> ## Documentation Index > Fetch the complete documentation index at: https://docs.getlago.com/llms.txt > Use this file to discover all available pages before exploring further. # AWS Bedrock > Bill AWS Bedrock token usage with the Lago Agent SDK. Converse and InvokeModel, streaming included, across seven response-shape families. Bedrock is the widest surface the SDK covers, because Bedrock is really two APIs over dozens of model families with different response shapes. The SDK normalizes all of them. Instrumented calls: | Method | Tagged as | | ----------------------------------- | ------------------ | | `converse` | `bedrock_converse` | | `converse_stream` | `bedrock_converse` | | `invoke_model` | `bedrock_invoke` | | `invoke_model_with_response_stream` | `bedrock_invoke` | In JavaScript the SDK wraps `client.send(command)` and dispatches on the command constructor: `ConverseCommand`, `ConverseStreamCommand`, `InvokeModelCommand`, `InvokeModelWithResponseStreamCommand`. ## Install ```bash pip theme={"dark"} pip install 'lago-agent-sdk[bedrock]' ``` ```bash npm theme={"dark"} npm install lago-agent-sdk @aws-sdk/client-bedrock-runtime ``` ## Wrap and call ```python Python theme={"dark"} import boto3 from lago_agent_sdk import LagoSDK sdk = LagoSDK( api_key="", default_subscription_id="sub_acme", ) client = sdk.wrap(boto3.client("bedrock-runtime", region_name="eu-west-1")) resp = client.converse( modelId="eu.amazon.nova-lite-v1:0", messages=[{"role": "user", "content": [{"text": "Hello"}]}], ) sdk.flush() ``` ```typescript TypeScript theme={"dark"} import { BedrockRuntimeClient, ConverseCommand } from "@aws-sdk/client-bedrock-runtime"; import { LagoSDK } from "lago-agent-sdk"; const sdk = new LagoSDK({ apiKey: process.env.LAGO_API_KEY!, defaultSubscriptionId: "sub_acme", }); const client = sdk.wrap(new BedrockRuntimeClient({ region: "eu-west-1" })); await client.send(new ConverseCommand({ modelId: "eu.amazon.nova-lite-v1:0", messages: [{ role: "user", content: [{ text: "Hello" }] }], })); await sdk.flush(); ``` The wrapper is installed on the boto3 client object itself, so any code holding that client is instrumented. `wrap()` is idempotent. ## InvokeModel `invoke_model` needs special handling and gets it. AWS returns the response body as a **single-use stream**. Reading it to extract usage would leave your code with an exhausted body. The SDK consumes the body once, parses the JSON, extracts usage, then re-wraps the bytes as a fresh `StreamingBody`. Your code reads `response["body"].read()` exactly as before. ```python Python theme={"dark"} import json resp = client.invoke_model( modelId="eu.anthropic.claude-haiku-4-5-v1:0", body=json.dumps({ "anthropic_version": "bedrock-2023-05-31", "max_tokens": 200, "messages": [{"role": "user", "content": "Hello"}], }), ) payload = json.loads(resp["body"].read()) # works unchanged ``` ```typescript TypeScript theme={"dark"} import { InvokeModelCommand } from "@aws-sdk/client-bedrock-runtime"; const out = await client.send(new InvokeModelCommand({ modelId: "eu.anthropic.claude-haiku-4-5-v1:0", body: JSON.stringify({ anthropic_version: "bedrock-2023-05-31", max_tokens: 200, messages: [{ role: "user", content: "Hello" }], }), })); const payload = JSON.parse(new TextDecoder().decode(out.body)); ``` ### Response-shape families `InvokeModel` has no single usage schema. Each model family reports differently. The SDK dispatches on `modelId` across seven families, verified against 39 models in `eu-west-1`: | Family | Models | | ---------------------------- | --------------------------------------------------------------------------------------------------------------- | | `openai_compat_basic` | Gemma, Qwen, gpt-oss-120b/20b, Voxtral, MiniMax M2.5, Magistral, Devstral, Ministral, NVIDIA Nemotron Nano, GLM | | `openai_compat_with_details` | gpt-oss Safeguard 120B/20B, MiniMax M2, MiniMax M2.1 | | `anthropic` | Claude Sonnet 4.5/4.6, Haiku 4.5, Opus 4.5/4.6 | | `opus_4_7` | Claude Opus 4.7 (adds `service_tier`, captured into `extras`) | | `nova` | Amazon Nova Pro / Lite / Micro / 2-Lite | | `pixtral` | Mistral Pixtral Large | | `mistral_legacy` | Mistral 7B, Mixtral 8x7B, Mistral Large 24.02 | `Converse` is simpler: three shape families, all handled by one adapter. Standard (`inputTokens` / `outputTokens`, 33 models), cache-read-only (Claude Opus 4.7), and full-cache (Claude Sonnet 4.5/4.6, Haiku 4.5, Opus 4.5/4.6). ## Streaming Both streaming methods are instrumented. Usage arrives in the terminal `metadata` chunk of