Braintrust Gateway Managed gateway

Overview

What kind of product Category ?

Managed gateway Not verified

Marketplaces resell many providers behind one key. Gateways add governance on top. Open-source projects you run yourself. Cloud platforms are hyperscaler surfaces. Inference providers host models on their own hardware.

Who runs it Deployment model ?

Managed or self-host Verified 3 days ago

Managed means the vendor operates it. Self-host means you run it on your own infrastructure. Both means you can choose.

Licence Licence ?

Open core Verified 3 days ago

Proprietary products cannot be inspected or forked. Open licences such as MIT and Apache-2.0 let you audit, modify, and run the code without permission.

Company Company ?

Braintrust Not verified

The organisation that maintains the product.

Who you would be signing with Vendor status ?

Independent company Not verified

Whether the product is still an independent company, has been acquired, is a large cloud vendor’s product line, is run by a software foundation, or has been put into maintenance mode. Maintenance mode means bug fixes and security patches only — no new features.

Last shipped an update Latest release ?

Not published Not verified

Braintrust dates its changelog by month only, so no exact release date is published. The latest entry is August 2026.

The date of the most recent release or version tag. A product that has not shipped in a year is a different risk from one that shipped last week, regardless of what its marketing site says.

GitHub stars GitHub stars ?

409 Verified 3 days ago

A rough proxy for community size on open-source projects. Not a quality measure.

Cost

Markup on model prices Token markup ?

Not published Not verified

How much the product adds on top of what the underlying model provider charges. Zero means you pay the same per-token price you would pay the model provider directly.

Fee to add funds Credit purchase fee ?

Not published Not verified

A percentage charged when you top up your balance, separate from token prices. It is easy to miss because it does not appear on the per-token price list.

Monthly cost per person Seat fee ?

None Verified 3 days ago

A recurring per-user platform charge that applies regardless of how much you use the models.

Can use your own provider accounts BYOK supported ?

Yes Verified 3 days ago

Bring Your Own Key: you keep direct contracts with OpenAI, Anthropic and others, and the gateway only routes traffic. This preserves negotiated rates and committed-spend discounts.

Cost of using your own accounts BYOK terms ?

Provider keys are configured at organization or project level (project keys override org keys); the proxy can even be used with only a provider key and no Braintrust account. Verified 3 days ago

What the product charges to route traffic through your own provider keys.

Free tier Free tier ?

Starter $0/month: unlimited users, $10 model credits, 1 GB processed data, 10k scores, 14-day retention. The Braintrust-hosted Gateway is free during public preview, with pricing to be announced before GA. Verified 3 days ago

What you can do without paying, useful for evaluation.

Enterprise plan from Enterprise plan from ?

Not published Not verified

Annual entry price for the enterprise tier, where one is published or credibly reported.

Cost to run it yourself Self-host cost ?

Self-hosted Braintrust deployments run the Gateway inside the customer's own data plane so LLM traffic stays in their account; the standalone proxy is MIT-licensed on GitHub. On-prem/hybrid deployment is an Enterprise-plan feature, and independent reviews note there is no free self-hosted tier below Enterprise. Verified 3 days ago

What self-hosting actually costs once you account for infrastructure and any paid tier.

How the vendor makes money Pricing model ?

Platform fee plus usage meters Not verified

The shape of the vendor’s bill: does the routing layer charge a percentage on top of tokens, a flat monthly fee, both, neither (because inference is the product), or nothing at all (open source with no paid tier).

How pricing works, briefly Pricing model detail ?

Flat monthly platform fee + included model credits then per-token rates + usage overages (processed data, scores, retention). Starter $0 with $10/mo credits; Pro $249/mo with $249/mo credits (drops to $100/mo credits after 2026-09-01); Enterprise annual invoice. AI proxy blog says the gateway itself is free 'as a beta', but Braintrust's docs index the proxy page as 'deprecated' — treat the free-proxy framing as unverified. Not verified

A one-paragraph description that covers the caveats a pricing category cannot: introductory rates, per-feature meters, tier gating, and pricing that resets on a specific date.

Minimum commitment Minimum commitment ?

None for Starter/Pro. Enterprise is annual-invoiced. Not verified

Whether the vendor requires a minimum contract term, a minimum spend, or a provisioned-capacity purchase to get its published rate.

Charges that fire after you go over an allowance Overage terms ?

