Claude Sonnet 4.5

claude-sonnet-4.5 by Anthropic Released September 30, 2025
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off
Input from
$3 / 1M
Output from
$15 / 1M
Cached input from
$0.3 / 1M
Context window
1M
Endpoints
5
from 2 providers
Regions
Monde, Europe, États-Unis

About Claude Sonnet 4.5

Claude Sonnet 4.5 est le modèle de raisonnement hybride le plus avancé d’Anthropic. Il propose deux modes : des réponses quasi instantanées et une réflexion approfondie pour un raisonnement plus poussé, en fonction de la complexité de la tâche. Claude Sonnet 4.5 est particulièrement adapté aux applications nécessitant un équilibre entre débit opérationnel et réflexion avancée, telles que les agents en contact avec la clientèle, les workflows de codage en production et la génération de contenu à grande échelle. Ce point de terminaison est hébergé par Databricks.

Claude Sonnet 4.5 est un modèle conversationnel développé par Anthropic, disponible sur Eden AI via 5 endpoints chez 2 fournisseurs, à partir de 3 $ par million de tokens en entrée et 15 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 1M tokens.

Providers and prices

5 endpoints from 2 providers, cheapest first, in USD per million tokens. Every one is called with the same Eden AI key: pin one with its endpoint ID, or let Eden AI route for you. .

Endpoint
Region
Context
Input / 1M
Output / 1M
Cached / 1M
Supports
Databricks (Europe)Official−%databricks/databricks-claude-sonnet-4-5@eu
Europe
200K
$3$3
$15
$0.3
ReasoningToolsJSONCacheVisionWeb
DatabricksOfficial−%databricks/databricks-claude-sonnet-4-5
Monde
200K
$3$3
$15
$0.3
ReasoningToolsJSONCacheVisionWeb
Google CloudOfficial−%vertex/claude-sonnet-4-5
Monde
1M
$3$3
$15
$0.3
ReasoningToolsJSONCacheVisionWeb
Google Cloud (Europe)Official−%vertex/claude-sonnet-4-5@eu
Europe
1M
$3.3$3.3
$16.5
$0.33
ReasoningToolsJSONCacheVisionWeb
Google Cloud (États-Unis)Official−%vertex/claude-sonnet-4-5@us
États-Unis
1M
$3.3$3.3
$16.5
$0.33
ReasoningToolsJSONCacheVisionWeb

Performance

Measured on real Eden AI traffic over the last 30 days. Endpoints with too little traffic are not shown.

Fastest first token
0.63 s
Google Cloud (Europe)
Lowest latency
0.89 s
Google Cloud (Europe)
Highest throughput
21.04 tok/s
Google Cloud
Best availability
100%
Databricks (Europe)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Databricks (Europe)
1.21 s
1.42 s
5.19 s
3.96 tok/s
100%
0%
0%
0%
Databricks
1.21 s
6.94 s
20.44 s
4.1 tok/s
100%
0%
0%
0%
Google Cloud
1.42 s
1.4 s
106.56 s
21.04 tok/s
100%
51.73%
0%
50%
Google Cloud (Europe)
0.63 s
0.89 s
5.64 s
8.26 tok/s
100%
0%
0%
50%
Google Cloud (États-Unis)
s
s
s
tok/s
%
%
%
%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call Claude Sonnet 4.5 with Eden AI

Use the model ID to let Eden AI pick an endpoint, or an endpoint ID from the table above to pin one.

import requests

response = requests.post(
    "https://api.edenai.run/v3/chat/completions",
    headers={"Authorization": "Bearer YOUR_EDENAI_API_KEY"},
    json={
        "model": "",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about Claude Sonnet 4.5

On Eden AI, prices for this model start at $3 per million input tokens and $15 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

Up to 1M tokens, depending on the endpoint.

5 endpoints from 2 providers, available in: Monde, Europe, États-Unis. All of them are called with the same Eden AI API key.

Yes. At least one endpoint is hosted in Europe; pin it with its endpoint ID from the providers table to keep requests in the EU.

Over the last 30 days, the fastest first token was 0.63 s (Google Cloud (Europe)) and the highest throughput was 21.04 tokens per second (Google Cloud).