xKiro
Anthropic

Sonnet 4

A balanced Sonnet-class model for general coding and professional tasks.

Claude models work only with Anthropic’s official tools

Claude models on xKiro accept requests only from Anthropic’s official tools: Claude Code (in the terminal or your IDE), Claude Desktop and Cowork. Third-party tools (such as OpenCode, Cline, Roo Code, Kilo Code, Cursor or Codex), xKiro chat and direct API calls from your own code are not supported and return an error. Every other model on xKiro works with any tool or SDK, including xKiro chat.

Set up Claude Code
Get your API key

Model ID

anthropic/claude-sonnet-4
Context window
1M
tokens
Max output
66K
tokens
Input
$3
per 1M tokens
Output
$15
per 1M tokens

Cache read $0.3 · Cache write $3.75

Quickstart

Call Sonnet 4 in one request.

Claude models run only in Anthropic’s official tools. Point Claude Code at xKiro once and select this model — the same key works for every model in the catalog.

SDK guides
~/.claude/settings.json
{  "env": {    "ANTHROPIC_BASE_URL": "https://api.xkiro.com",    "ANTHROPIC_AUTH_TOKEN": "sk-xt-...",    "ANTHROPIC_MODEL": ""  }}
Terminal
claude
Claude Code now sends its requests to anthropic/claude-sonnet-4 through xKiro.

Create an API key in the dashboard and paste it into ANTHROPIC_AUTH_TOKEN.

Pricing

What Sonnet 4 costs.

Billed per million tokens at these rates, from your plan’s budget or your wallet.

  • $3

    Input

    per 1M tokens

  • $15

    Output

    per 1M tokens

  • $0.3

    Cache read

    per 1M tokens

  • $3.75

    Cache write

    per 1M tokens

On a plan

From $0.1 / $0.5 on a plan

Plan: up to −96%

Usage on a plan comes out of your allowance, so Sonnet 4 costs from $0.1 / $0.5 per 1M tokens when you use the whole allowance — up to 96% less than pay-as-you-go.

Compare plans →

Billed fairly

  • Requests that fail with a 5xx error are never billed
  • Retrying an identical blocking request replays the first result — no double charge
  • Cancel a stream and pay only for the tokens generated

Specifications

Limits and capabilities.

Context window
1,000,000 tokens
Max output
65,536 tokens
Input
Text · Image
Output
Text
Provider
Anthropic
Model ID
anthropic/claude-sonnet-4
Good for
Coding · Long context

Capabilities

  • Tool useSupported
  • VisionSupported
  • Video inputNot supported
  • ReasoningSupported

Reasoning effort

  1. none
  2. high

Set it with reasoning_effort in the OpenAI format, or thinking in the Anthropic format.

Reasoning guide

Supported parameters

  • max_tokens
  • temperature
  • top_p
  • stop
  • frequency_penalty
  • presence_penalty
  • seed
  • stream
  • tools
  • tool_choice
  • response_format
  • structured_outputs
  • reasoning
  • include_reasoning

Compare

Similar models.

Closest in price and context window — same provider first, then alternatives from other providers.

Browse all 69 models
Sonnet 4 compared with similar models, prices per 1M tokens
ModelInput / 1MOutput / 1M
Sonnet 4This modelVision · Reasoning · Tool use1M$3$15$0.3
Sonnet 4.5Vision · Reasoning · Tool use1M$3$15$0.3
Sonnet 4.6Vision · Reasoning · Tool use1M$3$15$0.3
Opus 5.5Vision · Reasoning · Tool use1M$4$20$0.2
GPT-5.6 SolVision · Reasoning · Tool use1M$2$10$0.2
GPT-6 SolVision · Reasoning · Tool use1.05M$2$10$0.2
GPT-6.1 SolVision · Reasoning · Tool use1.05M$2$10$0.1
modelanthropic/claude-sonnet-4

Start building with Sonnet 4.

Create a key, point your SDK at xKiro and call anthropic/claude-sonnet-4.

Get your API keyRead the docs

No credit card · Cancel anytime · 26 free models, free forever