Processed data: 1 GB then +$4/GB (Starter) / 5 GB then +$3/GB (Pro). Scores: 10k then $2.50/1k (Starter) / 50k then $1.50/1k (Pro). Retention: 14 days (Starter) / 30 days then +$0.50/GB/month up to 180 days (Pro). Model credits do not roll over. Retention bills what you ingest into each month you keep beyond the base window, not what's currently stored. Deleting data does not reduce processed-data charges. Not verified

The line items that scale with usage after an included allowance is exhausted — log storage, extra requests, per-feature meters, data export — which is where cost estimates usually go wrong.

Prompt cache offered Cache mechanism ?

Exact-match cache Not verified

Whether the gateway offers its own response cache, what kind of match it does (exact request, prefix, semantic), or simply passes provider caching through unchanged.

Discount on cached input Cache-read discount ?

Not published Not verified

How much cheaper cached tokens are than fresh input, when the vendor publishes a single figure. Bundled-inference clouds usually price this per model instead of as one number.

Premium on cache writes Cache-write premium ?

Not published Not verified

How much more the first write of a cached prefix costs versus a plain input token. A high write premium and a low hit rate can leave you paying more than you save, so this matters as much as the read discount.

Who captures the cache saving Cache economics ?

Exact-request response caching in the proxy: requests with temperature=0 or `seed` are cached, encrypted per API key, controllable via x-bt-use-cache. No gateway-layer cached-token pricing; Braintrust's own model rates do publish cache-hit prices (GLM-5.2 81% off, Kimi K3 90% off). Cache hits avoid the provider call entirely, but cached traffic still counts as processed data at ingestion. Not verified

Whether the customer keeps the full saving from caching or the vendor captures part of it — and any conditions attached (write premium, storage fees, best-effort hits).

What you can split spend by Cost attribution ?

Not stated as cost splits. Environments tag object versions but are not described as cost attribution. Not verified

The dimensions the vendor documents for splitting spend — per key, per user, per team, per tag, per customer. Matters if you need to chargeback internally or bill an end customer.

How you get cost data out Cost export ?

S3 / Google Cloud Storage scheduled export automations on Enterprise only; price not stated. CSV, webhook and warehouse export not stated. Not verified

The mechanisms the vendor publishes for exporting cost and usage data: CSV, an API, webhooks, S3, a data warehouse, or nothing at all. Any per-unit price is included.

Who pays the model bill BYOK mode ?

Your keys or their credits Not verified

Whether you bring your own provider accounts (BYOK), buy inference from this vendor, or can do either. This is the single biggest commercial difference between these products: it decides who holds the contract with the model provider and who carries the spend.

Catalog

Models available Models available ?

~100 Verified 3 days ago

How many models you can call, shown as a range because several vendors publish different totals on different pages. Vendor-reported either way, so counts are not directly comparable — some count every provider variant of the same model separately.

Model providers reachable Upstream providers ?

9 Verified 3 days ago

How many distinct model providers or labs you can reach, shown as a range where the vendor’s own pages disagree. More providers usually means better redundancy when one has an outage.

Works with standard OpenAI code OpenAI-compatible API ?

Yes Verified 3 days ago

If yes, you can usually switch to it by changing one base URL, and switch away just as easily. This is the main defence against lock-in.

OpenAI chat endpoint POST /v1/chat/completions ?

Yes Not verified

The endpoint almost every application ports first. "Not documented" means the vendor never states it, which is different from a documented no.

Anthropic messages endpoint POST /v1/messages ?

Yes Not verified

Whether Anthropic-shaped calls work without rewriting them. Several products support this only as SDK compatibility or provider passthrough rather than a native endpoint — the detail page says which.

OpenAI Responses endpoint POST /v1/responses ?

Yes Not verified

The newer stateful OpenAI surface. Support is much thinner across this market than chat completions.

Embeddings endpoint POST /v1/embeddings ?

Yes Not verified

Whether you can generate vectors through the same gateway, or need a second integration for retrieval workloads.

Image generation endpoint POST /v1/images/generations ?

Not documented Not verified

Whether image models are reachable through the same surface as text.

Audio endpoints POST /v1/audio/* ?

Partly Not verified

Speech-to-text and text-to-speech. Frequently the first gap in an otherwise complete gateway.

Batch jobs endpoint POST /v1/batches ?

Not documented Not verified

Asynchronous bulk processing, usually at a discount. Commonly undocumented, and commonly the reason a migration stalls late.

Needs the vendor’s own code library Requires a vendor-specific SDK ?

