Claude Sonnet 5

claude-sonnet-5 by Anthropic Released July 1, 2026
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off
Input from
$2 / 1M
Output from
$10 / 1M
Cached input from
$0.2 / 1M
Context window
1M
Endpoints
10
from 5 providers
Regions
Monde, Europe, États-Unis

About Claude Sonnet 5

Sonnet 5 est le modèle de la classe Sonnet le plus performant d'Anthropic, offrant des performances de pointe dans les domaines du codage, des agents et des tâches professionnelles.

Claude Sonnet 5 est un modèle conversationnel développé par Anthropic, disponible sur Eden AI via 10 endpoints chez 5 fournisseurs, à partir de 2 $ par million de tokens en entrée et 10 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 1M tokens.

Providers and prices

10 endpoints from 5 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-5@eu
Europe
1M
$2$2
$10
$0.2
ReasoningToolsJSONCacheVisionWeb
DatabricksOfficial−%databricks/databricks-claude-sonnet-5
Monde
1M
$2$2
$10
$0.2
ReasoningToolsJSONCacheVisionWeb
Amazon Web ServicesOfficial−%amazon/anthropic.claude-sonnet-5
Monde
1M
$2$2
$10
$0.2
ReasoningToolsJSONCacheVisionWeb
Anthropic (États-Unis)Official−%anthropic/claude-sonnet-5
États-Unis
1M
$2$2
$10
$0.2
ReasoningToolsJSONCacheVisionWeb
Google CloudOfficial−%vertex/claude-sonnet-5
Monde
1M
$2$2
$10
$0.2
ReasoningToolsJSONCacheVisionWeb
Amazon Web Services (Europe)Official−%amazon/anthropic.claude-sonnet-5@eu
Europe
1M
$2.2$2.2
$11
$0.22
ReasoningToolsJSONCacheVisionWeb
Amazon Web Services (États-Unis)Official−%amazon/anthropic.claude-sonnet-5@us
États-Unis
1M
$2.2$2.2
$11
$0.22
ReasoningToolsJSONCacheVisionWeb
Google Cloud (Europe)Official−%vertex/claude-sonnet-5@eu
Europe
1M
$2.2$2.2
$11
$0.22
ReasoningToolsJSONCacheVisionWeb
Google Cloud (États-Unis)Official−%vertex/claude-sonnet-5@us
États-Unis
1M
$2.2$2.2
$11
$0.22
ReasoningToolsJSONCacheVisionWeb
DeepInfra (États-Unis)Official−%deepinfra/anthropic/claude-sonnet-5
États-Unis
1M
$3$3
$15
$
ReasoningToolsJSONCacheVisionWeb

Performance

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

Fastest first token
1.5 s
Google Cloud
Lowest latency
2.04 s
Databricks (Europe)
Highest throughput
77.69 tok/s
Google Cloud (Europe)
Best availability
100%
Databricks (Europe)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Databricks (Europe)
3.33 s
2.04 s
20.6 s
40.63 tok/s
100%
37.34%
3.13%
0%
Databricks
3.66 s
2.56 s
15.22 s
4.51 tok/s
100%
74.62%
20.9%
0%
Amazon Web Services
1.78 s
4.89 s
42.72 s
63.26 tok/s
99.16%
90.79%
0.85%
5.56%
Anthropic (États-Unis)
2.14 s
4.45 s
47.69 s
71.46 tok/s
99.9%
87.11%
0.1%
0%
Google Cloud
1.5 s
3.2 s
40.71 s
63.52 tok/s
100%
75.5%
1.25%
8.81%
Amazon Web Services (Europe)
1.71 s
4.96 s
40.39 s
65.18 tok/s
99.18%
92.14%
0.78%
5.71%
Amazon Web Services (États-Unis)
2.19 s
2.21 s
25.84 s
15.11 tok/s
50%
95.9%
88.24%
0%
Google Cloud (Europe)
2.58 s
8.47 s
76.96 s
77.69 tok/s
100%
14.84%
2.11%
7.59%
Google Cloud (États-Unis)
s
s
s
tok/s
%
%
%
%
DeepInfra (États-Unis)
s
s
s
tok/s
%
%
%
%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call Claude Sonnet 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 5

On Eden AI, prices for this model start at $2 per million input tokens and $10 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

Up to 1M tokens, depending on the endpoint.

10 endpoints from 5 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 1.5 s (Google Cloud) and the highest throughput was 77.69 tokens per second (Google Cloud (Europe)).