Claude Sonnet 4
anthropic/claude-sonnet-4Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...
Pricing
Current model usage rates. Choose your plan to see its published prices.
| Usage | Pricing |
|---|---|
| Input | US$3.18/ 1M token |
| InputInput length ≥ 200,001 tokens | US$6.36/ 1M token |
| Cache read | US$0.318/ 1M token |
| Cache readInput length ≥ 200,001 tokens | US$0.636/ 1M token |
| Cache write | US$3.975/ 1M token |
| Cache writeInput length ≥ 200,001 tokens | US$7.95/ 1M token |
| Cache write · 1 h | US$6.36/ 1M token |
| Cache write · 1 hInput length ≥ 200,001 tokens | US$12.72/ 1M token |
| Output | US$15.9/ 1M token |
| OutputInput length ≥ 200,001 tokens | US$23.85/ 1M token |
Membership and model usage are billed separately. Compare plans
Capabilities
- Input
- FileImageText
- Output
- Text
- Context window
- 1,000,000 token
- Maximum output
- 64,000 token
Providers
Model supply available through Vecbase.
Via OpenRouter
Access is subject to your account’s permissions and model availability.
Frequently asked questions
What is Claude Sonnet 4, and who develops it?
Claude Sonnet 4 is a model from Anthropic. Its model ID on Vecbase is anthropic/claude-sonnet-4. Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...
How much does Claude Sonnet 4 cost on Vecbase?
For Claude Sonnet 4, the Club plan lists USD 3.18 per 1 million input tokens and USD 15.9 per 1 million output tokens, as of 10/17/2026, 6:41:14 PM UTC. See the pricing table for cache rates, input-length tiers and other usage types. Membership fees are separate.
How many tokens fit in Claude Sonnet 4’s context window?
Claude Sonnet 4 has a context window of 1,000,000 tokens. Input and output must fit within the limits of the API you use.
What is the maximum output length for Claude Sonnet 4?
Claude Sonnet 4 can generate up to 64,000 tokens per response. Your API or request settings may set a lower limit.
Can Claude Sonnet 4 call tools in an agent workflow?
Yes. Claude Sonnet 4 supports tool calling. Your application provides the tool definitions and runs the tools the model requests.
Which input and output formats does Claude Sonnet 4 support?
Claude Sonnet 4 accepts File, Image, and Text and produces Text.
Which providers make Claude Sonnet 4 available through Vecbase?
Vecbase offers Claude Sonnet 4 through OpenRouter. Availability may vary by provider.
Which model ID should an agent use to request Claude Sonnet 4?
Use anthropic/claude-sonnet-4 as the model identifier for Claude Sonnet 4. See Vecbase’s API documentation for authentication, required inputs and supported request formats.
What does an agent need to access Claude Sonnet 4 through Vecbase?
To use Claude Sonnet 4, you need an authenticated account with the required permissions, sufficient balance and the relevant capability enabled. See the documentation for setup.
Is a release date available for Claude Sonnet 4?
We do not yet have a confirmed release date for Claude Sonnet 4.
Which models can I compare with Claude Sonnet 4 on Vecbase?
You can compare Claude Sonnet 4 with Claude Haiku Latest (anthropic/claude-haiku-latest), Claude Sonnet Latest (anthropic/claude-sonnet-latest), and Claude Opus Latest (anthropic/claude-opus-latest). Check their capabilities and prices to find the best fit for your task.
