Claude Opus 5

claude-opus-5 by Anthropic Released July 25, 2026
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off
Input from
$5 / 1M
Output from
$25 / 1M
Cached input from
$0.5 / 1M
Context window
1M
Endpoints
10
from 5 providers
Regions
Monde, Europe, États-Unis

About Claude Opus 5

Claude Opus 5 est le modèle phare d'Anthropic, conçu pour les tâches exigeantes de raisonnement, de programmation et de travail agentique à long terme.

Claude Opus 5 est un modèle conversationnel développé par Anthropic, disponible sur Eden AI via 10 endpoints chez 5 fournisseurs, à partir de 5 $ par million de tokens en entrée et 25 $ 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-opus-5@eu
Europe
1M
$5$5
$25
$0.5
ReasoningToolsJSONCacheVisionWeb
DatabricksOfficial−%databricks/databricks-claude-opus-5
Monde
1M
$5$5
$25
$0.5
ReasoningToolsJSONCacheVisionWeb
DeepInfra (États-Unis)Official−%deepinfra/anthropic/claude-opus-5
États-Unis
1M
$5$5
$25
$
ReasoningToolsJSONCacheVisionWeb
Amazon Web ServicesOfficial−%amazon/anthropic.claude-opus-5
Monde
1M
$5$5
$25
$0.5
ReasoningToolsJSONCacheVisionWeb
Anthropic (États-Unis)Official−%anthropic/claude-opus-5
États-Unis
1M
$5$5
$25
$0.5
ReasoningToolsJSONCacheVisionWeb
Google CloudOfficial−%vertex/claude-opus-5
Monde
1M
$5$5
$25
$0.5
ReasoningToolsJSONCacheVisionWeb
Amazon Web Services (Europe)Official−%amazon/anthropic.claude-opus-5@eu
Europe
1M
$5.5$5.5
$27.5
$0.55
ReasoningToolsJSONCacheVisionWeb
Amazon Web Services (États-Unis)Official−%amazon/anthropic.claude-opus-5@us
États-Unis
1M
$5.5$5.5
$27.5
$0.55
ReasoningToolsJSONCacheVisionWeb
Google Cloud (Europe)Official−%vertex/claude-opus-5@eu
Europe
1M
$5.5$5.5
$27.5
$0.55
ReasoningToolsJSONCacheVisionWeb
Google Cloud (États-Unis)Official−%vertex/claude-opus-5@us
États-Unis
1M
$5.5$5.5
$27.5
$0.55
ReasoningToolsJSONCacheVisionWeb

Performance

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

Fastest first token
1.39 s
Amazon Web Services (Europe)
Lowest latency
2.61 s
Databricks (Europe)
Highest throughput
71.03 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)
2.55 s
2.61 s
42.73 s
50.86 tok/s
100%
0.71%
0%
0%
Databricks
3.83 s
3.78 s
44.94 s
49.95 tok/s
99.54%
0.44%
2.7%
0%
DeepInfra (États-Unis)
s
s
s
tok/s
%
%
%
%
Amazon Web Services
1.4 s
5.61 s
48.99 s
68.93 tok/s
99.97%
92.44%
0.03%
0%
Anthropic (États-Unis)
2.49 s
6.07 s
39.87 s
62.06 tok/s
99.93%
93.09%
0.05%
0.02%
Google Cloud
6.26 s
9.33 s
76.11 s
71.03 tok/s
99.7%
64.11%
0.33%
0%
Amazon Web Services (Europe)
1.39 s
5.59 s
47.98 s
69.01 tok/s
99.97%
92.62%
0.03%
0%
Amazon Web Services (États-Unis)
s
s
s
tok/s
%
%
%
%
Google Cloud (Europe)
4.91 s
7.42 s
91.41 s
69.59 tok/s
99.54%
39.59%
0.52%
0%
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 Opus 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 Opus 5

On Eden AI, prices for this model start at $5 per million input tokens and $25 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 1.39 s (Amazon Web Services (Europe)) and the highest throughput was 71.03 tokens per second (Google Cloud).