No Verified 3 days ago

A proprietary client library spreads through your codebase and has to be torn out again if you leave. “No” is the better answer here, and it means the standard OpenAI client works.

You can export your request history Logs / usage data export ?

Yes Verified 3 days ago

Whether you can get your own request logs, traces, or usage records back out — through an API, a bulk export, or a download. Decides whether you leave with your history or abandon it.

Settings can live in version control Declarative config-as-code ?

Not published Not verified

Whether routing, fallback, and budget rules can be declared in a file you keep in Git, rather than existing only as settings clicked into a hosted dashboard.

Embeddings Embeddings ?

Yes Verified 3 days ago

Text-to-vector models, needed for search and retrieval features.

Image generation Image generation ?

Not published Not verified

Whether image models are reachable through the same interface.

Speech and audio Speech and audio ?

Yes Verified 3 days ago

Text-to-speech or transcription models through the same interface.

Video generation Video generation ?

Not published Not verified

Whether video models are reachable through the same interface.

Batch processing Batch processing ?

Not published Not verified

Submitting large jobs for cheaper, slower processing. Often 50% off for work that is not time-sensitive.

Routing & reliability

Uptime it promises in writing Contractual SLA uptime ?

Not published Not verified

The uptime percentage in a published, contractual service level agreement. A public status page is not an SLA — it reports what happened, it does not promise anything or pay you back when it breaks.

Automatic failover Automatic failover ?

Yes Verified 3 days ago

When a model provider goes down or rate-limits you, traffic moves to a backup automatically instead of returning errors to your users.

Load balancing Load balancing ?

Yes Verified 3 days ago

Spreads requests across several providers or keys to raise your effective rate limit.

Rule-based routing Conditional routing ?

Not published Not verified

Send different requests to different models based on rules — for example a cheap model for free users and a strong model for paying ones.

Response caching Response caching ?

Yes Verified 3 days ago

Reuses the answer when the exact same request comes in again, which cuts both cost and latency.

Similar-question caching Semantic cache ?

Not published Not verified

Reuses an answer when a new question means roughly the same thing as an earlier one. Saves far more than exact-match caching but can return subtly wrong answers if tuned loosely.

Where you set the timeout Request timeout surface ?

Not documented Not verified

No request-timeout header or key on the fetched proxy/gateway docs ([Braintrust AI proxy](https://www.braintrust.dev/docs/deploy/ai-proxy)).

Where a request timeout can be set: per request, in a config file, in the vendor dashboard, or nowhere. Nine of the twenty products documented here do not describe a request timeout at all, so the worst case of a hung upstream call is unknowable from the docs.

Where you set retries Retry policy surface ?

Not documented Not verified

Default count and backoff: `n.a.` The documented failure path is failover to the next endpoint, not a retry counter ([Braintrust proxy fallback reference](https://www.braintrust.dev/docs/api-reference/proxy/proxy-any-openai-request-fallback)).

Where retry count and backoff are configured. Worth knowing alongside billing: a retried streaming call can be charged more than once.

Where you set fallbacks Fallback surface ?

Per request Not verified

ORDERED, comma-separated: header `x-bt-fallback-providers`. Response headers `x-bt-used-endpoint`, `x-bt-failover-from` and `x-bt-failover-to` report what happened; `x-bt-endpoint-name` pins a specific endpoint ([Braintrust proxy fallback reference](https://www.braintrust.dev/docs/api-reference/proxy/proxy-any-openai-request-fallback)).

Where the fallback chain is defined. Almost every product claims fallback; the useful question is whether you can change it from code or only by hand in a dashboard.

Shape of the fallback chain Fallback shape ?

Ordered list Not verified

An ordered list tries targets in sequence; a weighted split sends a percentage of traffic to each, which is what you need to trial a new model on 5% of requests. Weighted splits are much rarer than the marketing implies.

Upstream health tracking Health checks / circuit breaking ?

Fixed, cannot change Not verified

`not_configurable`, and what exists is health checking at the gateway's own edge rather than upstream provider ejection: the global endpoint `gateway.braintrust.dev` uses DNS latency-based routing plus health checks across `us-east-1`, `eu-west-1`, `us-west-2` and `ap-southeast-1` ([Braintrust gateway](https://www.braintrust.dev/docs/deploy/gateway)).

Whether the product notices a failing upstream and stops sending traffic to it, and whether you can tune the thresholds. This is what turns a provider outage into a blip rather than a sustained error rate, and only four of the twenty expose it.

