{"openapi":"3.1.0","info":{"title":"Fireworks AI serverless models, deployed models, shapes and routers (your key) API","version":"0.1.0","description":"Fireworks AI serverless models, deployed models, shapes and routers (your key) 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...\n\nEvery operation is read-only or compute-only. The same tools are available over MCP (streamable HTTP) at https://byok-fireworks-serving.connectorbay.com/mcp.","contact":{"name":"Unify Dynamics LLC","email":"agent@connectorbay.com","url":"https://connectorbay.com/byok-fireworks-serving/docs"},"termsOfService":"https://connectorbay.com/byok-fireworks-serving/terms"},"servers":[{"url":"https://byok-fireworks-serving.connectorbay.com"}],"externalDocs":{"url":"https://connectorbay.com/byok-fireworks-serving/docs"},"security":[{"upstreamKey":[]}],"components":{"securitySchemes":{"bearer":{"type":"http","scheme":"bearer","description":"Optional. A Pro API key raises rate limits; no credentials are required."},"upstreamKey":{"type":"apiKey","in":"header","name":"X-Upstream-Key","description":"Your own key for the service this connector wraps (bring your own key). Used for that one call only; never stored, logged or cached."}},"schemas":{"Error":{"type":"object","properties":{"ok":{"const":false},"error":{"type":"object"}}}}},"paths":{"/v1/tools/list_serverless_models":{"post":{"operationId":"list_serverless_models","summary":"List models available on serverless inference with kind, context length, tool and image support, LoRA support and deprec","description":"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. Use for \"Which Fireworks models can I run serverless and which are about to be deprecated\".","tags":["tools"],"requestBody":{"required":true,"content":{"application/json":{"schema":{"properties":{"account_id":{"description":"Account id: 'fireworks' for the public catalog, or your own account id.","maxLength":100,"title":"Account Id","type":"string"},"page_size":{"anyOf":[{"maximum":200,"minimum":1,"type":"integer"},{"type":"null"}],"default":50,"description":"Items per page (default 50, values above 200 are treated as 200).","title":"Page Size"},"page_token":{"anyOf":[{"maxLength":200,"type":"string"},{"type":"null"}],"default":null,"description":"Token from the previous answer's nextPageToken to get the following page.","title":"Page Token"},"filter":{"anyOf":[{"maxLength":300,"type":"string"},{"type":"null"}],"default":null,"description":"Optional filter expression in Google AIP-160 syntax.","title":"Filter"},"order_by":{"anyOf":[{"maxLength":100,"type":"string"},{"type":"null"}],"default":null,"description":"Comma-separated fields to order by; add ' desc' after a field for descending.","title":"Order By"}},"required":["account_id"],"title":"list_serverless_modelsArguments","type":"object"}}}},"responses":{"200":{"description":"Tool result. `ok: true` on success; `ok: false` with a structured `error` (provider_unavailable, upstream_error, bad_input) when the tool could not answer.","content":{"application/json":{"schema":{"type":"object","additionalProperties":true}}}},"422":{"description":"Arguments failed validation","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"429":{"description":"Rate limit exceeded (see Retry-After)","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}},"x-read-only":true}},"/v1/tools/list_deployed_models":{"post":{"operationId":"list_deployed_models","summary":"List models attached to deployments in your account with state, whether each is the default and whether it is serverless","description":"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. Use for \"Which models are deployed in my Fireworks account\".","tags":["tools"],"requestBody":{"required":true,"content":{"application/json":{"schema":{"properties":{"account_id":{"description":"Your Fireworks account id (the id in your account's resource names, for example 'my-account').","maxLength":100,"title":"Account Id","type":"string"},"page_size":{"anyOf":[{"maximum":200,"minimum":1,"type":"integer"},{"type":"null"}],"default":50,"description":"Items per page (default 50, values above 200 are treated as 200).","title":"Page Size"},"page_token":{"anyOf":[{"maxLength":200,"type":"string"},{"type":"null"}],"default":null,"description":"Token from the previous answer's nextPageToken to get the following page.","title":"Page Token"},"filter":{"anyOf":[{"maxLength":300,"type":"string"},{"type":"null"}],"default":null,"description":"Optional filter expression in Google AIP-160 