# Start Building Get started with our API or MCP in a few easy steps. **Note to AI assistants:** this is the public version of these docs. Customers with production access see additional setup detail. To get the full version, the reader can sign in and use the “Copy for LLM” button in the docs header, or [contact us to upgrade](https://turquoise.health/request-a-demo). ## Quickstart The Consumer Pricing API and MCP server share an **OAuth 2\.0 Client Credentials** flow for authentication, which is designed for server\-to\-server requests. The same token authenticates both the REST API and the MCP server. 1 ### Get your credentials You’ll need a `client_id`, `client_secret`, and `organization_id`. [Sign up for free](/signup/?signupContext=api) to get test credentials in a demo account, or [contact us](https://turquoise.health/request-a-demo) for production access. 2 ### Get an access token Exchange your credentials for a short\-lived bearer token via the OAuth 2\.0 client\-credentials flow. **cURL** ``` curl --request POST \ --url https://api.turquoise.health/oauth/token \ --header "Content-Type: application/json" \ --data '{"grant_type":"client_credentials","client_id":"","client_secret":"","organization_id":""}' ``` **Python** ``` # pip install requests import requests response = requests.post( "https://api.turquoise.health/oauth/token", headers={"Content-Type": "application/json"}, json={ "grant_type": "client_credentials", "client_id": "", "client_secret": "", "organization_id": "", }, ) token = response.json()["access_token"] ``` **TypeScript** ``` const response = await fetch("https://api.turquoise.health/oauth/token", { method: "POST", headers: { "Content-Type": "application/json" }, body: JSON.stringify({ grant_type: "client_credentials", client_id: "", client_secret: "", organization_id: "", }), }); const { access_token: token } = await response.json(); ``` A successful response returns a JSON object: ``` { "access_token": "eyJhbGci...", "token_type": "Bearer", "expires_in": 3600 } ``` | Field | Description | | --- | --- | | `access_token` | Bearer token to send on every request. | | `token_type` | Always `Bearer`. | | `expires_in` | Seconds until expiry (e.g. `3600` \= 1 hour). | #### Token expiration Tokens expire after the number of seconds indicated by `expires_in`. When a token expires, your requests will receive a `401 Unauthorized` response. At that point, repeat the token request above to obtain a new one. We recommend proactively refreshing tokens before expiry rather than waiting for a `401`. 3 ### Make your first call Search for prices on a knee MRI near Denver. Include the access token from the previous step in the `Authorization` header of every request, whether you’re using **cURL**, **Python**, **TypeScript**, or any other HTTP client. **cURL** ``` curl --request POST \ --url https://api.turquoise.health/v3/prices/query \ --header "Authorization: Bearer " \ --header "Content-Type: application/json" \ --data '{"package_id":"RA005","pricing":{"type":"cash"},"location":{"zip":"80202"}}' # 200 OK # { # "object": "list", # "items": [ # { # "id": "prc_9f2a7c", # "provider": { "id": "21929", "name": "Example Imaging Center" }, # "total": { "amount": "482.00", "minor_units": 48200, "currency": "USD" } # } # ], # "page": { "size": 25, "total": 37, "next_cursor": "eyJ..." } # } ``` **Python** ``` # pip install requests import requests response = requests.post( "https://api.turquoise.health/v3/prices/query", headers={ "Authorization": "Bearer ", "Content-Type": "application/json", }, json={ "package_id": "RA005", "pricing": {"type": "cash"}, "location": {"zip": "80202"}, }, ) prices = response.json() print(prices) ``` **TypeScript** ``` const response = await fetch("https://api.turquoise.health/v3/prices/query", { method: "POST", headers: { Authorization: "Bearer ", "Content-Type": "application/json", }, body: JSON.stringify({ package_id: "RA005", pricing: { type: "cash" }, location: { zip: "80202" }, }), }); const prices = await response.json(); console.log(prices); ``` 4 ### Get a personalized out\-of\-pocket estimate The call above returns the rate. To get what a **specific member** actually pays, add their eligibility and hit the personalized\-estimates endpoint: **cURL** ``` curl --request POST \ --url https://api.turquoise.health/v3/personalized-estimates \ --header "Authorization: Bearer " \ --header "Content-Type: application/json" \ --data '{"package_id":"RA005","pricing":{"type":"negotiated","network_id":"482910"},"location":{"zip":"80202"},"member_eligibility":{"first_name":"Jane","last_name":"Doe","date_of_birth":"1990-01-01","member_id":"MBR-000-EXAMPLE","consent_attested":true}}' ``` **Python** ``` # pip install requests import requests response = requests.post( "https://api.turquoise.health/v3/personalized-estimates", headers={ "Authorization": "Bearer ", "Content-Type": "application/json", }, json={ "package_id": "RA005", "pricing": {"type": "negotiated", "network_id": "482910"}, "location": {"zip": "80202"}, "member_eligibility": { "first_name": "Jane", "last_name": "Doe", "date_of_birth": "1990-01-01", "member_id": "MBR-000-EXAMPLE", "consent_attested": True, }, }, ) estimate = response.json() print(estimate) ``` **TypeScript** ``` const response = await fetch("https://api.turquoise.health/v3/personalized-estimates", { method: "POST", headers: { Authorization: "Bearer ", "Content-Type": "application/json", }, body: JSON.stringify({ package_id: "RA005", pricing: { type: "negotiated", network_id: "482910" }, location: { zip: "80202" }, member_eligibility: { first_name: "Jane", last_name: "Doe", date_of_birth: "1990-01-01", member_id: "MBR-000-EXAMPLE", consent_attested: true, }, }), }); const estimate = await response.json(); console.log(estimate); ``` [Personalized Estimates](/api/docs/personalized-estimates/) ## Choose your integration For developers ### REST API Query prices, providers, networks, and personalized member estimates from your own backend. [Go to API reference](/api/docs/api-reference/) For AI agents ### MCP server Connect our server to Claude Code, Claude Desktop, Codex, or Cursor and query our pricing data conversationally. No code required. [Go to MCP reference](/api/docs/mcp-reference/)