Anthropic: Claude Sonnet 4.5

Claude Sonnet 4.5 is Anthropic's advanced Sonnet model, released 2025-09, optimized for real-world agents and coding workflows. It shows strong results on SWE-bench Verified, with improvements in system design, code security, and specification adherence. The model supports extended autonomous operation and fact-based progress tracking, and suits software engineering, cybersecurity, and research agents.

Modalities
inTextinImageinFileoutText
Price / 1M−70%
$0.90 / $4.50$3.00 / $15.00
Context
1M
Released
Sep 29, 2025
Knowledge cutoff
Jan 31, 2025

Channels

Every channel serves the same model, but they differ in price and stability. On each API key in the Platform, you pick a primary and a backup channel per vendor, and each billing line shows which channel served the request.

Provider
Discount
Input /M
Output /M
Cache read /M
Cache write 5m /M
Cache write 1h /M
Code_maxstable
−70%
$0.90
$4.50
$0.09
$1.13
$1.80

Context pricing

This model’s price depends on how much input context a request carries. The headline price is the cheapest band, and a longer prompt moves the whole request into a higher one.

Input context
Input /M
Output /M
Cache read /M
Cache write /M
Cache write 1h /M
standardBase
$0.90
$4.50
$0.09
$1.13
$1.80

Capabilities

ReasoningVisionTool useLong contextPrompt cachingStructured output

Parameters

Request parameters this model accepts through the API.

include_reasoningmax_completion_tokensmax_tokensreasoningresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

Cost calculator

Pick a channel and a usage scenario, then drag the sliders to match your workload. Each scenario assumes a different prompt-cache hit rate.

Channel
Scenario
Unit $0.90 / $4.50 /1MDaily chat: 40% cache hit rate assumed · cache read $0.09 /1M
List price $904.32On MirAPI$271.30/ moYou save $633.02Create an API key

Benchmarks

bar = score (0–100) · ▏ median

Scores come from vendor reports and public leaderboards, not private evals.

Intelligence Index
General ability
20.7
#80
Coding Index
Code
52.1
#42
Agentic Index
Agentic
15.8
#38
GPQA Diamond
Science QA
82.0
#68
τ-bench (airline)
Agentic tool use
73.0
#51

Showcase

Every chat model gets the same three fixed prompts. Outputs are archived verbatim, so you can copy a prompt and reproduce the result.

Task prompt · identical for all models
Build a single-file HTML page using three.js from a CDN: a low-poly planet with a tilted ring of ~200 orbiting particles, a soft key light plus rim light, slow auto-rotation, and drag-to-orbit controls. No build tools — one file only.
Archived output
Archive not published yet

Every model will run this exact prompt, and its output will appear here verbatim with token counts and the cost per run.

Quick start

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.mirapi.ai/v1",   # changed
    api_key=os.environ["MIRAPI_API_KEY"],   # changed
)

resp = client.chat.completions.create(
    model="claude-sonnet-4-5",
    messages=[{"role": "user", "content": "Hello"}],
)
Wire Claude Sonnet 4.5 into your product

1M free tokens to start, no card required. It’s OpenAI-compatible, so you only change the base URL.

Start free