Skip to content

Model Catalog Migration 8C/9: Extended LLM Provider Integration (Remaining Providers) #699

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
siddharthsambharia-portkey merged 2 commits into from
Feb 9, 2026
Merged

Model Catalog Migration 8C/9: Extended LLM Provider Integration (Remaining Providers) #699

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8af41e8
docs: Update remaining LLM provider integrations for Model Catalog
siddharthsambharia-portkey Feb 4, 2026
f313c17
fix: Address PR review comments across 7 provider docs
siddharthsambharia-portkey Feb 9, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
202 changes: 124 additions & 78 deletions integrations/llms/cerebras.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,107 +1,153 @@
---
title: "Cerebras"
description: "Integrate Cerebras models with Portkey's AI Gateway"
---

Portkey provides a robust and secure gateway to facilitate the integration of various Large Language Models (LLMs) into your applications, including the models hosted on [Cerebras Inference API](https://cerebras.ai/inference).
Portkey provides a robust and secure gateway to integrate various Large Language Models (LLMs) into applications, including [Cerebras Inference API](https://cerebras.ai/inference).

<Note>
Provider Slug: `cerebras`
</Note>
With Portkey, take advantage of features like fast AI gateway access, observability, prompt management, and more, while securely managing API keys through [Model Catalog](/product/model-catalog).

## Portkey SDK Integration with Cerebras
## Quick Start

Portkey provides a consistent API to interact with models from various providers. To integrate Cerebras with Portkey:
Get Cerebras working in 3 steps:

### 1\. Install the Portkey SDK
<Tabs>
<Tab title="NodeJS">
```sh
npm install --save portkey-ai
```
</Tab>
<Tab title="Python">
```sh
pip install portkey-ai
```
</Tab>
<CodeGroup>
```python Python icon="python"
from portkey_ai import Portkey

</Tabs>
# 1. Install: pip install portkey-ai
# 2. Add @cerebras provider in model catalog
# 3. Use it:

portkey = Portkey(api_key="PORTKEY_API_KEY")

response = portkey.chat.completions.create(
model="@cerebras/llama3.1-8b",
messages=[{"role": "user", "content": "Say this is a test"}]
)

### 2\. Initialize Portkey with Cerebras
print(response.choices[0].message.content)
```

To use Cerebras with Portkey, get your API key from [here](https://cerebras.ai/inference), then add it to Portkey to create the virtual key.
<Tabs>
<Tab title="NodeJS SDK">
```js
import Portkey from 'portkey-ai'
```js Javascript icon="square-js"
import Portkey from 'portkey-ai'

const portkey = new Portkey({
apiKey: "PORTKEY_API_KEY", // defaults to process.env["PORTKEY_API_KEY"]
provider:"@CEREBRAS_PROVIDER" // Your Cerebras Inference virtual key
})
```
</Tab>
<Tab title="Python SDK">
```py
from portkey_ai import Portkey

portkey = Portkey(
api_key ="PORTKEY_API_KEY", # Replace with your Portkey API key
provider="@CEREBRAS_PROVIDER" # Your Cerebras Inference virtual key
)
```
</Tab>
// 1. Install: npm install portkey-ai
// 2. Add @cerebras provider in model catalog
// 3. Use it:

const portkey = new Portkey({
apiKey: "PORTKEY_API_KEY"
})

</Tabs>
const response = await portkey.chat.completions.create({
model: "@cerebras/llama3.1-8b",
messages: [{ role: "user", content: "Say this is a test" }]
})

console.log(response.choices[0].message.content)
```

```python OpenAI Py icon="python"
from openai import OpenAI
from portkey_ai import PORTKEY_GATEWAY_URL

# 1. Install: pip install openai portkey-ai
# 2. Add @cerebras provider in model catalog
# 3. Use it:

client = OpenAI(
api_key="PORTKEY_API_KEY", # Portkey API key
base_url=PORTKEY_GATEWAY_URL
)

response = client.chat.completions.create(
model="@cerebras/llama3.1-8b",
messages=[{"role": "user", "content": "Say this is a test"}]
)

print(response.choices[0].message.content)
```

```js OpenAI JS icon="square-js"
import OpenAI from "openai"
import { PORTKEY_GATEWAY_URL } from "portkey-ai"

// 1. Install: npm install openai portkey-ai
// 2. Add @cerebras provider in model catalog
// 3. Use it:

const client = new OpenAI({
apiKey: "PORTKEY_API_KEY", // Portkey API key
baseURL: PORTKEY_GATEWAY_URL
})

const response = await client.chat.completions.create({
model: "@cerebras/llama3.1-8b",
messages: [{ role: "user", content: "Say this is a test" }]
})

console.log(response.choices[0].message.content)
```

```sh cURL icon="square-terminal"
# 1. Add @cerebras provider in model catalog
# 2. Use it:

curl https://api.portkey.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "x-portkey-api-key: $PORTKEY_API_KEY" \
-d '{
"model": "@cerebras/llama3.1-8b",
"messages": [
{ "role": "user", "content": "Say this is a test" }
]
}'
```
</CodeGroup>

