> The full index of these docs is at [llms.txt](https://u22a8.ai/llms.txt). # Anthropic Messages Call A8 through the Anthropic Messages API, the fields it reads, minimum accuracy and where the verdict, an abstention and precedents land. A8 answers the Anthropic Messages API at `POST https://api.u22a8.ai/eval/v1/messages`. Give an Anthropic SDK the base URL `https://api.u22a8.ai/eval`, and it adds `/v1/messages` itself. A8 takes the key as `x-api-key`, the way the Anthropic SDKs send it, or as `Authorization: Bearer`. ## 1 Request A8 reads the fields below. `system` states the criterion, the user messages carry the subject, and `output_config.format` gives the verdict its shape. A8 answers the conversation’s latest user message: | Field | Type | How A8 reads it | Default | | ---------------------- | --------------- | ----------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------- | | `model` | string | `a8` for your organization’s latest version, a pinned identifier, or `a8-1-1@reference`. Its tag sets the minimum accuracy: `a8:95` | Required | | `system` | string or array | The criterion | Required, or carried by the schema | | `messages` | array | The conversation: user messages carry the subject and its follow-ups, and assistant messages are A8’s earlier responses | Required | | `output_config.format` | object | The verdict’s shape, as a `json_schema` | A label or a number | | `tools`, `tool_choice` | array, object | A forced tool: its `input_schema` is the verdict’s shape | None | | `thinking` | object | Reasoning: `{"type": "disabled"}` reads the layout as written, and `adaptive` or `enabled` read the request however it is laid out | Reasoning on | | `output_config.effort` | string | Accepted from `low` to `max`; the minimum accuracy stays as the tag sets it | None | | `stream` | boolean | Streams the verdict as Messages events | `false` | | `max_tokens` | integer | The SDKs require it; A8 reads any value, or the field left out | Optional | *Table 1.* The fields A8 reads. Every other field is accepted and ignored, `temperature` and `top_p` among them. The subject can carry a context, a reference or a question, and one schema can carry several criteria. See [API overview](https://u22a8.ai/docs/api-overview.md). With reasoning on, a prompt written for another judge works too, and is answered in the format it asks for. See [Chat Completions](https://u22a8.ai/docs/a8-chat-completions.md#prompts-written-for-other-judges). To follow up on a verdict, send `messages` again with A8’s response as an assistant message and a new user message after it. See [Continue a conversation](https://u22a8.ai/docs/api-overview.md#continue-a-conversation). ## 2 What is refused Each of these returns `400` in Anthropic’s error envelope, with a message that names the field and the value that passes: | Request | Status | Send | | ---------------------------------------------------------------------------- | ------ | ------------------------------------------------------------------ | | `min_accuracy` in the body | `400` | The minimum accuracy as the model’s tag, as `a8:95` | | A `model` tag outside `0` to `99` | `400` | A whole number from `0` to `99` | | `expected` in the body | `400` | The answer as a teach, over [MCP](https://u22a8.ai/docs/a8-mcp.md) | | An `output_config.effort` outside `low`, `medium`, `high`, `xhigh` and `max` | `400` | One of those values | | A `thinking.type` outside `adaptive`, `enabled` and `disabled` | `400` | One of those values | | A `tool_choice` naming a tool outside `tools` | `400` | The name of a tool in `tools` | *Table 2.* Refused fields and values. Error bodies are on [Errors](https://u22a8.ai/docs/errors.md). ## 3 Minimum accuracy The minimum accuracy is the accuracy A8 promises on the verdicts it returns. At 95, at least 95% of answered verdicts are correct. The model’s tag sets it: `a8:95` asks for 95, and a pinned identifier carries it too, as `a8-1-1:95@20260715t140322z`. - **The tag is a whole number from `0` to `99`.** A higher level answers less often and is right more often. - **By default, the minimum accuracy is 90.