Fireworks AI serverless models, deployed models, shapes and routers (BYOK)

Fireworks AI serverless models, deployed models, shapes and routers (BYOK) — connector documentation

• MCP endpoint: https://byok-fireworks-serving.connectorbay.com/mcp
• REST API: POST https://byok-fireworks-serving.connectorbay.com/v1/tools/{tool_name}, described by the OpenAPI 3.1 spec at https://byok-fireworks-serving.connectorbay.com/openapi.json
• Transport: Streamable HTTP, stateless, MCP specification 2025-06-18 or later
• Authentication: your own Fireworks Serving Fireworks API key, sent in the X-Upstream-Key header of every request (never stored, logged or cached)
• Health: https://byok-fireworks-serving.connectorbay.com/health · Tool schemas: https://byok-fireworks-serving.connectorbay.com/tools.json
• Publisher: Unify Dynamics LLC · connectorbay.com/byok-fireworks-serving · agent@connectorbay.com

What Fireworks AI serverless models, deployed models, shapes and routers (BYOK) is for

Fireworks AI serverless models, deployed models, shapes and routers (BYOK) lets an AI assistant read your own Fireworks Serving data through the Fireworks Serving API with a key you supply (Fireworks API key). Read-only: 7 tools (list_serverless_models, list_deployed_models, get_deployed_model, list_deployment_shapes, list_routers, get_usage_limits, get_serverless_rate_limits). The BYOK key travels with each request, is used for that one call only and is never stored, logged or cached; it is only ever sent to api.fireworks.ai. Unofficial connector by Unify Dynamics LLC: not affiliated with, endorsed by or sponsored by Fireworks Serving. Fireworks Serving and its logos are trademarks of their owners and are used only to say which service the connector works with.

Ask your assistant things like:

• "Which Fireworks models can I run serverless and which are about to be deprecated?"
• "Which models are deployed in my Fireworks account?"
• "Show Fireworks deployed model dm1"
• "Which Fireworks deployment shapes fit Llama 3.1 8B?"
• "Which routers do I have on Fireworks?"
• "How much of my Fireworks usage limit have I used?"

What it does

• list_serverless_models: List models available on serverless inference with kind, context length, tool and image support, LoRA support and deprecation date. Use account 'fireworks' for the public catalog. Reads configuration only: it sends no prompt and uses no tokens.
• list_deployed_models: List models attached to deployments in your account with state, whether each is the default and whether it is serverless. Reads configuration only: it sends no prompt and uses no tokens.
• get_deployed_model: Get one deployed model by id with its model, deployment and state. Reads configuration only: it sends no prompt and uses no tokens.
• list_deployment_shapes: List deployment shapes (tested hardware and precision presets) with accelerator type and count, precision and maximum context length. Optionally only those compatible with a model. Reads configuration only: it sends no prompt and uses no tokens.
• list_routers: List routers (traffic splitters over deployments) with state, model, deployments and aliases. Reads configuration only: it sends no prompt and uses no tokens.
• get_usage_limits: Show the account's spend limit settings: default per-user limit, enforcement mode and amount used. Reads configuration only: it sends no prompt and uses no tokens.
• get_serverless_rate_limits: Show the effective serverless rate limits per deployment and metric (peak values per interval are in a separate series that is not returned). Reads configuration only: it sends no prompt and uses no tokens.

BYOK key

You bring your own Fireworks Serving Fireworks API key (https://app.fireworks.ai/settings/users/api-keys). Your assistant sends it in the X-Upstream-Key header with each request. ConnectorBay uses it for that one call only: it is never stored, logged or cached, never shown in an answer, and it is only sent to api.fireworks.ai over https, with no redirects followed. Create a key with the fewest permissions the tools need (read-only if the provider offers it), and revoke it at the provider whenever you like.

Data sources

• https://docs.fireworks.ai/api-reference/list-deployed-models.md (the API this connector calls, with a BYOK key)

Live from the Fireworks Serving API (api.fireworks.ai) with a BYOK key; documentation: https://docs.fireworks.ai/api-reference/list-deployed-models.md. Endpoints checked against that documentation on 2026-10-16.

What it is not

Unofficial connector by Unify Dynamics LLC: not affiliated with, endorsed by or sponsored by Fireworks Serving. Fireworks Serving and its logos are trademarks of their owners and are used only to say which service the connector works with. It is read-only: it never creates, changes, sends or deletes anything in your Fireworks Serving account.

Built for: Worldwide. Languages: English.

Fireworks AI serverless models, deployed models, shapes and routers (BYOK) — Privacy Policy

Effective 24 October 2026. Unify Dynamics LLC ("we", "us"), Menlo Park, California.

What Fireworks AI serverless models, deployed models, shapes and routers (BYOK) is. Fireworks AI serverless models, deployed models, shapes and routers (BYOK) is a connector (an MCP server and REST API) that an AI assistant calls on your behalf to read your own Fireworks Serving data: Read the Fireworks AI serverless model catalog, your deployed models, deployment shapes, routers, usage limits and serverless rate limits with your own API key. You bring your own Fireworks Serving Fireworks API key; the assistant sends it to us with each request.

