Claude Sonnet 4.5
AnthropicReleased Sep 29, 2025
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...
- Context window
- 1M tokens
- Max output
- 64K tokens
- Input
- text, image, file
- Output
- text
- Tokenizer
- Claude
- Knowledge cutoff
- Jan 31, 2025
- Released
- Sep 29, 2025
- Reasoning
- optional
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | $3.00 | $0.090 | $3.09 |
| Output | $15.00 | $0.450 | $15.45 |
| Cache read | $0.300 | $0.0090 | $0.309 |
| Cache write | $3.75 | $0.112 | $3.86 |
Benchmarks
Design Arena
| Category | Elo | Win rate | Rank |
|---|---|---|---|
| 3Dmodels | 1236 | 53.5% | #34 |
| ASCII artmodels | 1249 | 56.8% | #10 |
| Codemodels | 1232 | 53% | #34 |
| Data vizmodels | 1211 | 49.3% | #42 |
| Game devmodels | 1233 | 52.1% | #37 |
| SVGmodels | 1173 | 53% | #37 |
| UI componentsmodels | 1234 | 52.3% | #35 |
| Websitesmodels | 1232 | 53.4% | #38 |
| Full-stackagents | 1120 | 43.5% | #18 |
| Mobile appsagents | 1184 | 48.9% | #21 |
| Web appsagents | 1129 | 43.1% | #21 |
Head-to-head preference voting. How we filter and rank
Supported parameters
- include_reasoning
- max_tokens
- reasoning
- response_format
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_p
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model anthropic/claude-sonnet-4.5.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer $OPENKEY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-sonnet-4.5",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openkey.ai/v1",
api_key=os.environ["OPENKEY_API_KEY"],
)
completion = client.chat.completions.create(
model="anthropic/claude-sonnet-4.5",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openkey.ai/v1",
apiKey: process.env.OPENKEY_API_KEY,
});
const completion = await client.chat.completions.create({
model: "anthropic/claude-sonnet-4.5",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);Questions
- How much does Claude Sonnet 4.5 cost via API?
- Through OpenKey, Claude Sonnet 4.5 costs $3.09 per 1M input tokens and $15.45 per 1M output tokens. That is the provider price ($3.00 / $15.00) plus a flat 3% fee — nothing else.
- What is Claude Sonnet 4.5's context window?
- Claude Sonnet 4.5 accepts up to 1M tokens of context and returns up to 64K tokens per request.
- Is Claude Sonnet 4.5 OpenAI-compatible?
- Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "anthropic/claude-sonnet-4.5" using any OpenAI SDK — only the base URL and API key change.
- What inputs does Claude Sonnet 4.5 support?
- Claude Sonnet 4.5 accepts text, image, file input and produces text output. Its knowledge cutoff is Jan 31, 2025.
More from Anthropic
All Anthropic models →Claude Sonnet 5
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...
ctx 1Min $2.06out $10.30
Claude Fable 5
Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...
ctx 1Min $10.30out $51.50
Claude Fable Latest
This model always redirects to the latest model in the Claude Fable family.
ctx 1Min $10.30out $51.50
Claude Opus 4.8
Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...
ctx 1Min $5.15out $25.75