How much does Claude Sonnet 4.5 cost?

Claude Sonnet 4.5 costs $3.00/M input tokens and $15.00/M output tokens, with separate rates for Cache Read at $0.30/M tokens, Cache Write at $3.75/M tokens and Cache Write (1h) at $6.00/M tokens.

What is the context length of Claude Sonnet 4.5?

Claude Sonnet 4.5 has a 1,000,000 token context window. It supports up to 64,000 completion tokens.

Does Claude Sonnet 4.5 support tool calling and structured outputs?

Yes. Claude Sonnet 4.5 accepts tools and tool_choice for function calling. It does not support response_format, so JSON output is not enforced.

What inputs and outputs does Claude Sonnet 4.5 support?

Claude Sonnet 4.5 accepts text, images and files such as PDFs as input and returns text.

Which providers serve Claude Sonnet 4.5?

Claude Sonnet 4.5 is served by 5 providers on OpenRouter: Google Vertex (US), Azure, Claude Platform on AWS, Amazon Bedrock (EU) and Anthropic. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was Claude Sonnet 4.5 released?

Claude Sonnet 4.5 was released on September 29, 2025. Its knowledge cutoff is January 31, 2025.

Anthropic: Claude Sonnet 4.5

Name: Anthropic: Claude Sonnet 4.5
Author: anthropic

anthropic/claude-sonnet-4.5

Compare

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.

Sonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.

Modalities

In / Out Price

$3 / $15per 1M

Context

Released

Sep 29, 2025

Knowledge Cutoff

Jan 2025

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).

Latency / throughput


$3.00	$15.00	$0.30	1.02s	34 tps	100.00%
$3.00	$15.00	$0.30	1.73s	39 tps	100.00%
$3.00	$15.00	$0.30	--	--	99.96%
$3.00	$15.00	$0.30	1.60s	36 tps	99.92%
$3.00	$15.00	$0.30	1.00s	38 tps	99.89%
$3.30	$16.50	$0.33	--	--	100.00%
$3.30	$16.50	$0.33	--	--	100.00%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

39tok/s

P50, best across providers

Latency

1.00s

P50, best provider

Latency / throughput

AutoExacto Benchmarks

GPQA DiamondTAU-Bench

Amazon Bedrock

82.6%75.6%

auto-routing

82.8%74.8%

Amazon Bedrock

82.3%74.9%

Anthropic

80.6%76.1%

Google Vertex (US)

82.1%74.6%

Google Vertex (Global)

81.6%74.8%

Claude Platform on AWS

79.5%76.9%

Claude Platform on AWS

78.8%77.4%

Claude Platform on AWS

80.5%74.5%

+1 more providers

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.98%

Availability over the last 3 days

Last 72 hours

Availability 99.98%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.96%

Without Routing

98.23%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Chataigne Clerk

new

17.5Btokens

Claude Code

Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.

12.8Btokens

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

12.7Btokens

Janitor AI

Janitor AI is a chatbot platform where users create and chat with custom AI characters for interactive roleplay, storytelling, and immersive fiction.

9.88Btokens

OpenClaw

OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.

9.61Btokens