** - **The response’s `model` names the level that answered,** so a stored response says which promise it was answered under. The tag alone sets the minimum accuracy. A threshold written in the system prompt counts as part of the criterion. The identifier’s parts are on [Model identifiers](https://u22a8.ai/docs/a8-model-identifiers.md), and what the minimum accuracy promises is on [Accuracy and abstention](https://u22a8.ai/docs/a8-abstention.md). ## 4 Reasoning `thinking` turns A8’s reasoning on and off. Reasoning is on unless the request sends `{"type": "disabled"}`. - **Reasoning on** reads the request however it is laid out: a framework’s grader template, a follow-up, or a request in plain words. When the layout already says what each part is, A8 answers as fast as with reasoning off. - **Reasoning off** (`thinking: {"type": "disabled"}`) reads the layout as written, which is faster: | Part | Where it goes | | ---------------------------- | ----------------------------------------------------------------------------- | | Criterion | `system`, as written | | Subject | The latest user message, whole | | Reference, context, question | Keys of a subject object: a user message holding a JSON object with `output` | | Verdict shape | `output_config.format`, or a forced tool. Without either, a label or a number | | Labels | The schema’s `enum` | | Precedents | A `precedents` property reserved in the schema | *Table 3.* The layout with reasoning off. A8 judges the latest user message alone, and earlier turns are history. A framework’s grader template sent with reasoning off is read as written too: `system`, when it has one, is the criterion, and the template in the user message is the subject, so an untaught criterion abstains. A template sent as one user message alone abstains with kind `no_question`, since the criterion travels in `system`. The reading is reported as reasoning tokens, in `usage.output_tokens`. A repeat of the request reads from the cache and reports the same count in `usage.cache_read_input_tokens`, beside `usage.input_tokens`, as this API reports a prompt it had cached. A layout read as written reports `0`. ## 5 Response A8 answers with a standard `message`. The verdict is the text block. ```jsonc { "id": "eval-9f2c1d84ab30e5f7", "type": "message", "role": "assistant", "model": "a8-1-1:95@20260715t140322z", // the version and level that answered "content": [ {"type": "text", "text": "{\"queue\": \"shipping\"}"} // the verdict ], "stop_reason": "end_turn", "usage": { "input_tokens": 812, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0, "output_tokens": 0 }, "system_fingerprint": "fit-1a2b3c4d5e6f7890.9e2a1b3c", "min_accuracy": 95 // the level this verdict is promised at } ``` - **`model`** names the exact version that answered, with the minimum accuracy in its tag. See [Horizons](https://u22a8.ai/docs/a8-horizons.md). - **`usage.output_tokens`** holds reasoning tokens alone, since the verdict is scored. They are `0` here, as the layout is read as written. - **`system_fingerprint`**, `min_accuracy`, `abstention`, `interval` and `precedents` are A8’s fields beside the standard ones. Each is defined on [API overview](https://u22a8.ai/docs/api-overview.md). A forced tool is answered as a `tool_use` block holding the verdict as its `input`, with `stop_reason` set to `tool_use`. The Anthropic SDKs keep A8’s fields on the message object: **Python** ```python message.model_extra.get("min_accuracy") # 95, or None on an abstention message.model_extra.get("abstention") # set on an abstention ``` **TypeScript** ```typescript type A8Fields = { min_accuracy?: number; abstention?: { kind: string } }; const { min_accuracy, abstention } = message as typeof message & A8Fields; ``` ## 6 An abstention An abstention succeeds with `200`. `stop_reason` is `refusal`, `content` is an empty list, and `stop_details.explanation` holds the abstention in words. The top-level `abstention` says which check the evidence failed, and at what level the same request is answered: ```json { "id": "eval-4c1e0b9a2f7d3e65", "type": "message", "role": "assistant", "model": "a8-1-1:95@20260715t140322z", "content": [], "stop_reason": "refusal", "stop_details": { "type": "refusal", "category": null, "explanation": "Too close to call at min_accuracy 95; answered at 80." }, "usage": { "input_tokens": 812, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0, "output_tokens": 0 }, "abstention": { "kind": "too_close", "asked": 95, "answerable_at": 80, "earned": 97, "missing": null } } ``` Recorded from `a8-1-1@20260715t140322z` on 2026-10-22. Branch on `stop_reason`, then on `abstention.kind`. The kinds are on [Accuracy and abstention](https://u22a8.ai/docs/a8-abstention.md). ## 7 A filtered request With reasoning on, A8 filters some requests whose text is harmful, such as hate speech, violence or self-harm. A filtered request gets an outcome of its own, apart from verdicts and abstentions. It succeeds with `200` and `stop_reason: "refusal"`, as this API returns a request