Choose a Model

Not sure where to start? Ask the assistant — it can recommend a model based on your use case.

Use this guide to find the right model for your use case on Cerebras. All models listed below are served on dedicated endpoints for enterprise workloads with reserved capacity. A subset is also accessible on public endpoints with no additional setup. For architectural guidance on getting the most out of Cerebras speed, see Designing for Cerebras.

Category	Use Case	Large (>200B)	Medium (20B–200B)	Why Cerebras?
Code & Development	Code generation & reasoning	Kimi K2.7 Code GLM 5.1 MiniMax M2.5	Qwen 3.8 27B (Public) Gemma 4 31B	Reason through entire codebases, including complex requirements, dependencies, and edge cases, without disrupting developer workflows.
	Code completion & bug fixing	MiniMax M2.5 Kimi K2.7 Code	Qwen 3.8 27B (Public) Gemma 4 31B	Generate, critique, and repair code at the speed you type.
	Terminal tasks	GLM 5.1 Kimi K2.7 Code MiniMax M2.5	Qwen 3.8 27B (Public) GPT OSS 120B (Public)	Agents can reason between commands, inspect results, and continue acting while the experience remains interactive.
	Long-horizon autonomous coding	Kimi K2.7 Code GLM 5.1 MiniMax M2.5		Run long agent loops with strong open-source models, reducing hours of work to minutes.
AI-Powered Apps	Agents with tool use	Kimi K2.7 Code GLM 5.1 MiniMax M2.5	Qwen 3.8 27B (Public) GPT OSS 120B (Public)	Make more tool calls, complete more plan, act, and observe loops, and attempt more recoveries in a single user turn.
	Professional workflows	Kimi K2.6 GLM 5.1	Qwen 3.8 27B (Public) Gemma 4 31B	Complete more planning, comparison, and verification steps in the same time window.
	Summarization	Kimi K2.6 GLM 5.1	Gemma 4 31B GPT OSS 120B (Public)	Process longer contexts and synthesize information without making users wait.
	Conversational chat	MiniMax M2.5	GPT OSS 120B (Public)	Create responsive, natural conversations for consumer-facing assistants.
	Low-latency NLU & extraction		Gemma 4 31B	Extract and validate structured data fast enough for production workflows.
Vision & Multimodal	Vision & document understanding	Kimi K2.7 Code Kimi K2.6	Qwen 3.8 27B (Public) Gemma 4 31B	Richer reasoning across text, image, and other inputs while keeping multimodal workflows responsive.

Looking for the full dedicated model catalog? See Dedicated Endpoints.

Migrate from Closed Models

If you’re moving from Claude, GPT, or Gemini, here are open-source alternatives available on Cerebras.

Provider	Closed Source	Use Case	Open Source Alternatives
Claude	Claude Opus 4.8	Multi-hour coding agents, complex multi-file refactors, and difficult reasoning tasks where end-to-end correctness is critical	Kimi K2.6 Kimi K2.7 Code GLM 5.1
	Claude Sonnet 5	Daily coding and IDE-adjacent agent loops that balance speed and intelligence	Primary: GLM 5.1 Fallbacks: Kimi K2.7 Code, Qwen 3.8 27B (Public)
	Claude Haiku 4.5	Customer support, classification, extraction, short-form generation, and subagents in multi-agent systems	Gemma 4 31B GPT OSS 120B (Public) MiniMax M2.5
OpenAI GPT	GPT 5.6 Terra	Balanced reasoning and coding for subagents in agentic systems	Kimi K2.6 Kimi K2.7 Code GLM 5.1
	GPT 5.6 Luna	Classification, extraction, ranking, and low-cost coding subagents	Qwen 3.8 27B (Public)
	GPT 5.4 Nano/Mini	Balanced reasoning and coding, subagents in agentic systems, and structured tasks	MiniMax M2.5 Gemma 4 31B GPT OSS 120B (Public)
Gemini	Gemini 3.1 Pro	Image understanding for coding, document analysis, and scientific reasoning	Kimi K2.6 GLM 5.1 Qwen 3.8 27B (Public)
	Gemini 3.5 Flash Lite	Low-latency multimodal chat and tool use for real-time experiences	Gemma 4 31B GPT OSS 120B (Public) MiniMax M2.5 Qwen 3.8 27B (Public)

Explore the full model catalog at Dedicated Endpoints, or get started with the Quickstart.

Get Started

Models

Capabilities

Dedicated Endpoints

Compatibility

Cloud Console

Resources

Support

Migrate from Closed Models

​Migrate from Closed Models

Migrate from Closed Models