AI proxy

This guide walks through how to use the Braintrust AI proxy to access models from OpenAI, Anthropic, Google, AWS, Mistral, and 3rd party inference providers like Together which offer access to open source models like LLaMa 3 behind a single API. The AI proxy is a powerful tool that:

• Simplifies your code by providing a single API across AI providers.
• Reduces your costs by automatically caching results and reusing them when possible.
• Increases observability by automatically logging your requests.

To read more about why we launched the AI proxy, check out our blog post announcing the feature.

Quickstart

You can use your favorite OpenAI drivers, and simply set the base url to https://api.braintrust.dev/v1/proxy. Try running the following script in your favorite language, twice.

import { OpenAI } from "openai";
const client = new OpenAI({
  baseURL: "https://api.braintrust.dev/v1/proxy",
  apiKey: process.env.OPENAI_API_KEY, // Can use Braintrust, Anthropic, etc. API keys here
});
 
async function main() {
  const start = performance.now();
  const response = await client.chat.completions.create({
    model: "gpt-3.5-turbo", // Can use claude-2, llama-2-13b-chat, etc. here
    messages: [{ role: "user", content: "What is a proxy?" }],
    seed: 1, // A seed activates the proxy's cache
  });
  console.log(response.choices[0].message.content);
  console.log(`Took ${(performance.now() - start) / 1000}s`);
}
 
main();

If you have access to Anthropic, feel free to use their API key with a model like claude-3-5-sonnet-20240620 instead. Under the hood, we're proxying the requests through a Cloudflare worker, caching the results with end-to-end encryption, and returning the results.

Key features

The proxy is a drop-in replacement for the OpenAI API, with a few killer features:

• Automatic caching of results, with configurable semantics
• Interopability with other providers, including a wide range of open source models
• API key management

Caching

The proxy automatically caches results, and reuses them when possible. Because the proxy runs on the edge, you can expect cached requests to be returned in under 100ms. This is especially useful when you're developing and frequently re-running or evaluating the same prompts many times.

The cache follows the following rules:

• There are three caching modes: auto (default), always, never.
• In auto mode, requests are cached if they have temperature=0 or the seed parameter set.
• In always mode, requests are cached as long as they are one of the supported paths (/chat/completions, /completions, or /embeddings)
• In never mode, the cache is never read or written to.

You can set the cache by passing the x-bt-use-cache header to your request. For example, to always use the cache,

import { OpenAI } from "openai";
 
const client = new OpenAI({
  baseURL: "https://api.braintrust.dev/v1/proxy",
  defaultHeaders: {
    "x-bt-use-cache": "always",
  },
  apiKey: process.env.OPENAI_API_KEY, // Can use Braintrust, Anthropic, etc. API keys here
});
 
async function main() {
  const response = await client.chat.completions.create({
    model: "gpt-3.5-turbo", // Can use claude-2, llama-2-13b-chat, etc. here
    messages: [{ role: "user", content: "What is a proxy?" }],
  });
  console.log(response.choices[0].message.content);
}
 
main();

Encryption

We use AES-GCM to encrypt the cache, using a key derived from your API key. Currently, results are cached for 1 week.

This design ensures that the cache is only accessible to you, and that we cannot see your data. We also do not store or log API keys.

