Skip to content

Commit a8f5f22

Browse files
ericc-chericc-ch
committed
feat: Add Anthropic API documentation and OpenAI mapping
1 parent 3aeaa8f commit a8f5f22

7 files changed

Lines changed: 806 additions & 6 deletions

File tree

‎docs/anthropic.md‎

Lines changed: 148 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,148 @@
1+
# Claude API Reference
2+
3+
This document provides a condensed overview of the Anthropic Claude API, covering messages, token counting, and model management.
4+
5+
---
6+
7+
## Messages API
8+
9+
The Messages API is the primary way to interact with Claude for multi-turn conversations and single queries.
10+
11+
### Create a Message
12+
13+
Creates a model response for the given conversation.
14+
15+
**Endpoint:** `POST /v1/messages`
16+
17+
#### Request Body
18+
19+
The request body is a JSON object.
20+
21+
| Parameter | Type | Required | Description |
22+
| :--------------- | :-------------- | :------- | :-------------------------------------------------------------------------------------------------------------------------------------------------- |
23+
| `model` | string | Yes | The model that will complete your prompt. Example: `claude-3-7-sonnet-20250219`. |
24+
| `messages` | array | Yes | A list of input messages comprising the conversation so far. See [The Message Object](https://www.google.com/search?q=%23the-message-object) below. |
25+
| `max_tokens` | integer | Yes | The maximum number of tokens to generate. Different models have different maximums. |
26+
| `system` | string or array | No | A system prompt to provide context and instructions to Claude, such as specifying a role or goal. |
27+
| `metadata` | object | No | An object for metadata, such as a `user_id`, to help detect abuse. Do not include any personally identifying information. |
28+
| `stop_sequences` | array | No | Custom text sequences that will cause the model to stop generating. |
29+
| `stream` | boolean | No | If set, the response will be incrementally streamed using server-sent events. Defaults to `false`. |
30+
| `temperature` | number | No | The amount of randomness injected into the response, ranging from `0.0` to `1.0`. Defaults to `1.0`. |
31+
| `top_p` | number | No | Use nucleus sampling. The model considers tokens with `top_p` probability mass. Should alter `temperature` or `top_p`, but not both. |
32+
| `top_k` | integer | No | Only sample from the top K options for each subsequent token. Recommended for advanced use cases. |
33+
| `tools` | array | No | A list of tools the model may use. See [The Tool Object](https://www.google.com/search?q=%23the-tool-object) below. |
34+
| `tool_choice` | object | No | Controls how the model should use the provided tools. Can be `auto`, `any`, `tool`, or `none`. |
35+
36+
#### The Message Object
37+
38+
The `messages` array consists of message objects, where each object has a `role` and `content`. Models are trained on alternating `user` and `assistant` turns.
39+
40+
| Parameter | Type | Required | Description |
41+
| :-------- | :-------------- | :------- | :---------------------------------------------------------------------------------------------------------------------------------- |
42+
| `role` | string | Yes | The role of the message author. Must be either `user` or `assistant`. |
43+
| `content` | string or array | Yes | The content of the message. This can be a simple string or an array of content blocks for multimodal input (e.g., text and images). |
44+
45+
**Content Blocks:** For multimodal input, the `content` array can contain different types of blocks.
46+
47+
- **`text`**: A block with a `type` of "text" and a `text` field containing the string.
48+
- **`image`**: A block with a `type` of "image" and a `source` object. The source must specify its `type` (e.g., "base64"), `media_type` (e.g., "image/jpeg"), and `data`.
49+
- **`tool_result`**: A block used to return the output of a tool back to the model. It includes the `tool_use_id`, `content`, and an optional `is_error` flag.
50+
51+
#### The Tool Object
52+
53+
The `tools` array allows you to define client-side tools the model can call.
54+
55+
| Parameter | Type | Required | Description |
56+
| :------------- | :----- | :------- | :-------------------------------------------------------------------------------------------------------- |
57+
| `name` | string | Yes | The name of the tool, matching `^[a-zA-Z0-9_-]{1,64}$`. |