Cross-region failover you control Multi-region failover surface ?

Fixed, cannot change Not verified

The vendor runs multiple regions behind one hostname with DNS health-checked routing; there is no user-facing cross-region failover config ([Braintrust gateway](https://www.braintrust.dev/docs/deploy/gateway)).

Whether you can define what happens when a region degrades. A vendor running many regions is not the same as a vendor letting you configure failover between them; only three document a user-controlled mechanism.

Where you set load balancing Load balancing surface ?

Fixed, cannot change Not verified

`not_configurable` at the weight level: the proxy automatically load-balances across multiple API keys configured for the same provider, and no weight key is documented ([Braintrust AI proxy](https://www.braintrust.dev/docs/deploy/ai-proxy)).

Where traffic distribution across upstreams or keys is configured.

Operations

Usage dashboards and logs Observability ?

Yes Verified 3 days ago

Built-in visibility into what was sent, what came back, what it cost, and how long it took.

Spending limits Budget controls ?

Not published Not verified

Hard caps that stop spend before it becomes a surprise invoice. The single most valuable control for a small team.

Rate limits Rate limits ?

Not published Not verified

Caps on request volume per key or per user, useful for protecting against abuse and runaway loops.

Separate keys per team or app Virtual keys ?

Yes Verified 3 days ago

Issue scoped keys with their own budgets and permissions so you can attribute cost and revoke access without rotating everything.

Prompt versioning Prompt management ?

Yes Verified 3 days ago

Store and version prompts outside your code so they can be changed without a deploy.

Quality testing Evals ?

Yes Verified 3 days ago

Built-in tooling to score model output against test cases, so you can tell whether a model swap made things better or worse.

MCP support MCP support ?

Not published Not verified

Native support for the Model Context Protocol, the emerging standard for connecting models to external tools.

What gets logged Logged content ?

Your choice Not verified

Logging through the proxy requires passing an `x-bt-parent` header to name the destination project; without it, requests are not logged, and the repo lists automatic logging as "coming soon" ([Braintrust AI proxy](https://www.braintrust.dev/docs/deploy/ai-proxy), [Braintrust proxy repo](https://github.com/braintrustdata/braintrust-proxy)). When logging is enabled, full request/response spans including prompt and completion text are stored ([View logs](https://www.braintrust.dev/docs/observe/view-logs))

Whether full prompts and responses are stored, only metadata, or nothing. Full-body logging is the most useful debugging feature here and the one most likely to need a conversation with your compliance team.

You can turn logging off Body-logging opt-out ?

Yes Not verified

Omitting `x-bt-parent` sends the request through without logging ([Braintrust AI proxy](https://www.braintrust.dev/docs/deploy/ai-proxy))

Whether prompt and response bodies can be suppressed while still keeping usage metrics. Nineteen of the twenty document a way to do this; the mechanisms range from a per-request header to an organisation-wide setting.

Traces you can take elsewhere Distributed tracing ?

OpenTelemetry Not verified

OpenTelemetry is supported natively: Braintrust exposes an OTel-compatible backend endpoint and documents OpenLLMetry and Vercel AI SDK instrumentation, with multi-step spans forming agent traces ([Braintrust OpenTelemetry](https://www.braintrust.dev/docs/integrations/sdk-integrations/opentelemetry), [View logs](https://www.braintrust.dev/docs/observe/view-logs))

Whether the product emits OpenTelemetry, a proprietary format, or nothing. OpenTelemetry means the traces land in the tooling you already run instead of only in the vendor’s dashboard.

Where telemetry can go Export destinations ?

Braintrust Not verified

CSV and JSON download from the logs UI, plus `bt sync pull` for NDJSON extraction to local/customer storage; the OTel endpoint is an ingest, not an export ([View logs](https://www.braintrust.dev/docs/observe/view-logs), [Braintrust OpenTelemetry](https://www.braintrust.dev/docs/integrations/sdk-integrations/opentelemetry))

Documented sinks for logs and metrics. This is a good proxy for how replaceable the vendor’s own dashboard is: around twenty destinations means you never have to depend on it, while a CSV download means you do.

Can record user feedback Feedback capture API ?

Yes Not verified

`POST /v1/project_logs/{project_id}/feedback` attaches scores, comments, and metadata to a logged span ([Feedback API](https://www.braintrust.dev/docs/api-reference/logs/feedback-for-project-logs-events))

Whether there is an API to attach a rating or score to a logged request, which is what lets production traffic feed quality work later.

