# Cerebras
URL: /reference/llm-providers/cerebras

Cerebras provides extremely fast inference powered by their Wafer-Scale Engine hardware. This page covers all Cerebras models available in Tambo.

## Cerebras model overview

Cerebras hosts open-source models optimized for their specialized hardware:

* **Production Models**: Llama 3.1 8B and GPT-OSS 120B
* **Preview Models**: Qwen 3 235B and ZAI GLM 4.7

All context windows are limited to 8,192 tokens on the free tier.

## Supported Models

### Production Models

#### llama3.1-8b

**Status:** Untested
**API Name:** `llama3.1-8b`
**Context Window:** 128,000 tokens (8,192 on free tier)
**Speed:** \~2,200 tokens/sec
**Provider Docs:** [Cerebras - Llama 3.1 8B](https://inference-docs.cerebras.ai/models/llama-31-8b)

Meta's Llama 3.1 8B model running on Cerebras hardware. Best suited for simple tasks and cost-effective deployments.

**Best for:**

* Cost-sensitive applications
* Real-time chat and responses
* Simple text generation tasks
* High-volume, low-complexity workloads

#### gpt-oss-120b

**Status:** Untested
**API Name:** `gpt-oss-120b`
**Context Window:** 8,192 tokens
**Speed:** \~3,000 tokens/sec
**Provider Docs:** [Cerebras - OpenAI GPT OSS](https://inference-docs.cerebras.ai/models/openai-oss)

OpenAI open-weight 120B parameter model on Cerebras.

**Best for:**

* General-purpose high-performance tasks
* Applications requiring strong reasoning
* Complex content generation

### Preview Models

<Callout type="info" title="Preview Models">
  Preview models are intended for evaluation purposes only and may be
  discontinued with short notice.
</Callout>

#### qwen-3-235b-a22b-instruct-2507

**Status:** Untested
**API Name:** `qwen-3-235b-a22b-instruct-2507`
**Context Window:** 32,768 tokens (8,192 on free tier)
**Speed:** \~1,400 tokens/sec
**Provider Docs:** [Cerebras - Qwen 3 235B](https://inference-docs.cerebras.ai/models/qwen-3-235b-2507)

Alibaba's large-scale Qwen 3 model (235B params) optimized for instruction following.

**Best for:**

* Complex instruction following
* Advanced reasoning and analysis
* Multilingual applications

#### zai-glm-4.7

**Status:** Untested
**API Name:** `zai-glm-4.7`
**Context Window:** 128,000 tokens (8,192 on free tier)
**Speed:** \~1,000 tokens/sec
**Provider Docs:** [Cerebras - ZAI GLM 4.7](https://inference-docs.cerebras.ai/models/zai-glm-47)

Zhipu AI's GLM 4.7 (355B params) on Cerebras.

**Best for:**

* General text generation
* Conversational AI
* Bilingual (Chinese/English) tasks

<Callout type="warning" title="Untested Models">
  All Cerebras models are currently **Untested** in Tambo. Test them in your
  specific context before production deployment. See the
  [Labels](/reference/llm-providers/labels) page for more information about
  model status labels.
</Callout>

## Configuration

All Cerebras models are configured through your project settings in the Tambo dashboard:

1. Navigate to your project in the dashboard
2. Go to **Settings** -> **LLM Providers**
3. Select **Cerebras** as your provider
4. Enter your Cerebras API key (get one from [Cerebras Cloud](https://cloud.cerebras.ai/))
5. Choose your desired model from the dropdown
6. Configure any [additional parameters](/guides/setup-project/llm-provider)
7. Click **Save** to apply the configuration

## Model Selection Guide

**For speed and cost efficiency:**

* **Fastest**: [Llama 3.1 8B](#llama31-8b)

**For complex tasks:**

* **Maximum capability**: [Qwen 3 235B](#qwen-3-235b-a22b-instruct-2507) or [GPT-OSS 120B](#gpt-oss-120b)

**For bilingual (Chinese/English):**

* [GLM 4.7](#zai-glm-47)

## See Also

* [Labels](/reference/llm-providers/labels) - Understanding model status labels and observed behaviors
* [Custom LLM Parameters](/guides/setup-project/llm-provider) - Configuring model parameters for fine-tuned responses