Claude Haiku 5.5

claude-haiku-5.5 by Anthropic Released October 8, 2026
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off
Input from
$0.1 / 1M
Output from
$0.5 / 1M
Cached input from
$0.01 / 1M
Context window
1M
Endpoints
9
from 4 providers
Regions
Monde, Europe, États-Unis

About Claude Haiku 5.5

Claude Haiku 5.5 est le modèle compact et rapide d'Anthropic, destiné aux tâches à fort volume et à coût maîtrisé, telles que la synthèse, les sous-agents et l'utilisation d'un navigateur.

Claude Haiku 5.5 est un modèle conversationnel développé par Anthropic, disponible sur Eden AI via 9 endpoints chez 4 fournisseurs, à partir de 0,1 $ par million de tokens en entrée et 0,5 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 1M tokens.

Providers and prices

9 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. Au-delà de 100K tokens : 0,5 $ en entrée / 2,5 $ en sortie par 1M.

Endpoint
Region
Context
Input / 1M
Output / 1M
Cached / 1M
Supports
Anthropic (États-Unis)Official−%anthropic/claude-haiku-5-5
États-Unis
1M
$0.1$0.1
$0.5
$0.01
ReasoningToolsJSONCacheVisionWeb
Google CloudOfficial−%vertex/claude-haiku-5-5
Monde
1M
$0.1$0.1
$0.5
$0.01
ReasoningToolsJSONCacheVisionWeb
Amazon Web ServicesOfficial−%amazon/anthropic.claude-haiku-5-5
Monde
1M
$0.1$0.1
$0.5
$0.01
ReasoningToolsJSONCacheVisionWeb
Databricks (Europe)Official−%databricks/databricks-claude-haiku-5-5@eu
Europe
1M
$0.1$0.1
$0.5
$0.01
ReasoningToolsJSONCacheVisionWeb
DatabricksOfficial−%databricks/databricks-claude-haiku-5-5
Monde
1M
$0.1$0.1
$0.5
$0.01
ReasoningToolsJSONCacheVisionWeb
Google Cloud (Europe)Official−%vertex/claude-haiku-5-5@eu
Europe
1M
$0.11$0.11
$0.55
$0.011
ReasoningToolsJSONCacheVisionWeb
Google Cloud (États-Unis)Official−%vertex/claude-haiku-5-5@us
États-Unis
1M
$0.11$0.11
$0.55
$0.011
ReasoningToolsJSONCacheVisionWeb
Amazon Web Services (Europe)Official−%amazon/anthropic.claude-haiku-5-5@eu
Europe
1M
$0.11$0.11
$0.55
$0.011
ReasoningToolsJSONCacheVisionWeb
Amazon Web Services (États-Unis)Official−%amazon/anthropic.claude-haiku-5-5@us
États-Unis
1M
$0.11$0.11
$0.55
$0.011
ReasoningToolsJSONCacheVisionWeb

Performance

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

Fastest first token
1.22 s
Anthropic (États-Unis)
Lowest latency
1.25 s
Amazon Web Services (États-Unis)
Highest throughput
292.61 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
Anthropic (États-Unis)
1.22 s
4.25 s
13.04 s
142.63 tok/s
100%
90.2%
0%
0.76%
Google Cloud
2.84 s
3.28 s
24.87 s
286.92 tok/s
99.99%
77.45%
0.13%
0%
Amazon Web Services
1.81 s
1.94 s
4.43 s
124.42 tok/s
100%
85.49%
1.06%
0%
Databricks (Europe)
2.67 s
3.1 s
35.72 s
138.55 tok/s
100%
0.13%
5%
0%
Databricks
2.67 s
2.94 s
35.72 s
132.67 tok/s
100%
0.12%
4.62%
0%
Google Cloud (Europe)
2.85 s
3.28 s
24.52 s
292.61 tok/s
99.99%
76.6%
0.11%
0%
Google Cloud (États-Unis)
s
s
s
tok/s
%
%
%
%
Amazon Web Services (Europe)
1.78 s
1.94 s
4.42 s
124.44 tok/s
100%
85.52%
1.1%
0%
Amazon Web Services (États-Unis)
1.32 s
1.25 s
1.6 s
9.33 tok/s
100%
0%
0%
0%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call Claude Haiku 5.5 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 5.5

On Eden AI, prices for this model start at $0.1 per million input tokens and $0.5 per million output tokens. Prices differ by endpoint; the providers table lists each one. Au-delà de 100K tokens : 0,5 $ en entrée / 2,5 $ en sortie par 1M.

Up to 1M tokens, depending on the endpoint.

9 endpoints from 4 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 1.22 s (Anthropic (États-Unis)) and the highest throughput was 292.61 tokens per second (Google Cloud (Europe)).