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
Global, Europe, United States

About Claude Sonnet 5

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.

Claude Sonnet 5 is a chat model by Anthropic, available on Eden AI through 10 endpoints from 5 providers, from $2 per million input tokens and $10 per million output tokens, with a context window of up to 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
Global
1M
$2$2
$10
$0.2
ReasoningToolsJSONCacheVisionWeb
Amazon Web ServicesOfficial−%amazon/anthropic.claude-sonnet-5
Global
1M
$2$2
$10
$0.2
ReasoningToolsJSONCacheVisionWeb
AnthropicOfficial−%anthropic/claude-sonnet-5
Global
1M
$2$2
$10
$0.2
ReasoningToolsJSONCacheVisionWeb
Google CloudOfficial−%vertex/claude-sonnet-5
Global
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 (United States)Official−%amazon/anthropic.claude-sonnet-5@us
United States
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 (United States)Official−%vertex/claude-sonnet-5@us
United States
1M
$2.2$2.2
$11
$0.22
ReasoningToolsJSONCacheVisionWeb
DeepInfra (United States)Official−%deepinfra/anthropic/claude-sonnet-5
United States
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
1.72 s
Anthropic
Lowest latency
3.65 s
Anthropic
Highest throughput
74.44 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)
3.25 s
4.9 s
23.98 s
52.59 tok/s
100%
2.42%
28.32%
0%
Databricks
3.28 s
4.16 s
20.6 s
41.51 tok/s
100%
15.16%
30.06%
0%
Amazon Web Services
1.83 s
4.98 s
41.33 s
61.72 tok/s
99.69%
91.22%
0.38%
3.85%
Anthropic
1.72 s
3.65 s
35.85 s
65.52 tok/s
99.94%
91.18%
0.07%
0.97%
Google Cloud
2.66 s
4.86 s
50.4 s
65.55 tok/s
100%
79.68%
2.95%
17.94%
Amazon Web Services (Europe)
1.8 s
5.02 s
39.81 s
62.93 tok/s
99.76%
92.14%
0.3%
5.48%
Amazon Web Services (United States)
3.43 s
3.69 s
25.84 s
26.81 tok/s
61.29%
94.26%
83.33%
0%
Google Cloud (Europe)
3.46 s
9.7 s
76.96 s
74.44 tok/s
100%
8.76%
7.39%
12.26%
Google Cloud (United States)
s
s
s
tok/s
%
%
%
%
DeepInfra (United States)
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: Global, Europe, United States. 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 1.72 s (Anthropic) and the highest throughput was 74.44 tokens per second (Google Cloud (Europe)).