Claude Haiku 4 5 (2025-10-01)

claude-haiku-4-5-20251001 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
4
from 2 providers
Regions
Monde, Europe, États-Unis

About Claude Haiku 4 5 (2025-10-01)

Claude Haiku 4.5 est le modèle le plus rapide et le plus efficace d'Anthropic ; il offre des performances proches de la pointe de la technologie, pour un coût et une latence bien inférieurs à ceux des modèles Claude de plus grande envergure.

Claude Haiku 4 5 (2025-10-01) est un modèle conversationnel développé par Anthropic, disponible sur Eden AI via 4 endpoints chez 2 fournisseurs, à partir de 1 $ par million de tokens en entrée et 5 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 200K tokens.

Providers and prices

4 endpoints from 2 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
Amazon Web ServicesOfficial−%amazon/anthropic.claude-haiku-4-5-20251001-v1:0
Monde
200K
$1$1
$5
$0.1
ReasoningToolsJSONCacheVisionWeb
Anthropic (États-Unis)Official−%anthropic/claude-haiku-4-5-20251001
États-Unis
200K
$1$1
$5
$0.1
ReasoningToolsJSONCacheVisionWeb
Amazon Web Services (Europe)Official−%amazon/anthropic.claude-haiku-4-5-20251001-v1:0@eu
Europe
200K
$1.1$1.1
$5.5
$0.11
ReasoningToolsJSONCacheVisionWeb
Amazon Web Services (États-Unis)Official−%amazon/anthropic.claude-haiku-4-5-20251001-v1:0@us
États-Unis
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
0.69 s
Anthropic (États-Unis)
Lowest latency
1.55 s
Anthropic (États-Unis)
Highest throughput
75.76 tok/s
Amazon Web Services (Europe)
Best availability
99.99%
Anthropic (États-Unis)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Amazon Web Services
0.87 s
1.63 s
6.69 s
75.54 tok/s
98.46%
83.42%
0.73%
13.64%
Anthropic (États-Unis)
0.69 s
1.55 s
2.89 s
52.91 tok/s
99.99%
0.29%
0%
0%
Amazon Web Services (Europe)
0.87 s
1.63 s
6.69 s
75.76 tok/s
98.44%
83.84%
0.69%
42.86%
Amazon Web Services (États-Unis)
s
s
s
tok/s
%
%
%
%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call Claude Haiku 4 5 (2025-10-01) 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 (2025-10-01)

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.

4 endpoints from 2 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 0.69 s (Anthropic (États-Unis)) and the highest throughput was 75.76 tokens per second (Amazon Web Services (Europe)).