the event stream, and the SDK emits once the stream is exhausted. ```python Python theme={"dark"} resp = client.converse_stream( modelId="eu.amazon.nova-lite-v1:0", messages=[{"role": "user", "content": [{"text": "Hello"}]}], ) for event in resp["stream"]: ... ``` ```typescript TypeScript theme={"dark"} import { ConverseStreamCommand } from "@aws-sdk/client-bedrock-runtime"; const out = await client.send(new ConverseStreamCommand({ modelId: "eu.amazon.nova-lite-v1:0", messages: [{ role: "user", content: [{ text: "Hello" }] }], })); for await (const event of out.stream!) { // ... } ``` ## Per-call override Bedrock's request shape is validated strictly by AWS, so the override rides on the command object rather than inside the request body. ```python Python theme={"dark"} client.converse( modelId="eu.amazon.nova-lite-v1:0", messages=[{"role": "user", "content": [{"text": "Hello"}]}], extra_lago={ "subscription": "sub_acme", "dimensions": {"feature": "summarize"}, "mode": "price", # optional "markup": 1.5, # optional }, ) ``` ```typescript TypeScript theme={"dark"} const cmd = new ConverseCommand({ modelId: "eu.amazon.nova-lite-v1:0", messages: [{ role: "user", content: [{ text: "Hello" }] }], }); (cmd as any).__lago = { subscription: "sub_acme", dimensions: { feature: "summarize" }, mode: "price", // optional markup: 1.5, // optional }; await client.send(cmd); ``` ## What gets captured | Canonical field | Converse | InvokeModel | | ---------------- | ------------------------------------------------ | ---------------------- | | `input` | `usage.inputTokens` | family-dependent | | `output` | `usage.outputTokens` | family-dependent | | `cache_read` | `usage.cacheReadInputTokens` (Anthropic models) | ✓ (Anthropic families) | | `cache_write` | `usage.cacheWriteInputTokens` (Anthropic models) | ✓ (Anthropic families) | | `cache_write_5m` | ✗ | ✓ (Anthropic families) | | `cache_write_1h` | ✗ | ✓ (Anthropic families) | | `reasoning` | folded into `output` | folded into `output` | | `tool_calls` | server-side tools only (`usage.serverToolUsage`) | ✓ (Anthropic families) | On `Converse`, `tool_calls` counts only Bedrock's own server-side tool invocations, which is the one number the API reports. Client-side tool calls you execute yourself are not counted — meter those on your own side if you bill on them. The `provider` property on each event is derived from `modelId`, so a single Bedrock client produces events tagged `anthropic`, `amazon`, `meta`, `mistral`, `cohere`, `openai`, `qwen`, `google`, `minimax`, `nvidia`, or `zai`. That makes `provider` a useful charge filter when you resell several model families through one Bedrock account. Combine the `provider` and `model` properties with [charges with filters](/guide/plans/charges/charges-with-filters) to price Nova and Claude differently off the same billable metric. ## Pricing In price mode, Bedrock is priced from the **AWS Bedrock Price List Bulk API**, parsed per region. Region comes from the model id prefix when present (`eu.`, `us.`), otherwise from `bedrock_default_region` / `bedrockDefaultRegion`, which defaults to `us-east-1`. **Set your default region.** If your model ids carry no region prefix and you leave `bedrock_default_region` at `us-east-1` while calling `eu-west-1`, you will price against the wrong region's rates. ## Known limits **AWS's public bulk price data has a gap.** It lists Titan, Llama, Mistral, Cohere, and older Claude models, but at time of writing not the current Claude 3.5/3.7/4 models. Bedrock calls for models absent from AWS's data fall back to token-count events and fire `on_error` with a `PricingUnavailableError`. Native Anthropic clients are priced through OpenRouter and unaffected. **Legacy Mistral models report no usage at all through `InvokeModel`.** Mistral 7B, Mixtral 8x7B, and Mistral Large 24.02 return no token counts, so the SDK logs a warning and emits nothing — there is nothing to bill on. Use `Converse` with those models, or a current model, if you need to meter them. **Only `Converse` and `InvokeModel` are instrumented**, in both their streaming and non-streaming forms. Two other billable Bedrock Runtime operations pass through unmetered: `start_async_invoke` (asynchronous inference) and `apply_guardrail`. If you use either, build a `CanonicalUsage` yourself and pass it to [`sdk.emit()`](/guide/ai-agents/agent-sdk/reference#billing-a-provider-the-sdk-does-not-wrap). ## Next steps Every config knob, in both SDKs. Price each model family off one billable metric.