<Note>
**Tip:** You can also set `provider="@cerebras"` in `Portkey()` and use just `model="llama3.1-8b"` in the request.
</Note>

### 3\. Invoke Chat Completions
<Tabs>
<Tab title="NodeJS SDK">
```js
const chatCompletion = await portkey.chat.completions.create({
messages: [{ role: 'user', content: 'Say this is a test' }],
model: 'llama3.1-8b',
});
## Add Provider in Model Catalog

console.log(chatCompletion.choices);
```
</Tab>
<Tab title="Python SDK">
```python
completion = portkey.chat.completions.create(
messages= [{ "role": 'user', "content": 'Say this is a test' }],
model= 'llama3.1-8b'
)

print(completion)
```
</Tab>
1. Go to [**Model Catalog → Add Provider**](https://app.portkey.ai/model-catalog/providers)
2. Select **Cerebras**
3. Choose existing credentials or create new by entering your [Cerebras API key](https://cerebras.ai/inference)
4. Name your provider (e.g., `cerebras-prod`)

</Tabs>
<Card title="Complete Setup Guide →" href="/product/model-catalog">
See all setup options, code examples, and detailed instructions
</Card>

---

## Supported Models

Cerebras currently supports `Llama-3.1-8B` and `Llama-3.1-70B`. You can find more info here:
<Info>
[![Logo](/images/llms/apple-touch-icon.png)Overview - Starter KitStarter Kit](https://inference-docs.cerebras.ai/introduction)
</Info>
## Next Steps

The complete list of features supported in the SDK are available on the link below.

<Card title="SDK" href="/api-reference/sdk">
<Card title="Cerebras Models" icon="list" href="https://inference-docs.cerebras.ai/introduction">
View all available models and documentation
</Card>

You'll find more information in the relevant sections:
## Next Steps

1. [Add metadata to your requests](/product/observability/metadata)
2. [Add gateway configs to your Cerebras](/product/ai-gateway/configs)[ requests](/product/ai-gateway/configs)
3. [Tracing Cerebras requests](/product/observability/traces)
4. [Setup a fallback from OpenAI to Cerebras](/product/ai-gateway/fallbacks)
<CardGroup cols={2}>
<Card title="Add Metadata" icon="tags" href="/product/observability/metadata">
Add metadata to your Cerebras requests
</Card>
<Card title="Gateway Configs" icon="gear" href="/product/ai-gateway/configs">
Add gateway configs to your Cerebras requests
</Card>
<Card title="Tracing" icon="chart-line" href="/product/observability/traces">
Trace your Cerebras requests
</Card>
<Card title="Fallbacks" icon="arrow-rotate-left" href="/product/ai-gateway/fallbacks">
Setup fallback from OpenAI to Cerebras
</Card>
</CardGroup>

For complete SDK documentation:

<Card title="SDK Reference" icon="code" href="/api-reference/sdk/list">
Complete Portkey SDK documentation
</Card>
Loading