BYOK key. The key you supply is used to make the one Fireworks Serving call you asked for. Our application does not store it, write it to a log, put it in a cache, or share it. It is sent only to api.fireworks.ai, over https, and is removed from any text we return to you or your assistant. We do not follow redirects with your key. If Fireworks Serving rejects it, we say so without repeating it.

What we receive. The arguments of each tool call, the BYOK key (for that call only), the technical headers needed to serve the request (an IP address or a client identifier supplied by the assistant) and standard server logs. What Fireworks Serving receives. The request we make on your behalf, including the key and the arguments, under Fireworks Serving's own terms and privacy policy. Fireworks Serving acts at your direction and is the only recipient of the data of your request besides our hosting provider.

What we return. The answer Fireworks Serving gives for your request, trimmed to the fields the tool documents. We do not keep it: it is returned to your assistant and not stored, cached or used to train anything.

What we do not do. We do not build a profile, sell or share personal information, or keep your Fireworks Serving data. Rate-limit counters (a client identifier and timestamps) are held in memory for at most 24 hours. Hosting access logs (IP addresses, request paths and status codes) are kept for up to 30 days for security and abuse prevention; our application adds no request headers or bodies to them.

Sub-processors. Fireworks Serving (the API you call with a BYOK key, at your direction). Hosting: Vercel (United States regions).

Your rights. Because we store no personal data beyond short-lived logs, requests to access, correct or delete data are usually satisfied automatically; you can still contact agent@connectorbay.com and we will respond within 30 days. Revoke your key at Fireworks Serving at any time to end all access.

Children. Fireworks AI serverless models, deployed models, shapes and routers (BYOK) is a general-audience service operated by the adult using the assistant, under Fireworks Serving's own age rules.

Changes. We will post changes here with a new effective date.

Fireworks AI serverless models, deployed models, shapes and routers (BYOK) — Terms of Service

Effective 24 October 2026. These terms govern use of the Fireworks AI serverless models, deployed models, shapes and routers (BYOK) connector ("the Service") operated by Unify Dynamics LLC ("we", "us").

1. The Service. Fireworks AI serverless models, deployed models, shapes and routers (BYOK) provides: Read the Fireworks AI serverless model catalog, your deployed models, deployment shapes, routers, usage limits and serverless rate limits with your own API key. It is accessed through an AI assistant or directly over MCP or HTTP, and is read-only.
2. Your own key, your own account. You must use your own Fireworks Serving credentials and only access data you are allowed to access. Fireworks Serving's terms apply to your use of Fireworks Serving; you are responsible for complying with them, including any rate limits and permitted uses. Do not share a key you do not own.
3. Independent. Unofficial connector by Unify Dynamics LLC: not affiliated with, endorsed by or sponsored by Fireworks Serving. Fireworks Serving and its logos are trademarks of their owners and are used only to say which service the connector works with.
4. No advice, no guarantees. Output is the data Fireworks Serving returns, lightly trimmed; it may be incomplete, delayed or changed by Fireworks Serving. Check important facts at the source.
5. Read-only. The Service does not create, change, send or delete anything in your Fireworks Serving account.
6. Acceptable use. Automated use within the published rate limits is welcome. Do not use the Service to access data you are not entitled to, to circumvent Fireworks Serving's controls, or to attack any system.
7. Availability. The Service is provided "as is" without warranty. We may change, limit or discontinue it at any time; Fireworks Serving may change or end its API at any time.
8. Data. Our Privacy Policy describes what we process. In short: the BYOK key is used for the one call and not stored or logged.
9. Pro keys. Optional ConnectorBay Pro API keys are issued at our discretion and are separate from your Fireworks Serving key.
10. Liability. To the fullest extent permitted by law, Unify Dynamics LLC is not liable for any loss arising from use of or reliance on the Service, including any action Fireworks Serving takes on your account. Our total liability is limited to US $100.
11. Governing law. California law; venue in San Mateo County, California.
12. Contact. Unify Dynamics LLC · agent@connectorbay.com · https://connectorbay.com/byok-fireworks-serving

Fireworks AI serverless models, deployed models, shapes and routers (BYOK) support

Email agent@connectorbay.com. We answer within two business days.

• MCP endpoint: https://byok-fireworks-serving.connectorbay.com/mcp
• REST API: https://byok-fireworks-serving.connectorbay.com/openapi.json
• Live status: https://byok-fireworks-serving.connectorbay.com/health

When you report a problem, include the question you asked your agent, roughly when, and which agent you used (for example Claude, ChatGPT or Gemini). Never send us passwords, account numbers or ID numbers. Fireworks AI serverless models, deployed models, shapes and routers (BYOK) never asks for them.