Anthropic: Claude Sonnet 4.5
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows.
- Input
- 1,082,872 Toman/M tokens
- Output
- 5,407,528 Toman/M tokens
- Context
- 1M
- Max output
- 64K
- Published
- Sep 29, 2025
- Maker
- Anthropic
Free plan prices, in Toman at today's rate. Plans and prices
Price by plan
Toman per million tokens at today's rate. A plan lowers the price of your usage up to a limit each period. Up to 200K tokens.
| Plan | Input | Output |
|---|---|---|
| Free | 1,082,872 | 5,407,528 |
| Pro | 1,038,492 | 5,185,908 |
| Max | 994,112 | 4,964,288 |
Long prompts
This model costs more when a request's prompt is long: once the prompt reaches the size below, the whole request is billed at the higher price (as its provider bills it). Toman per million tokens, per plan.
| Plan | Input | Output |
|---|---|---|
| Free | 2,162,328 | 8,109,584 |
| Pro | 2,073,708 | 7,777,224 |
| Max | 1,985,088 | 7,444,864 |
Images and other units
Toman per million tokens of each kind, per plan, at today's rate. A generated 1024×1024 image is usually 1,100–1,300 image tokens on Gemini image models and up to about 6,000 on GPT image models at high quality; the exact count is in each response's usage.
| Unit | Free | Pro | Max |
|---|---|---|---|
| Prompt cache writes (5 minutes) | 1,352,736 | 1,297,296 | 1,241,856 |
| Prompt cache writes (1 hour) | 2,162,328 | 2,073,708 | 1,985,088 |
Capabilities
- Text
- Vision
- Tools
- JSON
- Reasoning
What it takes and gives
- Text
- Image
- File (PDF)
- Text
Every input listed here works through the API and the playground: images and PDFs as data URLs or https links, audio as base64, video as a data URL or a link the model supports.
Call it
Pass anthropic/claude-sonnet-4.5 as the model name, or let router/auto choose for you.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://ai.fluxcdn.cloud/api/v1",
api_key=os.environ["FLUXCDN_API_KEY"],
)
resp = client.chat.completions.create(
model="router/auto",
messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)
