Input

Output

Send a message on the left. The reply appears here.

Pricing

This model is priced by the usage dimensions listed here. Compare all pricing.

List prices in USD. Your effective price also depends on the billing group attached to your API key.

Criteria输入tokenclaude-opus-4-6-aws

$3.25per 1M~~5/1M~~

Criteria输出tokenclaude-opus-4-6-aws

$16.25per 1M~~25/1M~~

Criteria缓存读tokenclaude-opus-4-6-aws

$0.325per 1M~~0.5/1M~~

Criteria缓存写tokenclaude-opus-4-6-aws

$4.0625per 1M~~6.25/1M~~

API

POST/v1/messages

const BASE_URL = "https://api.dreamtoai.com";
const API_KEY = process.env.MIX_API_KEY;

const headers = {
  "Authorization": `Bearer ${API_KEY}`,
  "Content-Type": "application/json",
};

const payload = {
  "model": "claude-opus-4-6-aws",
  "messages": [
    {
      "content": "你好，世界",
      "role": "user"
    }
  ],
  "system_instruction": "请用简洁中文回答。",
  "max_tokens": 4096,
  "temperature": 0.7,
  "top_p": 0.95,
  "top_k": 40,
  "thinking": {
    "budget_tokens": 1024,
    "type": "enabled"
  },
  "tools": [],
  "tool_choice": "auto",
  "stream": false,
  "stop_sequences": [
    "\n\nHuman:"
  ],
  "metadata": {
    "user_id": "user-xxx"
  },
  "output_config": {
    "effort": "high"
  },
  "cache_control": {
    "ttl": "5m",
    "type": "ephemeral"
  }
};

const submit = await fetch(`${BASE_URL}/v1/jobs`, {
  method: "POST",
  headers,
  body: JSON.stringify(payload),
}).then((r) => r.json());

const status = await fetch(`${BASE_URL}/v1/jobs/${submit.id}`, { headers })
  .then((r) => r.json());
console.log(status);

Create a key in Console → API Keys and replace the placeholder in the sample.

README

claude-opus-4-6-aws

AWS官方版本，服务稳定

Why Choose This?

Language and reasoning: Handles writing, analysis, coding and multi-turn conversation in one model.
Pay per token: $3.25 per 1M input tokens and $16.25 per 1M output tokens, with no subscription.
Prompt caching: Cached input is billed at $0.33 per 1M tokens, which cuts the cost of repeated context.
Works with your existing SDK: Call it in the Anthropic Messages / OpenAI Chat Completions format, so existing clients only need a new base URL and key.
One key for every model: The same API key works for every model on dreamtoai.

Parameters

Parameter	Required	Description
`messages`array	Required	Conversation history as a list of role and content messages.
`system_instruction`string	Optional	Instructions that set the assistant behavior.
`max_tokens`integer	Optional	Maximum number of tokens to generate. Default: `4096`.
`temperature`number	Optional	Sampling temperature. Lower is more focused, higher is more varied. Default: `0.7`.
`top_p`number	Optional	Nucleus sampling threshold.
`top_k`integer	Optional	Top K
`thinking`object	Optional	扩展思考
`tools`array	Optional	工具列表
`tool_choice`string	Optional	工具选择
`stream`boolean	Optional	Stream the reply as server-sent events. Default: `false`.
`stop_sequences`array	Optional	停止序列
`metadata`object	Optional	元数据
`output_config`object	Optional	输出配置
`cache_control`object	Optional	提示词缓存控制

How to Use

Try it here first — Sign in and run the model in the playground above to check the output before you write code.
Create an API key — Open Console → API Keys and create a key. The same key works for every model.
Write your messages — Put the task and its context in the messages array; add a system prompt to set the assistant behavior.
Set optional parameters — Adjust the optional parameters listed above to control the output.
Send the request — Call POST /v1/messages with the model ID claude-opus-4-6-aws.
Read the reply — The reply and its token usage come back in the response and are logged in the console.

Writing Effective Prompts

Clear instructions get better answers. Tell the model who it is, what you need and how the answer should look.

1. Set the role and goal

Open with who the model should act as and what the task is. Put rules that never change in the system prompt.

You are a senior Python reviewer. Review the function below for bugs and readability.

2. Give the context

Paste what the answer depends on: documents, code, data or earlier decisions. Separate each part with a heading or tag.

3. Specify the output

Name the format, length and tone: a table, JSON with given keys, five bullet points, a 200-word summary.

4. Show an example

One or two input and output examples fix the style faster than a long description.

5. Iterate

When an answer misses, add the missing constraint to the prompt instead of starting over.

	Prompt
Weak	Write about our product.
Strong	You are a B2B copywriter. Write three 40-word LinkedIn posts announcing our invoicing API for small accounting firms. Tone: confident, plain English, no emojis. End each post with a question.

Pricing

Billing item	Price	Official price
输入token	$3.25 per 1M	~~$5.00/1M~~
输出token	$16.25 per 1M	~~$25.00/1M~~
缓存读token	$0.325 per 1M	~~$0.50/1M~~
缓存写token	$4.0625 per 1M	~~$6.25/1M~~

That is 35% below the official list price.

Example: a request with 10,000 input tokens and 1,000 output tokens costs about $0.05.

List prices in USD. Your effective price also depends on the billing group attached to your API key. Compare all pricing

Best Use Cases

Coding assistants — Generate, review and refactor code, or explain an unfamiliar codebase.
Agents and automation — Plan multi-step tasks and call tools from your own workflows.
Knowledge work — Summarize reports, draft documents and answer questions over your own content.
Customer support — Power help-desk bots and draft replies in a consistent tone.
Data extraction — Turn unstructured text into structured JSON for downstream systems.
Translation and localization — Translate and adapt copy across languages.

Pro Tips

Put stable instructions in the system prompt and keep user messages for the task itself.
Set max_tokens to cap the length and cost of each reply.
Keep a long shared prefix identical across requests so repeated input is billed at the cache price.
Ask for JSON with the exact keys you need when a program reads the answer.
Test prompts in the playground above before wiring them into code.
Check token usage in the console to spot unusually expensive prompts.

claude-opus-4-6
claude-opus-4-6-fast
Claude Opus 4.7 — claude-opus-4-7
Claude Sonnet 4.6 — claude-sonnet-4-6
Claude Haiku 4.5 — claude-haiku-4-5

Browse all LLMs Browse API Market

FAQ

What is claude-opus-4-6-aws?

AWS官方版本，服务稳定

How do I call the claude-opus-4-6-aws API?

Send POST /v1/messages with the model ID claude-opus-4-6-aws and your API key. Ready-to-run samples are in the API section above.

How is billing calculated?

Requests are billed at the prices listed above and charged to your wallet. Final cost depends on usage and the billing group attached to your API key.

Where do I get an API key?

Create one in Console → API Keys. The same key works for every model on the gateway.

Can I use the output commercially?

Yes. You can use what you generate in commercial projects, subject to the model provider’s terms.

Claude/claude-opus-4-6-aws

Input

Output

Pricing

API

claude-opus-4-6-aws

Why Choose This?

Parameters

How to Use

Writing Effective Prompts

1. Set the role and goal

2. Give the context

3. Specify the output

4. Show an example

5. Iterate

Pricing

Best Use Cases

Pro Tips

FAQ

About claude-opus-4-6-aws on dreamtoai

Related models

Next steps