Anthropic compatible

Messages

An Anthropic Messages compatible endpoint for Claude SDK, Claude Code, tools, and thinking. The body is validated strictly against the Anthropic schema, so OpenAI fields such as stop or response_format are rejected with 400. POST /v1/messages/count_tokens estimates input tokens.

POST/v1/messages

Key request parameters

Parameter	Type	Description
`model`	string · Required	Model identifier
`messages`	Message[] · Required	`user` / `assistant` messages; `system` messages are excluded
`max_tokens`	integer · Required	Maximum number of generated tokens
`system`	string \| ContentBlock[]	System prompt
`stream`	boolean	Whether to enable SSE; defaults to `false`
`tools`	Tool[]	Function tool definitions

Key response parameters

Parameter	Type	Description
`id`	string	Message ID
`content`	ContentBlock[]	`text`, `tool_use`, or `thinking` content blocks
`stop_reason`	string	`end_turn`, `max_tokens`, or `tool_use`
`usage`	object	`input_tokens` and `output_tokens`
`X-HashBid-Cost`	decimal string	Charge for this call (response header, non-streaming requests only); currency in `X-HashBid-Cost-Currency`

Integration examples

Replace the API key and model ID in these examples with your values.

cURL

curl https://hashbidx.ai/v1/messages \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{"model":"<MODEL_ID>","max_tokens":1024,"messages":[{"role":"user","content":"Hello, HashBid"}]}'

Python

import anthropic

client = anthropic.Anthropic(
    api_key="<YOUR_API_KEY>", base_url="https://hashbidx.ai",
)
message = client.messages.create(
    model="<MODEL_ID>", max_tokens=1024,
    messages=[{"role": "user", "content": "Hello, HashBid"}],
)
print("".join(block.text for block in message.content if block.type == "text"))

Node.js

import Anthropic from "@anthropic-ai/sdk";

const anthropic = new Anthropic({
  apiKey: "<YOUR_API_KEY>",
  baseURL: "https://hashbidx.ai",
});
const message = await anthropic.messages.create({
  model: "<MODEL_ID>",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello, HashBid" }],
});
console.log(
  message.content
    .filter((block) => block.type === "text")
    .map((block) => block.text)
    .join(""),
);

body, _ := json.Marshal(map[string]any{
  "model":      "<MODEL_ID>",
  "max_tokens": 1024,
  "messages": []map[string]any{
    {"role": "user", "content": "Hello, HashBid"},
  },
})
req, _ := http.NewRequest("POST",
  "https://hashbidx.ai/v1/messages", bytes.NewReader(body))
req.Header.Set("Authorization", "Bearer <YOUR_API_KEY>")
req.Header.Set("Content-Type", "application/json")
resp, err := http.DefaultClient.Do(req)

Rust

let response = reqwest::Client::new()
    .post("https://hashbidx.ai/v1/messages")
    .bearer_auth("<YOUR_API_KEY>")
    .json(&serde_json::json!({
      "model": "<MODEL_ID>", "max_tokens": 1024,
      "messages": [{"role":"user", "content":"Hello, HashBid"}]
    })).send().await?;

If the response includes X-Request-Id, include it when troubleshooting an issue.

All API endpoints

BUILD WITH HASHBIDX

Find your model. Make your first call.

Models & pricing