HiAPI
OverviewModel MarketplaceAPI KeysUsage StatisticsCall LogsBillingReferralPlaygroundStorageChangelogContact UsSettings
Display unit
N
Powered by hiapi
Settings

Welcome

Contact Us

Claude Sonnet 4.6 supports text conversations, image understanding, adaptive thinking, streaming and tool calling.

Provider: Anthropic

Category: text generation

Endpoint: /v1/chat/completions

Status: Available

Cost: --

Back to models
AnthropicText APIOnline

Claude Sonnet 4.6

Claude Sonnet 4.6 supports text conversations, image understanding, adaptive thinking, streaming and tool calling.

Use in your agent

API access

Endpoint

POST /v1/chat/completions

Base URL

https://api.hiapi.ai

OpenAI Chat Completions compatible. Use one HiAPI key across all available models.

Input price

6,000 Credits

/ 1M tokens

Output price

30,000 Credits

/ 1M tokens

Context

-

context window

Max output

-

output tokens

PlaygroundAPIPricingCapabilitiesOverview

Run settings

The Playground charges the signed-in account balance without requiring an extra API key. Server-side API calls still require a HiAPI API key.

Try Claude Sonnet 4.6

Ask a question, upload images, or paste from clipboard. Then inspect the streamed answer, token usage, latency, and estimated cost.

Upload or paste up to 4 images, 10 MB each. Images are safety reviewed.

Claude Sonnet 4.6 API Quickstart

Call Claude Sonnet 4.6 with the OpenAI-compatible Chat Completions format. Copy a ready-to-use cURL, Python, or Node.js example below.

Code Example
API Endpoint:/v1/chat/completions
curl -X POST "https://api.hiapi.ai/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "claude-sonnet-4-6",
  "messages": [
    {
      "role": "user",
      "content": "A cat walking on the beach at sunset"
    }
  ],
  "stream": false,
  "thinking": {
    "type": "adaptive"
  },
  "output_config": {
    "effort": "high"
  }
}'

Tip: Replace YOUR_API_KEY with your actual API key from the API Keys page.

Compatible with the OpenAI Chat Completions format. Set the base URL, API key, and model name to get started.

Image understanding example

Combine text and image_url in the Chat Completions content array. Use a public HTTPS image URL.

API Endpoint:/v1/chat/completions
curl -X POST "https://api.hiapi.ai/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "claude-sonnet-4-6",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Describe the main subject, setting, and important visual details."
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://static.hiapi.ai/example/subject-1.jpg",
            "detail": "low"
          }
        }
      ]
    }
  ],
  "stream": false,
  "thinking": {
    "type": "adaptive"
  },
  "output_config": {
    "effort": "high"
  }
}'

Tip: Replace YOUR_API_KEY with your actual API key from the API Keys page.

Compatible with the OpenAI Chat Completions format. Set the base URL, API key, and model name to get started.

Claude Sonnet 4.6 full API documentationManage API keysUse the same HiAPI key across all available models.

Claude Sonnet 4.6 API Pricing

Billing follows the input, output, and cache token categories actually reported in usage. All prices below are shown per 1 million tokens.

Input tokens
6,000 Credits/ 1M tokens

Prompts and context sent to the model

Output tokens
30,000 Credits/ 1M tokens

Responses and reasoning generated by the model

Cache read
600 Credits/ 1M tokens
Cache write
7,500 Credits/ 1M tokens
Cache write (1h)
12,000 Credits/ 1M tokens

Claude Sonnet 4.6 Model Specifications

These specifications reflect the current public HiAPI text request contract. Undisclosed capabilities are not inferred by the page.

Streaming
Supported
Tool calling
Supported
Structured JSON
Not disclosed
Reasoning
Supported
Input modalities
text · image
Output modalities
text
Reasoning efforts
low · medium · high · max
Max output
-

About Claude Sonnet 4.6

Claude Sonnet 4.6 supports text conversations, image understanding, adaptive thinking, streaming and tool calling.

HiAPI exposes this model through /v1/chat/completions. Test prompts and parameters in the Playground, then use the same HiAPI API key in your server application.

Provider
Anthropic
Endpoint
/v1/chat/completions
Context window
-
Released
Not disclosed

How to Use Claude Sonnet 4.6

The Playground and API share the same model ID, so three steps take a tested prompt into production.

  1. Step 1

    Validate online

    Test the system prompt, output length, and model-supported reasoning options in the Playground.

  2. Step 2

    Manage API keys

    View an existing key or create another after signing in; one key works across all available models.

  3. Step 3

    Integrate your server

    Send requests to /v1/chat/completions and track cost with the usage object.

Need to compare models and billing tiers?View live pricing for all models

Frequently asked questions

What is Claude Sonnet 4.6?

It is Anthropic's Claude Sonnet 4.6. This page separates provider-described capabilities from HiAPI features verified for this release.

Which endpoint and model ID should I use?

Use POST /v1/chat/completions with model=claude-sonnet-4-6.

Can I reuse the same HiAPI API key?

Yes. The same HiAPI API key can call enabled models. Media models use /v1/tasks with a different request shape.

How do I control thinking and effort?

Use thinking.type=adaptive with output_config.effort. The verified effort values are low, medium, high, and max; adaptive/high is the default. To disable thinking, send thinking.type=disabled and omit effort.

Can I send images?

When image input is enabled in the live catalog, send a messages content array with a text block and an image_url block whose image_url.url is the uploaded URL. The Playground reuses the existing image upload flow.

Does it support streaming and tool continuation?

Set stream=true for SSE. For tools, replay the assistant tool_calls message and matching tool result with the next messages array.

How does prompt caching work?

You may add cache_control with a 5m or 1h TTL to system content. A cache read or write may appear in usage when applicable; sending the control does not guarantee a hit. Check usage and HiAPI logs.

How is usage billed?

Input, output, and applicable cached token categories use the live rates shown on HiAPI model and pricing pages. Check usage and account logs for settled charges.

What should I check when a request fails?

Check the exact model ID, endpoint, key scope and balance, message content shape, and whether selected thinking or cache fields are supported by the current live contract. Start with the API error body and usage/log detail.