Replicate

Replicate provides access to a wide variety of open-source models including language models, image generation, and other AI capabilities. Braintrust integrates seamlessly with Replicate through direct API access, wrapper functions for automatic tracing, and proxy support.

Setup

To use Replicate models, configure your Replicate API key in Braintrust.

Get a Replicate API key from Replicate Console
Add the Replicate API key as an organization or project AI provider.
Set the Replicate API key and your Braintrust API key as environment variables

.env

REPLICATE_API_KEY=<your-replicate-api-key>
BRAINTRUST_API_KEY=<your-braintrust-api-key>

# For organizations on the EU data plane, use https://api-eu.braintrust.dev
# For self-hosted deployments, use your data plane URL
# BRAINTRUST_API_URL=<your-braintrust-api-url>

API keys are stored as one-way cryptographic hashes, never in plaintext.

Use Replicate with Braintrust gateway

The Braintrust gateway allows you to access Replicate models through a unified interface. Use any supported provider’s SDK to call Replicate models. Install the braintrust and openai packages.

# pnpm
pnpm add braintrust openai
# npm
npm install braintrust openai

pip install braintrust openai

Then, initialize the client and make a request to a Replicate model via the Braintrust gateway.

import { OpenAI } from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.braintrust.dev/v1",
  apiKey: process.env.BRAINTRUST_API_KEY,
});

const response = await client.chat.completions.create({
  model: "gpt-oss-120b",
  messages: [{ role: "user", content: "Hello, world!" }],
});

import os

from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.braintrust.dev/v1",
    api_key=os.environ["BRAINTRUST_API_KEY"],
)

response = client.chat.completions.create(
    model="gpt-oss-120b",
    messages=[{"role": "user", "content": "Hello, world!"}],
)

Trace logs with Replicate

Trace your Replicate LLM calls for observability and monitoring. When using the Braintrust gateway, API calls are automatically logged to the specified project.

import { OpenAI } from "openai";
import { initLogger } from "braintrust";

initLogger({
  projectName: "My Project",
  apiKey: process.env.BRAINTRUST_API_KEY,
});

const client = new OpenAI({
  baseURL: "https://gateway.braintrust.dev/v1",
  apiKey: process.env.BRAINTRUST_API_KEY,
});

// All API calls are automatically logged
const result = await client.chat.completions.create({
  model: "gpt-oss-120b",
  messages: [{ role: "user", content: "What is machine learning?" }],
});

import os

from braintrust import init_logger
from openai import OpenAI

init_logger(project="My Project")

client = OpenAI(
    base_url="https://gateway.braintrust.dev/v1",
    api_key=os.environ["BRAINTRUST_API_KEY"],
)

# All API calls are automatically logged
result = client.chat.completions.create(
    model="gpt-oss-120b",
    messages=[{"role": "user", "content": "What is machine learning?"}],
)

The Braintrust gateway is not required. For more control, learn how to customize traces.

Evaluate with Replicate

Evaluations distill the non-deterministic outputs of Replicate models into an effective feedback loop that enables you to ship more reliable, higher quality products. Braintrust Eval is a simple function composed of a dataset of user inputs, a task, and a set of scorers. To learn more about evaluations, see the Experiments guide.

import { Eval } from "braintrust";
import { OpenAI } from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.braintrust.dev/v1",
  apiKey: process.env.BRAINTRUST_API_KEY,
});

Eval("Replicate Evaluation", {
  data: () => [
    { input: "What is 2+2?", expected: "4" },
    { input: "What is the capital of France?", expected: "Paris" },
  ],
  task: async (input) => {
    const response = await client.chat.completions.create({
      model: "meta/llama-2-70b-chat",
      messages: [{ role: "user", content: input }],
    });
    return response.choices[0].message.content;
  },
  scores: [
    {
      name: "accuracy",
      scorer: (args) => (args.output === args.expected ? 1 : 0),
    },
  ],
});

import os

from braintrust import Eval
from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.braintrust.dev/v1",
    api_key=os.environ["BRAINTRUST_API_KEY"],
)


def task(input):
    response = client.chat.completions.create(
        model="meta/llama-2-70b-chat",
        messages=[{"role": "user", "content": input}],
    )
    return response.choices[0].message.content


def accuracy_scorer(output, expected, **kwargs):
    return 1 if output == expected else 0


Eval(
    "Replicate Evaluation",
    data=[
        {"input": "What is 2+2?", "expected": "4"},
        {"input": "What is the capital of France?", "expected": "Paris"},
    ],
    task=task,
    scores=[accuracy_scorer],
)

To learn more about tool use, multimodal support, attachments, and masking sensitive data with Replicate, visit the customize traces guide.

AI providers

SDKs

Developer tools

Setup

Use Replicate with Braintrust gateway

Trace logs with Replicate

Evaluate with Replicate

​Setup

​Use Replicate with Braintrust gateway

​Trace logs with Replicate

​Evaluate with Replicate

Setup

Use Replicate with Braintrust gateway

Trace logs with Replicate

Evaluate with Replicate