> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gptproto.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Claude-Opus-4-Thinking - Web Search
> Claude-Opus-4-Thinking — Web Search. GPTProto API reference.
```bash cURL theme={null}
curl --location --request POST 'https://gptproto.com/v1/messages' \
--header 'Authorization: YOUR_API_KEY' \
--header 'anthropic-version: 2023-06-01' \
--header 'Content-Type: application/json' \
--data-raw '{
"model": "claude-opus-4-thinking",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": "What'\''s the weather in NYC?"
}
],
"tools": [{
"type": "web_search_20250305",
"name": "web_search",
"max_uses": 5
}]
}'
```
```python Python theme={null}
import anthropic
client = anthropic.Anthropic(
api_key="YOUR_API_KEY",
base_url="https://gptproto.com"
)
message = client.messages.create(
model="claude-opus-4-thinking",
max_tokens=1024,
messages=[
{"role": "user", "content": "What's the weather in NYC?"}
],
tools=[{
"type": "web_search_20250305",
"name": "web_search",
"max_uses": 5
}]
)
print(message.content)
```
```javascript JavaScript theme={null}
import Anthropic from '@anthropic-ai/sdk';
const client = new Anthropic({
apiKey: 'YOUR_API_KEY',
baseURL: 'https://gptproto.com'
});
const message = await client.messages.create({
model: 'claude-opus-4-thinking',
max_tokens: 1024,
messages: [
{ role: 'user', content: "What's the weather in NYC?" }
],
tools: [{
type: 'web_search_20250305',
name: 'web_search',
max_uses: 5
}]
});
console.log(message.content);
```
```go Go theme={null}
package main
import (
"bytes"
"encoding/json"
"fmt"
"io/ioutil"
"net/http"
)
func main() {
url := "https://gptproto.com/v1/messages"
payload := []byte(`{
"model": "claude-opus-4-thinking",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": "What's the weather in NYC?"
}
],
"tools": [{
"type": "web_search_20250305",
"name": "web_search",
"max_uses": 5
}]
}`)
req, _ := http.NewRequest("POST", url, bytes.NewBuffer(payload))
req.Header.Set("Authorization", "YOUR_API_KEY")
req.Header.Set("anthropic-version", "2023-06-01")
req.Header.Set("Content-Type", "application/json")
client := &http.Client{}
resp, err := client.Do(req)
if err != nil {
panic(err)
}
defer resp.Body.Close()
body, _ := ioutil.ReadAll(resp.Body)
fmt.Println(string(body))
}
```
```json 401 - Invalid API Key theme={null}
{
"error": {
"type": "authentication_error",
"message": "Invalid API key"
}
}
```
```json 400 - Invalid Request theme={null}
{
"error": {
"type": "invalid_request_error",
"message": "messages: field required"
}
}
```
```json 429 - Rate Limit Exceeded theme={null}
{
"error": {
"type": "rate_limit_error",
"message": "Rate limit exceeded"
}
}
```
```json 500 - Internal Server Error theme={null}
{
"error": {
"type": "api_error",
"message": "Internal server error"
}
}
```
```json 529 - Overloaded theme={null}
{
"error": {
"type": "overloaded_error",
"message": "Service is temporarily overloaded"
}
}
```
## Parameters
| Parameter | Type | Required | Default | Description |
| ---------------- | ------- | -------- | ------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------- |
| `model` | string | ✅ Yes | `claude-opus-4-thinking` | The model to use for the request |
| `messages` | array | ✅ Yes | `[{'role': 'user', 'content': "What's the weather in NYC?"}]` | Array of message objects for the conversation. Each message must have a role (user or assistant) and content. |
| `max_tokens` | integer | ✅ Yes | `1024` | The maximum number of tokens to generate before stopping |
| `tools` | array | ✅ Yes | - | Array of tool objects. For web search, must include the web\_search tool configuration. |
| `temperature` | number | ❌ No | `1.0` | Amount of randomness injected into the response. Ranges from 0.0 to 1.0 |
| `top_p` | number | ❌ No | `1.0` | Use nucleus sampling. Ranges from 0.0 to 1.0 |
| `top_k` | integer | ❌ No | `null` | Only sample from the top K options for each subsequent token |
| `stream` | boolean | ❌ No | `false` | Whether to incrementally stream the response using server-sent events |
| `stop_sequences` | array | ❌ No | - | Custom text sequences that will cause the model to stop generating |
### Messages Array Structure
Each message object in the `messages` array should have the following structure:
| Field | Type | Required | Description |
| --------- | ------------ | -------- | ----------------------------------------------------------------- |
| `role` | string | ✅ Yes | The role of the message. Can be: `user`, `assistant`, or `system` |
| `content` | array/string | ✅ Yes | The content of the message |
### Content Array Structure (when content is an array)
| Field | Type | Required | Example | Description |
| ------ | ------ | -------- | ------------------------------ | ------------------------------------ |
| `type` | string | ✅ Yes | `text` | The type of content |
| `text` | string | ✅ Yes | `"What's the weather in NYC?"` | The text content when type is `text` |
### Tools Array Structure
For web search functionality, the `tools` array should contain a web search tool object:
| Field | Type | Required | Example | Description |
| ----------------- | ------- | -------- | -------------------------------------- | --------------------------------------------------------------------------- |
| `type` | string | ✅ Yes | `web_search_20250305` | The type of tool. Must be `web_search_20250305` for web search |
| `name` | string | ✅ Yes | `web_search` | The name of the tool |
| `max_uses` | integer | ❌ No | `5` | Maximum number of times the web search tool can be used in a single request |
| `allowed_domains` | array | ❌ No | `["example.com", "trusteddomain.org"]` | Only include search results from these domains |
| `blocked_domains` | array | ❌ No | `["untrustedsource.com"]` | Never include search results from these domains |
| `user_location` | object | ❌ No | - | Localize search results based on user's location |
#### Max Uses
The `max_uses` parameter limits the number of searches performed. If Claude attempts more searches than allowed, the `web_search_tool_result` will be an error with the `max_uses_exceeded` error code.
#### Domain Filtering
When using domain filters:
* Domains should not include the HTTP/HTTPS scheme (use `example.com` instead of `https://example.com`)
* Subdomains are automatically included (`example.com` covers `docs.example.com`)
* Specific subdomains restrict results to only that subdomain (`docs.example.com` returns only results from that subdomain, not from `example.com` or `api.example.com`)
* Subpaths are supported (`example.com/blog`)
* You can use either `allowed_domains` or `blocked_domains`, but not both in the same request
* Request-level domain restrictions must be compatible with organization-level domain restrictions configured in the Console
#### User Location Structure
The `user_location` object allows you to localize search results based on a user's location:
| Field | Type | Required | Example | Description |
| ---------- | ------ | -------- | --------------------- | -------------------------------------------- |
| `type` | string | ✅ Yes | `approximate` | The type of location (must be `approximate`) |
| `city` | string | ✅ Yes | `San Francisco` | The city name |
| `region` | string | ✅ Yes | `California` | The region or state |
| `country` | string | ✅ Yes | `US` | The country code |
| `timezone` | string | ✅ Yes | `America/Los_Angeles` | The IANA timezone ID |
#### Complete Tool Configuration Example
```json theme={null}
{
"type": "web_search_20250305",
"name": "web_search",
"max_uses": 5,
"allowed_domains": ["example.com", "trusteddomain.org"],
"user_location": {
"type": "approximate",
"city": "San Francisco",
"region": "California",
"country": "US",
"timezone": "America/Los_Angeles"
}
}
```