its classifiers decline, and `stop_details.category` is `"general_harms"`, this API’s category for a policy outside its named ones. An abstention’s category is `null`, so the category tells the two apart: ```json { "type": "message", "role": "assistant", "model": "a8-1-1:95@20260715t140322z", "content": [], "stop_reason": "refusal", "stop_details": { "type": "refusal", "category": "general_harms", "explanation": "This request was filtered for harmful content." }, "usage": { "input_tokens": 0, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0, "output_tokens": 0 } } ``` A filtered request is free, and is filtered the same way every time it is sent. ## 8 Precedents and recall Ask for [precedents](https://u22a8.ai/docs/a8-precedents.md) in the prompt (“quote precedents”), and the response carries a top-level `precedents` object. Reserve a `precedents` property in the schema, and they arrive inside the verdict. Either way the key needs the `models:explain` permission. See [API keys](https://u22a8.ai/docs/api-keys.md). A question about what you taught, such as “What have I taught you about refunds?”, is answered with recall. The text block is the `precedents` object as JSON, holding your taught examples, and the same object sits at the top level. ## 9 Streaming With `stream: true`, the answer arrives as Messages events. The verdict comes whole, in one `content_block_delta`, and `message_delta` carries the stop reason, `stop_details` and A8’s fields. ## 10 Example A ticket router at a minimum accuracy of 95: **curl** ```bash curl https://api.u22a8.ai/eval/v1/messages \ -H "x-api-key: $U22A8_API_KEY" \ -H "anthropic-version: 2023-06-01" \ -H "Content-Type: application/json" \ -d '{ "model": "a8:95", "max_tokens": 1024, "system": "Which queue does the ticket belong in?", "messages": [ {"role": "user", "content": "It arrived crushed. I want a refund."} ], "output_config": { "format": { "type": "json_schema", "schema": { "type": "object", "properties": { "queue": {"enum": ["billing", "shipping", "account"]} } } } } }' ``` **Python** ```python import json import os from anthropic import Anthropic client = Anthropic( base_url="https://api.u22a8.ai/eval", api_key=os.environ["U22A8_API_KEY"], ) route = { "type": "json_schema", "schema": { "type": "object", "properties": {"queue": {"enum": ["billing", "shipping", "account"]}}, }, } message = client.messages.create( model="a8:95", # minimum accuracy 95 max_tokens=1024, # the SDK requires it system="Which queue does the ticket belong in?", messages=[ {"role": "user", "content": "It arrived crushed. I want a refund."}, ], output_config={"format": route}, ) print(message.stop_reason) # "end_turn", or "refusal" on an abstention print(json.loads(message.content[0].text)) # {'queue': 'shipping'} print(message.model) # the version that answered ``` **TypeScript** ```typescript import Anthropic from "@anthropic-ai/sdk"; const client = new Anthropic({ baseURL: "https://api.u22a8.ai/eval", apiKey: process.env.U22A8_API_KEY, }); const message = await client.messages.create({ model: "a8:95", // minimum accuracy 95 max_tokens: 1024, // the SDK requires it system: "Which queue does the ticket belong in?", messages: [{ role: "user", content: "It arrived crushed. I want a refund." }], output_config: { format: { type: "json_schema", schema: { type: "object", properties: { queue: { enum: ["billing", "shipping", "account"] } }, }, }, }, }); const block = message.content[0]; if (block?.type === "text") console.log(JSON.parse(block.text)); console.log(message.model); // the version that answered ``` ```json { "id": "eval-9f2c1d84ab30e5f7", "type": "message", "role": "assistant", "model": "a8-1-1:95@20260715t140322z", "content": [{"type": "text", "text": "{\"queue\": \"shipping\"}"}], "stop_reason": "end_turn", "usage": { "input_tokens": 812, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0, "output_tokens": 0 }, "system_fingerprint": "fit-1a2b3c4d5e6f7890.9e2a1b3c", "min_accuracy": 95 } ``` Recorded from `a8-1-1@20260715t140322z` on 2026-10-22. ## Next steps - [Accuracy and abstention](https://u22a8.ai/docs/a8-abstention.md): How a request sets the minimum accuracy a verdict must meet, what that level promises and the five kinds of abstention. - [API overview](https://u22a8.ai/docs/api-overview.md): What every request to A8 shares, from the base URL and authentication to the request parts and the response fields. - [Errors](https://u22a8.ai/docs/errors.md): Every status A8 returns for a failed request, with its body, its cause and its fix, and how each SDK raises it.