Scores live traffic Online eval hooks ?

Yes Not verified

Yes — online scoring runs automated scorers against logged production traffic inside Braintrust; it is a Braintrust platform feature ([View logs](https://www.braintrust.dev/docs/observe/view-logs))

Whether automated scorers can run against real production requests, rather than only against a test set you assemble yourself.

Performance

Delay it adds Proxy overhead ?

Not published Not verified

Extra time the product itself adds to each request, on top of however long the model takes. Usually irrelevant next to multi-second model latency, but it matters for high-volume or streaming-sensitive workloads.

Requests per second ceiling Throughput ?

Not published Not verified

Published sustained request rate before the product becomes the bottleneck. Only relevant at genuinely high volume.

What the request path runs on Architecture class ?

Edge worker Not verified

Repo is TypeScript 99.0% and is documented as deployable to Vercel, Cloudflare Workers, AWS Lambda or Express ([braintrustdata/braintrust-proxy](https://github.com/braintrustdata/braintrust-proxy)).

The comparable way to talk about latency here. An edge worker, a compiled Go or Rust binary, and a Python proxy have different overhead floors no matter which figures each vendor publishes. Products that never disclose their runtime are recorded as undisclosed rather than assumed.

You can run the request path yourself Self-hostable data plane ?

Yes Not verified

MIT-licensed repo with deploy targets for Vercel, Cloudflare, AWS Lambda and a Node/Express server ([braintrustdata/braintrust-proxy](https://github.com/braintrustdata/braintrust-proxy)).

Whether the component that actually carries your prompts can run on your own infrastructure. Distinct from a vendor offering a self-hosted control plane while still proxying traffic through their network.

Streaming responses Streaming support ?

Yes Not verified

Supported, and failover is documented as working for streaming requests. Caveat: caching is disabled for requests that went through failover ([Braintrust proxy fallback reference](https://www.braintrust.dev/docs/api-reference/proxy/proxy-any-openai-request-fallback)).

Whether token-by-token streaming is documented. The caveats matter more than the yes: some products cannot cancel a stream without still being billed, and several timeout and fallback mechanisms stop applying once the first token has been sent.

Security & compliance

Does your prompt reach their servers Prompt transits vendor ?

Depends how you deploy it Not verified

Three shapes: multi-tenant SaaS, bring-your-own-cloud where Braintrust operates the data plane inside your account, or full self-hosting. In BYOC the SDK and browser talk straight to your data plane, so no AI data crosses Braintrust's control plane.

Whether the text you send passes through this company’s own infrastructure. If it does, every other promise on this page is a policy commitment rather than a physical impossibility. Self-hosted products can answer no outright.

What they keep if you change nothing Logging default ?

Yes — prompts and replies Not verified

Once instrumented, Braintrust captures every request as a trace. That is the product, not a side effect — the data plane stores prompts, outputs, datasets and traces.

Defaults matter more than options. A product that stores full prompts and replies unless you find the right header will have stored them by the time you read the docs.

How long they keep it Default content retention (days) ?

14 days Not verified

Fourteen days on Starter, thirty on Pro (extendable to 180 in 30-day steps), up to 365 on Enterprise.

Default retention for request content, in days. Zero means nothing is kept. Read the note: several products keep nothing as a rule but make timed exceptions for abuse review or specific models.

Could they train on your prompts Training on customer data ?

No Not verified

Prompts, traces and customer conversations are never used to improve models.

Whether the vendor may use your prompts and outputs to train models. “Not published” means we could not find any position, which is not the same as a no — ask for it in writing.

Where it runs, and what you can pin Region and residency control ?

Hosted data plane in the US or the EU on Pro. BYOC and self-hosted keep data in your own cloud account and region. Not verified

Which regions are offered and whether you can force processing to stay in one. A global endpoint that silently picks a region is a different compliance story from an endpoint you pin yourself.

Where safety filters run Guardrail execution location ?

Either, depending on deployment Not verified

Global masking functions redact PII before logging. In BYOC or self-hosted that masking runs inside your own cloud.

A filter that strips personal data only helps if it runs before the data leaves your boundary. If guardrails execute in the vendor’s cloud, the vendor has already received whatever you wanted redacted.

Who else touches the data Subprocessor list ?

https://www.braintrust.dev/legal/dpa Not verified

The published list of third parties the vendor passes your data to. No list means you cannot know the full chain, which most data-protection agreements require you to.

