Claude Haiku 4.5

claude-haiku-4.5 by Anthropic Released October 16, 2025
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off
Input from
$1 / 1M
Output from
$5 / 1M
Cached input from
$0.1 / 1M
Context window
200K
Endpoints
7
from 4 providers
Regions
Global, Europe, United States

About Claude Haiku 4.5

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models.

Claude Haiku 4.5 is a chat model by Anthropic, available on Eden AI through 7 endpoints from 4 providers, from $1 per million input tokens and $5 per million output tokens, with a context window of up to 200K tokens.

Providers and prices

7 endpoints from 4 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
DeepInfra (United States)Official−%deepinfra/anthropic/claude-haiku-4-5
United States
200K
$1$1
$5
$
ReasoningToolsJSONCacheVisionWeb
Databricks (Europe)Official−%databricks/databricks-claude-haiku-4-5@eu
Europe
200K
$1$1
$5
$0.1
ReasoningToolsJSONCacheVisionWeb
DatabricksOfficial−%databricks/databricks-claude-haiku-4-5
Global
200K
$1$1
$5
$0.1
ReasoningToolsJSONCacheVisionWeb
AnthropicOfficial−%anthropic/claude-haiku-4-5
Global
200K
$1$1
$5
$0.1
ReasoningToolsJSONCacheVisionWeb
Google CloudOfficial−%vertex/claude-haiku-4-5
Global
200K
$1$1
$5
$0.1
ReasoningToolsJSONCacheVisionWeb
Google Cloud (Europe)Official−%vertex/claude-haiku-4-5@eu
Europe
200K
$1.1$1.1
$5.5
$0.11
ReasoningToolsJSONCacheVisionWeb
Google Cloud (United States)Official−%vertex/claude-haiku-4-5@us
United States
200K
$1.1$1.1
$5.5
$0.11
ReasoningToolsJSONCacheVisionWeb

Performance

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

Fastest first token
0.84 s
Databricks (Europe)
Lowest latency
1.04 s
Google Cloud (Europe)
Highest throughput
88.49 tok/s
Anthropic
Best availability
100%
DeepInfra (United States)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
DeepInfra (United States)
0.95 s
1.46 s
7.5 s
18.59 tok/s
100%
1.95%
5.26%
0%
Databricks (Europe)
0.84 s
1.33 s
8.18 s
76.66 tok/s
100%
13.1%
1.17%
0%
Databricks
0.88 s
1.81 s
9.15 s
77.31 tok/s
100%
10.29%
3.05%
0%
Anthropic
0.95 s
4.99 s
83.33 s
88.49 tok/s
99.94%
54.31%
2.53%
0%
Google Cloud
1.42 s
1.05 s
5.06 s
74.91 tok/s
99.99%
7.37%
0.05%
0.55%
Google Cloud (Europe)
1.4 s
1.04 s
4.98 s
76.63 tok/s
99.99%
7.41%
0.02%
0.56%
Google Cloud (United States)
s
s
s
tok/s
%
%
%
%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call Claude Haiku 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 Haiku 4.5

On Eden AI, prices for this model start at $1 per million input tokens and $5 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

Up to 200K tokens, depending on the endpoint.

7 endpoints from 4 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 0.84 s (Databricks (Europe)) and the highest throughput was 88.49 tokens per second (Anthropic).