~claude Opus Latest

~claude-opus-latest by Anthropic Released September 23, 2026
Reasoning · Function calling · Structured output · Prompt caching · Web search · Computer use · Image input · File input · EU hosting
Input from
$4 / 1M
Output from
$20 / 1M
Cached input from
$0.2 / 1M
Context window
1M
Endpoints
10
from 5 providers
Regions
Global, Europe, United States

About ~claude Opus Latest

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.

~claude Opus Latest is a chat model by Anthropic, available on Eden AI through 10 endpoints from 5 providers, from $4 per million input tokens and $20 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)databricks/databricks-claude-opus-5-5@eu
Europe
1M
$4
$20
$0.4
Reasoning · Tools · Cache · Vision
Databricksdatabricks/databricks-claude-opus-5-5
Global
1M
$4
$20
$0.4
Reasoning · Tools · Cache · Vision
DeepInfra (United States)deepinfra/anthropic/claude-opus-5-5
United States
1M
$4
$20
$0.2
Reasoning · Tools · JSON · Cache · Vision
Amazon Web Servicesamazon/anthropic.claude-opus-5-5
Global
1M
$4
$20
$0.2
Reasoning · Tools · JSON · Cache · Vision
Anthropic (United States)anthropic/claude-opus-5-5
United States
1M
$4
$20
$0.2
Official · Reasoning · Tools · JSON · Cache · Vision · Web
Google Cloudvertex/claude-opus-5-5
Global
1M
$4
$20
$0.2
Reasoning · Tools · JSON · Cache · Vision · Web
Amazon Web Services (Europe)amazon/anthropic.claude-opus-5-5@eu
Europe
1M
$4.4
$22
$0.22
Reasoning · Tools · JSON · Cache · Vision
Amazon Web Services (United States)amazon/anthropic.claude-opus-5-5@us
United States
1M
$4.4
$22
$0.22
Reasoning · Tools · JSON · Cache · Vision
Google Cloud (Europe)vertex/claude-opus-5-5@eu
Europe
1M
$4.4
$22
$0.22
Reasoning · Tools · JSON · Cache · Vision · Web
Google Cloud (United States)vertex/claude-opus-5-5@us
United States
1M
$4.4
$22
$0.22
Reasoning · Tools · JSON · Cache · Vision · Web

Performance

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

Fastest first token
1.57 s
Google Cloud (Europe)
Lowest latency
1.82 s
Databricks (Europe)
Highest throughput
93.74 tok/s
Google Cloud (Europe)
Best availability
100%
Amazon Web Services (United States)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Databricks (Europe)
1.83 s
1.82 s
37.88 s
7.28 tok/s
99.71%
74.61%
1.01%
100%
Databricks
2.7 s
4 s
25.86 s
43.18 tok/s
99.88%
27.19%
9.87%
5.65%
DeepInfra (United States)
3.58 s
4.48 s
29.77 s
51.25 tok/s
99.99%
0%
4.35%
0%
Amazon Web Services
4.23 s
5.07 s
43.68 s
68.62 tok/s
98.1%
88.08%
1.7%
0.16%
Anthropic (United States)
3.96 s
6.84 s
94.79 s
83.77 tok/s
97.64%
79.09%
3.6%
0.24%
Google Cloud
1.61 s
4.22 s
66.19 s
83.51 tok/s
99.93%
91.57%
0.72%
1.79%
Amazon Web Services (Europe)
4.04 s
6.05 s
57.4 s
80.23 tok/s
97.16%
86.54%
3.01%
0.43%
Amazon Web Services (United States)
2.28 s
2.18 s
5.64 s
35.79 tok/s
100%
88.01%
0%
0%
Google Cloud (Europe)
1.57 s
6.34 s
90.31 s
93.74 tok/s
99.86%
94.97%
0.16%
0%
Google Cloud (United States)
2.41 s
2.93 s
91 s
67.31 tok/s
100%
90.67%
0%
0%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call ~claude Opus Latest 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": "~claude-opus-latest",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about ~claude Opus Latest

On Eden AI, prices for this model start at $4 per million input tokens and $20 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.

Can I run ~claude Opus Latest in the EU? 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. ‖ How fast is ~claude Opus Latest? Over the last 30 days, the fastest first token was 1.57 s (Google Cloud (Europe)) and the highest throughput was 93.74 tokens per second (Google Cloud (Europe)).