SOC 2 audited SOC 2 audited ?

Yes Verified 3 days ago

An independent audit of security controls. Enterprise buyers and their procurement teams routinely require it.

Will sign a HIPAA agreement HIPAA BAA ?

Yes Verified 3 days ago

Required before you may send protected health information through the service. Without a signed BAA, healthcare data is off limits.

GDPR commitments GDPR commitments ?

Not published Not verified

Published data processing terms for handling personal data of people in the EU and UK.

Can keep data in the EU EU data residency ?

Yes Verified 3 days ago

Requests can be processed inside the EU rather than routed to US infrastructure. Often the deciding constraint for European customers.

Does not retain your data Zero data retention ?

Not published Not verified

Prompts and responses are not stored after the request completes. Sometimes a paid add-on rather than the default.

Strips personal data PII redaction ?

Not published Not verified

Detects and removes identifiers such as names, emails, and card numbers before the request reaches the model provider.

Content guardrails Content guardrails ?

No Verified 3 days ago

Policy checks on inputs and outputs — blocking unsafe content, enforcing formats, or catching prompt-injection attempts.

Runs fully disconnected Air-gapped deployment ?

Not published Not verified

Can be deployed in a network with no internet access, which some regulated and defence environments require.

Blocks personal data in prompts PII / DLP enforcement ?

Not documented Not verified

The AI proxy documentation describes routing, caching, and logging; no PII scanner ([Braintrust AI proxy](https://www.braintrust.dev/docs/deploy/ai-proxy))

Whether personal data detection sits on the request path and can stop the call, merely inspects and forwards it, or is not documented. A control that only reports is a logging feature, not a policy control.

Blocks prompt injection Injection / jailbreak enforcement ?

Not documented Not verified

Same ([Braintrust AI proxy](https://www.braintrust.dev/docs/deploy/ai-proxy))

Whether injection and jailbreak detection can stop a request. Most products offering this call a partner classifier rather than shipping their own.

Blocks harmful content Toxicity / moderation enforcement ?

Not documented Not verified

Same ([Braintrust proxy repo](https://github.com/braintrustdata/braintrust-proxy))

Whether hate, violence, sexual and self-harm categories are checked inline and can stop a request, in either direction.

Your own policy rules Custom policy hooks ?

Not documented Not verified

No request-path policy engine documented; policies exist as scorers applied to logs, not as blocking checks ([View logs](https://www.braintrust.dev/docs/observe/view-logs))

Whether you can add your own rule — a regex, a webhook, or your own classifier — rather than choosing from the vendor library.

Where guardrails run Guardrail execution location ?

Not documented Not verified

Whether guardrail evaluation happens inside your infrastructure or on the vendor’s servers. This decides whether the prompt you are trying to protect leaves your network in order to be checked.

If the guardrail itself fails Guardrail failure mode ?

Not documented Not verified

`not_documented` ([Braintrust AI proxy](https://www.braintrust.dev/docs/deploy/ai-proxy))

What happens when the guardrail service times out or errors: does the request proceed unchecked, or is it blocked? This is the worst-documented field in the entire catalogue — only two vendors state it plainly, which means most teams are running a control whose failure behaviour they cannot know.

Third-party guardrail vendors Guardrail integrations ?

Not published Not verified

Named external guardrail services the product can call. A long list means the product is a router for policy engines rather than a policy engine itself — which also means another vendor bill and another hop.

Fit & integration

Work to try it Evaluation work shape ?

Change one base URL Not verified

The shape of the work on the vendor’s own quickstart, from swapping one base URL through to deploying infrastructure. An ordinal class rather than a duration, because elapsed time depends on accounts and quota we cannot see.

Work to run it Production work shape ?

Change one base URL Not verified

The same scale applied to the vendor’s recommended production path. For several products this is much heavier than the quickstart, which is exactly why both are recorded.

Steps on the quickstart Numbered quickstart steps ?

0 Not verified

The page carrying the quickstart and first-call snippet is marked deprecated, and it publishes no numbered procedure. The current Gateway page has no quickstart at all.

A literal count of numbered steps on the vendor’s quickstart, recorded as evidence beside the work shape. Zero means the page publishes no numbered procedure at all. Large counts usually mean interleaved language tracks rather than more work.

Can you self-host it today Self-host install documentation ?

