# Replace llm pricing rules URL: https://docs.hanzo.ai/docs/openapi/o11y/createorupdatellmpricingrules > Writes the pricing-rule batch — the single write endpoint used by both the user and the Zeus sync job. `PUT /v1/o11y/llm_pricing_rules` > [O11y →](https://docs.hanzo.ai/docs/openapi/o11y) · [All API references →](https://docs.hanzo.ai/docs/openapi) · [Get started →](https://docs.hanzo.ai/docs/guides) | | | | ------------- | ------------------------------------------------ | | **Address** | `https://api.hanzo.ai/v1/o11y/llm_pricing_rules` | | **Method** | `PUT` | | **Operation** | `CreateOrUpdateLLMPricingRules` | | **Auth** | `Authorization: Bearer $HANZO_API_KEY` | Writes the pricing-rule batch — the single write endpoint used by both the user and the Zeus sync job. Per-rule match is by id, then sourceId, then insert; an override row is fully preserved when the request omits isOverride, only its synced\_at stamped. Callers need the admin role; the runtime's own gate enforces it. ## Request 16 fields, body `application/json` (required). | Field | In | Type | Required | Description | | ----------------------------- | ---- | ----------------------------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------- | | `rules` | body | o11y.O11yLLMUpdatablePricingRule\[] | — | Rules are the rules to create or update, matched per rule. | | `rules[].enabled` | body | boolean | — | Enabled turns the rule on. | | `rules[].id` | body | string | — | ID matches an existing rule by its id. | | `rules[].isOverride` | body | boolean | — | IsOverride pins the rule so the sync job skips it. | | `rules[].modelName` | body | string | — | Model is the model the rule prices. | | `rules[].modelPattern` | body | string\[] | — | ModelPattern are the model-name globs the rule matches. | | `rules[].pricing` | body | o11y.O11yLLMRulePricing | — | | | `rules[].pricing.cache` | body | o11y.O11yLLMPricingCacheCosts | — | | | `rules[].pricing.cache.mode` | body | string | — | Mode is how cached tokens are counted — subtract (inside input\_tokens, OpenAI-style), additive (reported separately, Anthropic-style) or unknown. | | `rules[].pricing.cache.read` | body | number (double) | — | Read is the cost per unit of cache-read tokens. | | `rules[].pricing.cache.write` | body | number (double) | — | Write is the cost per unit of cache-write tokens. | | `rules[].pricing.input` | body | number (double) | — | Input is the cost per unit of input tokens. | | `rules[].pricing.output` | body | number (double) | — | Output is the cost per unit of output tokens. | | `rules[].provider` | body | string | — | Provider is the model's provider. | | `rules[].sourceId` | body | string | — | SourceID matches an existing rule by its upstream source id. | | `rules[].unit` | body | string | — | Unit is the pricing unit, e.g. per\_million\_tokens. | ## Response | Status | Body | Meaning | | --------- | --------------- | ----------------- | | `202` | Approval | held for approval | | `204` | — | no content | | `default` | problem-details | refused | `202` body — 3 fields. | Field | In | Type | Always | Description | | -------- | ---- | ------ | ------ | ----------- | | `clause` | body | string | — | | | `reason` | body | string | — | | | `status` | body | string | — | | Failure carries the platform error shape — see [Errors](https://docs.hanzo.ai/docs/errors). ## Examples **CLI** ```bash hanzo o11y llm_pricing_rules replace ``` **SDK** **.ts** ```ts import { Configuration, O11yApi } from 'hanzoai'; const api = new O11yApi(new Configuration({ accessToken: process.env.HANZO_API_KEY })); const { data } = await api.createOrUpdateLLMPricingRules({ rules: [{"enabled":false,"id":"","isOverride":false,"modelName":""}] }); ``` **.py** ```python from hanzoai.cloud import ApiClient, Configuration from hanzoai.cloud.api import O11yApi client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"])) result = O11yApi(client).create_or_update_llm_pricing_rules(rules=[{"enabled":false,"id":"","isOverride":false,"modelName":""}]) ``` **.go** ```go cfg := hanzoai.NewConfiguration() cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY")) client := hanzoai.NewAPIClient(cfg) resp, _, err := client.O11yAPI.CreateOrUpdateLLMPricingRules(context.Background()).Execute() if err != nil { return err } ``` **.rs** ```rust use hanzo_client::apis::{configuration::Configuration, o11y_api}; let mut cfg = Configuration::new(); cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok(); let result = o11y_api::create_or_update_llm_pricing_rules(&cfg, Default::default()).await?; ``` **.java** ```java import ai.hanzo.cloud.ApiClient; import ai.hanzo.cloud.api.O11yApi; ApiClient client = new ApiClient(); client.setBearerToken(System.getenv("HANZO_API_KEY")); var result = new O11yApi(client).createOrUpdateLLMPricingRules(); ``` **HTTP** ```bash curl -X PUT https://api.hanzo.ai/v1/o11y/llm_pricing_rules \ -H "Authorization: Bearer $HANZO_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "rules": [ { "enabled": false, "id": "", "isOverride": false, "modelName": "" } ] }' ``` **MCP** Tool `o11y`, op `CreateOrUpdateLLMPricingRules` — POST the JSON-RPC envelope to `https://api.hanzo.ai/v1/mcp`. ```bash curl -X POST https://api.hanzo.ai/v1/mcp \ -H "Authorization: Bearer $HANZO_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "o11y", "arguments": { "op": "CreateOrUpdateLLMPricingRules", "input": { "rules": [ { "enabled": false, "id": "", "isOverride": false, "modelName": "" } ] } } } }' ``` --- [O11y API](https://docs.hanzo.ai/docs/openapi/o11y) · [All Hanzo APIs](https://docs.hanzo.ai/docs/openapi) · [Interactive reference](https://docs.hanzo.ai/docs/openapi/reference)