58+
| `description` | string | No | A detailed description of what the tool does, which helps the model decide when to use it. |
59+
| `input_schema` | object | Yes | A [JSON Schema](https://json-schema.org/draft/2020-12) object describing the parameters the tool accepts. |
60+
61+
#### Response (200 OK)
62+
63+
A successful non-streaming request returns a `Message` object.
64+
65+
| Parameter | Type | Description |
66+
| :-------------- | :----- | :------------------------------------------------------------------------------------------------------------------------ |
67+
| `id` | string | A unique identifier for the message object. |
68+
| `type` | string | The object type, which is always `message`. |
69+
| `role` | string | The role of the author, which is always `assistant`. |
70+
| `content` | array | An array of content blocks generated by the model (e.g., `text` or `tool_use`). |
71+
| `model` | string | The model that handled the request. |
72+
| `stop_reason` | string | The reason the model stopped generating tokens. Can be `end_turn`, `max_tokens`, `stop_sequence`, or `tool_use`. |
73+
| `stop_sequence` | string | If the model was stopped by a stop sequence, this field will contain which sequence was generated. Can be null. |
74+
| `usage` | object | An object containing token usage statistics. See [The Usage Object](https://www.google.com/search?q=%23the-usage-object). |
75+
76+
#### The Usage Object
77+
78+
The `usage` object details billing and rate-limit token counts.
79+
80+
| Parameter | Type | Description |
81+
| :-------------- | :------ | :------------------------------------- |
82+
| `input_tokens` | integer | The number of input tokens used. |
83+
| `output_tokens` | integer | The number of output tokens generated. |
84+
85+
### Count Message Tokens
86+
87+
Calculates the number of tokens for a given set of messages without executing the model.
88+
89+
**Endpoint:** `POST /v1/messages/count_tokens`
90+
91+
#### Request Body
92+
93+
The request accepts a subset of the "Create a Message" parameters.
94+
95+
| Parameter | Type | Required | Description |
96+
| :--------- | :-------------- | :------- | :----------------------------------- |
97+
| `model` | string | Yes | The model that would be used. |
98+
| `messages` | array | Yes | A list of input messages. |
99+
| `system` | string or array | No | A system prompt. |
100+
| `tools` | array | No | A list of tools the model could use. |
101+
102+
#### Response (200 OK)
103+
104+
A successful request returns a JSON object.
105+
106+
| Parameter | Type | Description |
107+
| :------------- | :------ | :------------------------------------------------------------------------------ |
108+
| `input_tokens` | integer | The total number of tokens counted from the messages, system prompt, and tools. |
109+
110+
---
111+
112+
## Models API
113+
114+
The Models API allows you to list and retrieve information about available models.
115+
116+
### List Models
117+
118+
Lists the currently available models, with the most recent models appearing first.
119+
120+
**Endpoint:** `GET /v1/models`
121+
122+
#### Response (200 OK)
123+
124+
A successful request returns a list of model objects.
125+
126+
| Parameter | Type | Description |
127+
| :--------- | :------ | :------------------------------------------------------------------------------ |
128+
| `data` | array | A list of [Model Objects](https://www.google.com/search?q=%23the-model-object). |
129+
| `has_more` | boolean | Indicates if more results are available for pagination. |
130+
131+
### Get a Model
132+
133+
Retrieves a specific model instance by its ID or alias.
134+
135+
**Endpoint:** `GET /v1/models/{model_id}`
136+
137+
#### Response (200 OK)
138+
139+
A successful request returns a single [Model Object](https://www.google.com/search?q=%23the-model-object).
140+
141+
#### The Model Object
142+
143+
| Parameter | Type | Description |
144+
| :------------- | :----- | :------------------------------------------------------------------ |
145+
| `id` | string | The unique model identifier. Example: `claude-3-7-sonnet-20250219`. |
146+
| `type` | string | The object type, which is always `model`. |
147+
| `display_name` | string | A human-readable name for the model. Example: `Claude 3.7 Sonnet`. |
148+
| `created_at` | string | An RFC 3339 datetime string of when the model was released. |

0 commit comments

Comments
 (0)