Offered, but no command published Not verified

No literal command is published; self-hosting uses "official Terraform modules" on AWS (ECS/EC2) and GCP/Azure (Kubernetes and Helm), with Braintrust hosting the control plane ([Self-hosting Braintrust](https://www.braintrust.dev/docs/admin/self-hosting))

Whether an install command is actually published. Several products advertise self-hosting while publishing no command to start from, which a plain yes/no would hide.

Works with the OpenAI SDK OpenAI SDK drop-in ?

Yes Not verified

Yes. The AI proxy is “fully compatible with the OpenAI SDK”; set `baseURL`/`base_url` to `https://api.braintrust.dev/v1/proxy`. The Gateway documentation also supports keeping the OpenAI SDK and changing the base URL to `https://gateway.braintrust.dev`, with a Braintrust API key. ([Braintrust Gateway documentation](https://www.braintrust.dev/docs/deploy/gateway))

Whether an existing OpenAI-compatible client can be pointed at it by changing the base URL and key.

Vercel AI SDK support AI SDK provider package ?

Documented integration, not a provider Not verified

Braintrust documents a Vercel AI SDK integration. Install `braintrust`, `ai`, and `zod` with `pnpm add braintrust ai zod` or `npm install braintrust ai zod`; use `wrapAISDK` for AI SDK v3–v6 or `braintrustAISDKTelemetry()` for AI SDK v7. ([Braintrust Vercel AI SDK integration](https://www.braintrust.dev/docs/integrations/sdk-integrations/vercel))

Whether a first-party AI SDK provider package exists, or only a community package, a documented workaround, or the generic OpenAI provider pointed at a custom base URL.

Python framework integrations Documented Python frameworks ?

LangChain, LlamaIndex Not verified

LangChain and LlamaIndex integrations are documented. The LlamaIndex integration uses packages including `braintrust`, `llama-index`, `llama-index-llms-openai`, and `openinference-instrumentation-llama-index`, with `braintrust.auto_instrument()`, `setup_llamaindex()`, `LlamaIndexInstrumentor`, and `BraintrustSpanProcessor`. ([Braintrust LlamaIndex integration](https://www.braintrust.dev/docs/integrations/sdk-integrations/llamaindex))

LangChain, LangGraph, LlamaIndex and similar orchestration frameworks with a documented integration.

Callable from Cloudflare Workers Cloudflare Workers support ?

Documented from your Worker Not verified

Cloudflare Workers are supported. Documented integrations include `OpenAIRealtimeWebSocket` from `openai/realtime/websocket` for realtime connections and `wrapCloudflareAIChat()` from `braintrust` for Cloudflare AI Chat tracing; Cloudflare Workers require `nodejs_compat`, a `BRAINTRUST_API_KEY` Wrangler secret, and flushing with `ctx.waitUntil(logger.flush())`. ([Braintrust Cloudflare AI Chat integration](https://www.braintrust.dev/docs/integrations/agent-frameworks/cloudflare-ai-chat))

Whether the docs show calling this product from your own Worker. Deliberately separated from the several products whose own gateway runs on Workers, which is a fact about their infrastructure and not about your edge compatibility.

Kubernetes install Helm chart availability ?

Official Helm chart Not verified

Official self-hosting deployment uses the Helm chart named `braintrust`, installed from `oci://public.ecr.aws/braintrust/helm/braintrust`, with the chart repository at `https://github.com/braintrustdata/helm`. Other evidence documents chart versions `6.2.1`, `6.13.0+`, and `v5.0.1+` for specific self-hosting and scaling features. ([Braintrust self-hosting deployment](https://www.braintrust.dev/docs/admin/self-hosting/deploy))

Whether a named, published Helm chart exists, versus Helm being referenced with no chart named, versus generic cluster documentation that has nothing to do with this product.

Terraform support Terraform provider or modules ?

Official modules Not verified

Official Terraform modules are documented for AWS, GCP, and Azure: `github.com/braintrustdata/terraform-aws-braintrust-data-plane`, `github.com/braintrustdata/terraform-google-braintrust-data-plane`, and `github.com/braintrustdata/terraform-azure-braintrust-data-plane`. Additional documentation identifies Terraform module versions `v5.2.1` and `v6.0` for specific AWS deployments; no Terraform Registry name is stated. ([Braintrust self-hosting deployment](https://www.braintrust.dev/docs/admin/self-hosting/deploy))

Whether you can declare this in code: an official provider, official modules, resources inside a hyperscaler’s provider, a community provider, or only Terraform code shipped in a repo.