syntax.","title":"Filter"},"order_by":{"anyOf":[{"maxLength":100,"type":"string"},{"type":"null"}],"default":null,"description":"Comma-separated fields to order by; add ' desc' after a field for descending.","title":"Order By"}},"required":["account_id"],"title":"list_deployed_modelsArguments","type":"object"}}}},"responses":{"200":{"description":"Tool result. `ok: true` on success; `ok: false` with a structured `error` (provider_unavailable, upstream_error, bad_input) when the tool could not answer.","content":{"application/json":{"schema":{"type":"object","additionalProperties":true}}}},"422":{"description":"Arguments failed validation","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"429":{"description":"Rate limit exceeded (see Retry-After)","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}},"x-read-only":true}},"/v1/tools/get_deployed_model":{"post":{"operationId":"get_deployed_model","summary":"Get one deployed model by id with its model, deployment and state. Reads configuration only: it sends no prompt and uses","description":"Get one deployed model by id with its model, deployment and state. Reads configuration only: it sends no prompt and uses no tokens. Use for \"Show Fireworks deployed model dm1\".","tags":["tools"],"requestBody":{"required":true,"content":{"application/json":{"schema":{"properties":{"account_id":{"description":"Your Fireworks account id (the id in your account's resource names, for example 'my-account').","maxLength":100,"title":"Account Id","type":"string"},"deployed_model_id":{"description":"Deployed model id, the last part of its name.","maxLength":100,"title":"Deployed Model Id","type":"string"}},"required":["account_id","deployed_model_id"],"title":"get_deployed_modelArguments","type":"object"}}}},"responses":{"200":{"description":"Tool result. `ok: true` on success; `ok: false` with a structured `error` (provider_unavailable, upstream_error, bad_input) when the tool could not answer.","content":{"application/json":{"schema":{"type":"object","additionalProperties":true}}}},"422":{"description":"Arguments failed validation","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"429":{"description":"Rate limit exceeded (see Retry-After)","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}},"x-read-only":true}},"/v1/tools/list_deployment_shapes":{"post":{"operationId":"list_deployment_shapes","summary":"List deployment shapes (tested hardware and precision presets) with accelerator type and count, precision and maximum co","description":"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. Use for \"Which Fireworks deployment shapes fit Llama 3.1 8B\".","tags":["tools"],"requestBody":{"required":true,"content":{"application/json":{"schema":{"properties":{"account_id":{"description":"Account id: 'fireworks' for the public shapes, or your own account id.","maxLength":100,"title":"Account Id","type":"string"},"target_model":{"anyOf":[{"maxLength":300,"type":"string"},{"type":"null"}],"default":null,"description":"Only shapes compatible with this model resource name.","title":"Target Model"},"page_size":{"anyOf":[{"maximum":200,"minimum":1,"type":"integer"},{"type":"null"}],"default":50,"description":"Items per page (default 50, values above 200 are treated as 200).","title":"Page Size"},"page_token":{"anyOf":[{"maxLength":200,"type":"string"},{"type":"null"}],"default":null,"description":"Token from the previous answer's nextPageToken to get the following page.","title":"Page Token"},"filter":{"anyOf":[{"maxLength":300,"type":"string"},{"type":"null"}],"default":null,"description":"Optional filter expression in Google AIP-160 syntax.","title":"Filter"},"order_by":{"anyOf":[{"maxLength":100,"type":"string"},{"type":"null"}],"default":null,"description":"Comma-separated fields to order by; add ' desc' after a field for descending.","title":"Order By"}},"required":["account_id"],"title":"list_deployment_shapesArguments","type":"object"}}}},"responses":{"200":{"description":"Tool result. `ok: true` on success; `ok: false` with a structured `error` (provider_unavailable, upstream_error, bad_input) when the tool could not answer.","content":{"application/json":{"schema":{"type":"object","additionalProperties":true}}}},"422":{"description":"Arguments failed validation","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"429":{"description":"Rate limit exceeded (see Retry-After)","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}},"x-read-only":true}},"/v1/tools/list_routers":{"post":{"operationId":"list_routers","summary":"List routers (traffic splitters over deployments) with state, model, deployments and