Supported models

The full list of supported models is

• gpt-4o (openai, azure)
• gpt-4o-mini (openai, azure)
• gpt-4o-2024-08-06 (openai, azure)
• gpt-4o-2024-05-13 (openai, azure)
• gpt-4o-mini-2024-07-18 (openai, azure)
• gpt-4-turbo (openai, azure)
• gpt-4-turbo-2024-04-09 (openai, azure)
• gpt-4-turbo-preview (openai, azure)
• gpt-4-0125-preview (openai, azure)
• gpt-4-1106-preview (openai, azure)
• gpt-4 (openai, azure)
• gpt-4-0613 (openai, azure)
• gpt-4-0314 (openai, azure)
• gpt-3.5-turbo-0125 (openai, azure)
• gpt-3.5-turbo (openai, azure)
• gpt-35-turbo (azure)
• gpt-3.5-turbo-1106 (openai, azure)
• gpt-3.5-turbo-instruct (openai, azure)
• gpt-3.5-turbo-instruct-0914 (openai, azure)
• gpt-4-32k (openai, azure)
• gpt-4-32k-0613 (openai, azure)
• gpt-4-32k-0314 (openai, azure)
• gpt-4-vision-preview (openai, azure)
• gpt-4-1106-vision-preview (openai, azure)
• gpt-3.5-turbo-16k (openai, azure)
• gpt-35-turbo-16k (azure)
• gpt-3.5-turbo-16k-0613 (openai, azure)
• gpt-3.5-turbo-0613 (openai, azure)
• gpt-3.5-turbo-0301 (openai, azure)
• text-davinci-003 (openai, azure)
• claude-3-5-sonnet-20240620 (anthropic)
• claude-3-haiku-20240307 (anthropic)
• claude-3-sonnet-20240229 (anthropic)
• claude-3-opus-20240229 (anthropic)
• anthropic.claude-3-5-sonnet-20240620-v1:0 (bedrock)
• anthropic.claude-3-haiku-20240307-v1:0 (bedrock)
• anthropic.claude-3-sonnet-20240229-v1:0 (bedrock)
• anthropic.claude-3-opus-20240229-v1:0 (bedrock)
• claude-instant-1.2 (anthropic)
• claude-instant-1 (anthropic)
• claude-2.1 (anthropic)
• claude-2.0 (anthropic)
• claude-2 (anthropic)
• meta/llama-2-70b-chat (replicate)
• mistral (ollama)
• phi (ollama)
• pplx-7b-chat (perplexity)
• pplx-7b-online (perplexity)
• pplx-70b-chat (perplexity)
• pplx-70b-online (perplexity)
• codellama-34b-instruct (perplexity)
• codellama-70b-instruct (perplexity)
• llama-3-8b-instruct (perplexity)
• llama-3-70b-instruct (perplexity)
• llama-2-13b-chat (perplexity)
• llama-2-70b-chat (perplexity)
• mistral-7b-instruct (perplexity)
• mixtral-8x7b-instruct (perplexity)
• mixtral-8x22b-instruct (perplexity)
• openhermes-2-mistral-7b (perplexity)
• openhermes-2.5-mistral-7b (perplexity)
• meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo (together)
• meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo (together)
• meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo (together)
• meta-llama/Meta-Llama-3-70B (together)
• meta-llama/Llama-3-8b-hf (together)
• meta-llama/Llama-3-8b-chat-hf (together)
• meta-llama/Llama-3-70b-chat-hf (together)
• meta-llama/Llama-2-70b-chat-hf (together)
• mistralai/Mistral-7B-Instruct-v0.1 (together)
• mistralai/mixtral-8x7b-32kseqlen (together)
• mistralai/Mixtral-8x7B-Instruct-v0.1 (together)
• mistralai/Mixtral-8x7B-Instruct-v0.1-json (together)
• mistralai/Mixtral-8x22B (together)
• mistralai/Mixtral-8x22B-Instruct-v0.1 (together)
• NousResearch/Nous-Hermes-2-Yi-34B (together)
• deepseek-ai/deepseek-coder-33b-instruct (together)
• mistral-large-latest (mistral)
• open-mistral-nemo (mistral)
• codestral-latest (mistral)
• open-mixtral-8x22b (mistral)
• open-codestral-mamba (mistral)
• mistral-tiny (mistral)
• mistral-small (mistral)
• mistral-medium (mistral)
• llama-3.1-8b-instant (groq)
• llama-3.1-70b-versatile (groq)
• llama-3.1-405b-reasoning (groq)
• gemma-7b-it (groq)
• llama3-8b-8192 (groq)
• llama3-70b-8192 (groq)
• llama2-70b-4096 (groq)
• mixtral-8x7b-32768 (groq)
• llama3-1-8b (lepton)
• llama3-1-70b (lepton)
• llama3-1-405b (lepton)
• accounts/fireworks/models/llama-v3p1-8b-instruct (fireworks)
• accounts/fireworks/models/llama-v3p1-70b-instruct (fireworks)
• accounts/fireworks/models/llama-v3p1-405b-instruct (fireworks)
• gemini-1.5-pro-latest (google)
• gemini-1.5-flash-latest (google)
• gemini-1.0-pro (google)
• gemini-pro (google)

We are constantly adding new models, and if you have a model you'd like to see supported, please let us know!