Reuses your cloud identity Cloud IAM reuse ?

Reuses your cloud identity Not verified

Braintrust documents keyless cloud authentication and IAM reuse. AWS Bedrock supports STS `AssumeRole`; Azure AI Foundry and Azure OpenAI support Microsoft Entra Workload Identity using Braintrust-signed OIDC tokens; Google Vertex AI supports Workload Identity Federation using Braintrust-signed OIDC tokens. Self-hosted GCP deployments also use Workload Identity for GCS, and Azure uses workload identity for Key Vault. ([Braintrust changelog](https://www.braintrust.dev/docs/changelog))

Whether you can authenticate with IAM roles, workload identity or managed identities instead of another long-lived API key. Distinguished from products that only accept static upstream provider credentials.

Fits behind your API gateway API gateway integration ?

Service mesh routing documented Not verified

Chart-managed Istio integration is documented through an Istio `VirtualService`; enable `virtualService.workloadIsolation.enabled: true`, along with `virtualService.enabled: true` and `api.workloadIsolation.enabled: true`. No Kong, APISIX, Envoy, nginx, or other gateway plugin is documented. ([Braintrust self-hosting scaling configuration](https://ai-proxy-5k9q3mg0z.preview.braintrust.dev/docs/admin/self-hosting/configure/scaling))

Whether AI traffic can go through a gateway you already run, and who documented that — the product’s vendor or the gateway’s.

MCP support MCP surface shape ?

Hosted MCP server Not verified

Braintrust provides a hosted MCP server at `https://api.braintrust.dev/mcp` using streamable HTTP, with support for Claude Code, Cursor, Codex, VS Code, and other MCP-compatible clients. It supports reading and writing Braintrust data, querying logs, authoring prompts and scorers, configuring monitoring, and running evals; self-hosted deployments use the MCP URL shown in organization data-plane settings. ([Braintrust MCP integration](https://www.braintrust.dev/docs/integrations/developer-tools/mcp))

Which kind of MCP support this is: a gateway that governs many MCP servers, a hosted MCP server you connect to, MCP tools accepted inside the completion API, or client tooling. These are different products behind one acronym.

Needs your own provider key Upstream provider key required ?

Optional Not verified

Optional, not required: with an account "you can use a single Braintrust API key to access all AI providers"; without an account "you can use the proxy with individual provider API keys." For tracing, "you must use a `BRAINTRUST_API_KEY` rather than a provider's key." ([AI proxy - Braintrust](https://www.braintrust.dev/docs/guides/proxy))

Whether an upstream provider account and key must exist before your first call works. A prerequisite rather than a step, and it can differ between the hosted and self-hosted forms of the same product.

Gate before models work Model access gate ?

No gate Not verified

No model gate: "The proxy supports over 100 models... New models are added regularly." One org-level enablement gate exists for infra monitoring: "The Infra dashboard option is available once Braintrust has enabled infrastructure monitoring for your organization." ([AI proxy - Braintrust](https://www.braintrust.dev/docs/guides/proxy), [Self-hosting Braintrust](https://www.braintrust.dev/docs/admin/self-hosting))

Whether an enablement click, a quota grant, a paid tier or an approval form stands between a valid key and a working model call.

Official client languages First-party client SDK languages ?

TypeScript, Python, Go, Java, Ruby, C# Not verified

Documented provider clients include the OpenAI SDK (`openai` for TypeScript/Python), Anthropic SDK (`@anthropic-ai/sdk` and `anthropic`), Google GenAI SDK (`@google/genai` and `google.genai`), and cURL. Braintrust’s official/native SDKs are documented for TypeScript/JavaScript (`braintrust`), Python (`braintrust`), Go, Java, Ruby, and C#/.NET; `@braintrust/otel` provides OpenTelemetry functionality. ([Braintrust changelog](https://www.braintrust.dev/docs/changelog))

Languages with a first-party client library. An empty list can still mean the product is usable from any language via an OpenAI-compatible SDK.

Additional charges

These are the fees that do not appear on a per-token price list, and they are where estimates usually go wrong.

• Pro platform fee $249/month (includes $249 model credits, 5 GB data, 50k scores)
• Processed data overage $4/GB (Starter), $3/GB (Pro)
• Scores overage $2.50 per 1,000 (Starter), $1.50 per 1,000 (Pro)
• Extended retention $0.50 per GB per month beyond the included 30 days (Pro, up to 180 days)