anthropic/claude-sonnet-4-6
200K context · $1.20 / M input tokens · $6.00 / M output tokens
Claude Sonnet 4.6 is Anthropic's balanced frontier model, offering strong reasoning and coding performance at a lower cost than Opus, ideal for high-volume production workloads.
2026-07-09 06:37:20 UTC
Pricing
Pay-per-use
No upfront costs, pay only for what you use
API Usage
API Access Guide
Code examples
Use the OurToken API endpoint for this model. The examples below use direct HTTP requests and the recommended endpoint for the model family.
curl https://api.ourtoken.ai/v1/messages \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "claude-sonnet-4-6",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"max_tokens": 256
}'Messages API Reference
Create a Claude Messages-compatible response through OurToken. This format uses a messages array, max_tokens, optional system prompts, tools, and thinking settings.
Authorization
| Content-Type | application/json |
| Authorization | Bearer YOUR_API_KEY |
Request Body
| Field | Type | Required | Description |
|---|---|---|---|
| model | string | Required | Model ID to call. |
| messages | array<object> | Required | Conversation messages sent to the model. |
| system | string | array<object> | Optional | Optional system prompt. |
| max_tokens | integer | Required | Maximum number of output tokens. |
| temperature | number | Optional | Sampling temperature. |
| top_p | number | Optional | Nucleus sampling parameter. |
| top_k | integer | Optional | Top-k sampling parameter. |
| stream | boolean | Optional | Whether to return a streaming response. |
| stop_sequences | array<string> | Optional | Sequences that stop generation. |
| tools | array<object> | Optional | Tools available to the model. |
| tool_choice | object | Optional | Controls how the model selects tools. |
| thinking | object | Optional | Thinking configuration for supported Claude models. |
| metadata | object | Optional | Optional request metadata. |
Response Body
| Field | Type | Required | Description |
|---|---|---|---|
| id | string | Required | Unique message identifier. |
| type | "message" | Required | Object type returned by the Messages API. |
| role | "assistant" | Required | Role of the returned message. |
| content | array<object> | Required | Array of content blocks returned by the model. |
| content[].text | string | Optional | Text inside a returned content block. |
| model | string | Required | Model that produced the response. |
| stop_reason | string | Optional | Reason generation stopped. |
| usage | object | Optional | Token usage information for the message. |
| usage.input_tokens | integer | Optional | Input token count. |
| usage.output_tokens | integer | Optional | Output token count. |
| usage.cache_creation_input_tokens | integer | Optional | Tokens written to prompt cache. |
| usage.cache_read_input_tokens | integer | Optional | Tokens read from prompt cache. |
Model Introduction
Anthropic claude-sonnet-4-6
Claude Sonnet 4.6 is Anthropic's balanced frontier model, offering strong reasoning and coding performance at a lower cost than Opus, ideal for high-volume production workloads.
Claude Sonnet 4.6 delivers strong reasoning, coding, and analysis capabilities with a 200K token context window, optimized for production workloads that need quality at scale. At $1.20 input / $6.00 output per million tokens (40% of official price), it is the most cost-effective Claude 4 series model for teams running high-volume applications.
Why It Looks Great
- Strong reasoning and coding at a significantly lower price than Claude Opus 4.6/4.7.
- 200K token context window with up to 64K output tokens for long-form generation.
- Supports vision inputs for document understanding and multimodal workflows.
- Optimized for high-volume production use cases with consistent output quality.
- Accessible via the OurToken unified API at 40% of the standard Anthropic price.
Key Features
- Context Window: 200000 tokens
- Max Output: 64000 tokens
- Vision: Supported
- Function Calling: Supported
- Input: Text, Image
- Output: Text
Specifications
Claude Sonnet 4.6 API Features for Developers
Use Claude Sonnet 4.6 API on OurToken for strong reasoning, Claude Sonnet 4.6 pricing clarity, long output, coding workflows, and production-scale access.
Strong Reasoning
Use Claude Sonnet 4.6 API for complex analysis, planning, and multi-step reasoning that needs consistent production quality. Teams evaluating Claude Sonnet 4.6 can test it on high-volume tasks before choosing it as their default balanced Anthropic model.
Production Coding
Apply Claude Sonnet 4.6 to code generation, debugging, refactoring, and customer-facing engineering pipelines. This also serves claude sonnet 4.6 api search intent for teams looking for a practical coding model with strong throughput.
Long Output
Use the 64K output window for detailed reports, long code files, extended responses, and workflow steps that need more room than typical models provide. Claude Sonnet 4.6 API is well suited to tasks that must finish in one pass.
Vision and Multimodal Input
Send text and image inputs for document understanding, screenshot analysis, and multimodal product experiences. Claude Sonnet 4.6 API can handle user-facing workflows that combine text reasoning with visual context.
Cost Efficiency
At $1.20 input and $6.00 output per million tokens on OurToken, Claude Sonnet 4.6 gives teams a practical balance of cost and quality. That makes claude sonnet 4.6 pricing and claude sonnet 4.6 price comparisons easy to evaluate.
Unified Anthropic API Access
Route Claude Sonnet 4.6 API requests through the same OurToken endpoint used for supported providers. Developers searching for anthropic 4.6 api access can compare integration behavior, price, and production quality in one place.
How to Use Claude Sonnet 4.6 API on OurToken
Create an API key, choose Claude Sonnet 4.6 API, compare pricing, then test coding, long output, structured output, and production quality.
Generate API Key
Create an OurToken API key and store it in a secure server-side environment variable. That gives your backend a stable way to call Claude Sonnet 4.6 API without exposing credentials in client-side code.
01Select Model ID
Use claude-sonnet-4-6 as the model value when sending chat completions requests. Keep your documentation clear for developers searching Claude Sonnet 4.6, Claude Sonnet 4.6 API, or anthropic 4.6 api access.
02Compare Pricing
Before production rollout, compare Claude Sonnet 4.6 pricing against expected request volume, prompt size, and output length. Use the displayed Claude Sonnet 4.6 price to estimate coding, document, and automation costs.
03Use Context and Output
Provide relevant documents, code, and task constraints, then take advantage of the 64K output limit for detailed reports, long code generation, and extended responses. Claude Sonnet 4.6 API works well when the prompt has enough structure.
04Connect Tools
Expose only the tools your workflow actually needs and describe when each should be used. Claude Sonnet 4.6 API can support tool-heavy workflows without requiring a separate integration path.
05Compare with Opus 4.6
Benchmark Claude Sonnet 4.6 vs Opus 4.6 on your hardest tasks to find the right quality-cost tradeoff. This helps answer sonnet 4.6 vs opus 4.6 searches with practical production guidance.
06Claude Sonnet 4.6 API FAQ
Answers about Claude Sonnet 4.6 API access, Claude Sonnet 4.6 pricing, long output, Anthropic 4.6 API usage, and production workflows.