Supported protocols

We're currently focused on supporting the OpenAI protocol (i.e. their v1 api), and automatically translating OpenAI requests into various providers' APIs. That means you can interact with other providers like Anthropic by using OpenAI client libraries and API calls. However, the proxy does not currently support other providers' APIs. That means, for example, you cannot use the Anthropic SDKs with the proxy. If you are interested in using other providers' APIs, please let us know.

API key management

The proxy allows you to either use the provider's API key, or your Braintrust API key. If you use the provider's API key, you can use the proxy without a Braintrust account, and caching will still work (scoped to your API key).

However, you can manage all your API keys in one place by configuring secrets in your Braintrust account. To do so, sign up for an account and add each provider's API key on the secrets page.

Custom models

If you have custom models as part of your OpenAI or other accounts, you can use them with the proxy by adding them to a custom provider. For example, if you have a custom model called gpt-3.5-acme, you can add it like so:

Each custom model must have a flavor (chat or completion) and format (openai, anthropic, google, window or js). Additionally, they can optionally have a boolean flag if the model is multimodal and an input cost and output cost, which will only be used to calculate and display estimated prices for experiment runs.

Specifying an org

If you are part of multiple organizations, you can specify which organization to use by passing the x-bt-org-name header in the SDK:

import { OpenAI } from "openai";
 
const client = new OpenAI({
  baseURL: "https://api.braintrust.dev/v1/proxy",
  defaultHeaders: {
    "x-bt-org-name": "Acme Inc",
  },
  apiKey: process.env.OPENAI_API_KEY, // Can use Braintrust, Anthropic, etc. API keys here
});
 
async function main() {
  const response = await client.chat.completions.create({
    model: "gpt-3.5-turbo", // Can use claude-2, llama-2-13b-chat, etc. here
    messages: [{ role: "user", content: "What is a proxy?" }],
  });
  console.log(response.choices[0].message.content);
}
 
main();

Load balancing

If you have multiple API keys for a given model type, e.g. OpenAI and Azure for gpt-3.5-turbo, the proxy will automatically load balance across them. This is a useful way to work around per-account rate limits and provide resiliency in case one provider is down.

You can setup endpoints directly on the secrets page in your Braintrust account by adding endpoints:

Advanced configuration

The following headers allow you to configure the proxy's behavior:

• x-bt-use-cache: auto | always | never. See Caching
• x-bt-use-creds-cache: auto | always | never. Similar to x-bt-use-cache, but controls whether to cache the credentials used to access the provider's API. This is useful if you are rapidly tweaking credentials and don't want to wait ~60 seconds for the credentials cache to expire.
• x-bt-org-name: Specify if you are part of multiple organizations and want to use API keys/log to a specific org.
• x-bt-endpoint-name: Specify to use a particular endpoint (by its name).

Integration with Braintrust platform

Several features in Braintrust are powered by the proxy. For example, when you create a playground, the proxy handles running the LLM calls. Similarly, if you create a prompt, when you preview the prompt's results, the proxy is used to run the LLM. However, the proxy is not required when you:

• Run evals in your code
• Load prompts to run in your code
• Log traces to Braintrust

If you'd like to use it in your code to help with caching, secrets management, and other features, follow the instructions above to set it as the base URL in your OpenAI client.

Self-hosting

If you're self-hosting Braintrust, your API service (serverless functions or containers) contain a built-in proxy that runs within your own environment. See the self-hosting docs for more information on how to set up self-hosting.

Open source

The AI proxy is open source, and you can find the code on Github.