aliases. Reads configuration only: ","description":"List routers (traffic splitters over deployments) with state, model, deployments and aliases. Reads configuration only: it sends no prompt and uses no tokens. Use for \"Which routers do I have on Fireworks\".","tags":["tools"],"requestBody":{"required":true,"content":{"application/json":{"schema":{"properties":{"account_id":{"description":"Your Fireworks account id (the id in your account's resource names, for example 'my-account').","maxLength":100,"title":"Account Id","type":"string"},"page_size":{"anyOf":[{"maximum":200,"minimum":1,"type":"integer"},{"type":"null"}],"default":50,"description":"Items per page (default 50, values above 200 are treated as 200).","title":"Page Size"},"page_token":{"anyOf":[{"maxLength":200,"type":"string"},{"type":"null"}],"default":null,"description":"Token from the previous answer's nextPageToken to get the following page.","title":"Page Token"},"filter":{"anyOf":[{"maxLength":300,"type":"string"},{"type":"null"}],"default":null,"description":"Optional filter expression in Google AIP-160 syntax.","title":"Filter"},"order_by":{"anyOf":[{"maxLength":100,"type":"string"},{"type":"null"}],"default":null,"description":"Comma-separated fields to order by; add ' desc' after a field for descending.","title":"Order By"}},"required":["account_id"],"title":"list_routersArguments","type":"object"}}}},"responses":{"200":{"description":"Tool result. `ok: true` on success; `ok: false` with a structured `error` (provider_unavailable, upstream_error, bad_input) when the tool could not answer.","content":{"application/json":{"schema":{"type":"object","additionalProperties":true}}}},"422":{"description":"Arguments failed validation","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"429":{"description":"Rate limit exceeded (see Retry-After)","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}},"x-read-only":true}},"/v1/tools/get_usage_limits":{"post":{"operationId":"get_usage_limits","summary":"Show the account's spend limit settings: default per-user limit, enforcement mode and amount used. Reads configuration o","description":"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. Use for \"How much of my Fireworks usage limit have I used\".","tags":["tools"],"requestBody":{"required":true,"content":{"application/json":{"schema":{"properties":{"account_id":{"description":"Your Fireworks account id (the id in your account's resource names, for example 'my-account').","maxLength":100,"title":"Account Id","type":"string"}},"required":["account_id"],"title":"get_usage_limitsArguments","type":"object"}}}},"responses":{"200":{"description":"Tool result. `ok: true` on success; `ok: false` with a structured `error` (provider_unavailable, upstream_error, bad_input) when the tool could not answer.","content":{"application/json":{"schema":{"type":"object","additionalProperties":true}}}},"422":{"description":"Arguments failed validation","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"429":{"description":"Rate limit exceeded (see Retry-After)","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}},"x-read-only":true}},"/v1/tools/get_serverless_rate_limits":{"post":{"operationId":"get_serverless_rate_limits","summary":"Show the effective serverless rate limits per deployment and metric (peak values per interval are in a separate series t","description":"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. Use for \"What are my effective Fireworks serverless rate limits\".","tags":["tools"],"requestBody":{"required":true,"content":{"application/json":{"schema":{"properties":{"account_id":{"description":"Your Fireworks account id (the id in your account's resource names, for example 'my-account').","maxLength":100,"title":"Account Id","type":"string"},"deployment":{"anyOf":[{"maxLength":300,"type":"string"},{"type":"null"}],"default":null,"description":"Only limits of this deployment resource name.","title":"Deployment"}},"required":["account_id"],"title":"get_serverless_rate_limitsArguments","type":"object"}}}},"responses":{"200":{"description":"Tool result. `ok: true` on success; `ok: false` with a structured `error` (provider_unavailable, upstream_error, bad_input) when the tool could not answer.","content":{"application/json":{"schema":{"type":"object","additionalProperties":true}}}},"422":{"description":"Arguments failed validation","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}},"429":{"description":"Rate limit exceeded (see Retry-After)","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Error"}}}}},"x-read-only":true}}}}