
- Prompt
- Max Tokens
- Temperature
- Top P
- Stop Sequence
- Seed
- Log Probabilities
- Echo Prompt
List Models
Retrieve a list of all currently available Cerebras models including their IDs and ownership details.
Retrieve Model
Retrieve details about a specific Cerebras model by its ID.
- 1 parameters
- Model
Make HTTP Request
Make an HTTP request to any URL with full control over method, headers, and body.