~claude Haiku Latest

~claude-haiku-latest by Anthropic Released October 8, 2026
Reasoning · Function calling · Structured output · Prompt caching · Web search · Computer use · Image input · File input · EU hosting
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
Global, Europe, United States

About ~claude Haiku Latest

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.

~claude Haiku Latest is a chat model by Anthropic, available on Eden AI through 9 endpoints from 4 providers, from $0.1 per million input tokens and $0.5 per million output tokens, with a context window of up to 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. Above 100K tokens: $0.5 input / $2.5 output per 1M.

Endpoint
Region
Context
Input / 1M
Output / 1M
Cached / 1M
Supports
Databricks (Europe)databricks/databricks-claude-haiku-5-5@eu
Europe
1M
$0.1
$0.5
$0.01
Reasoning · Tools · Cache · Vision
Databricksdatabricks/databricks-claude-haiku-5-5
Global
1M
$0.1
$0.5
$0.01
Reasoning · Tools · Cache · Vision
Amazon Web Servicesamazon/anthropic.claude-haiku-5-5
Global
1M
$0.1
$0.5
$0.01
Reasoning · Tools · JSON · Cache · Vision
Anthropic (United States)anthropic/claude-haiku-5-5
United States
1M
$0.1
$0.5
$0.01
Official · Reasoning · Tools · JSON · Cache · Vision · Web
Google Cloudvertex/claude-haiku-5-5
Global
1M
$0.1
$0.5
$0.01
Reasoning · Tools · JSON · Cache · Vision · Web
Amazon Web Services (Europe)amazon/anthropic.claude-haiku-5-5@eu
Europe
1M
$0.11
$0.55
$0.011
Reasoning · Tools · JSON · Cache · Vision
Amazon Web Services (United States)amazon/anthropic.claude-haiku-5-5@us
United States
1M
$0.11
$0.55
$0.011
Reasoning · Tools · JSON · Cache · Vision
Google Cloud (Europe)vertex/claude-haiku-5-5@eu
Europe
1M
$0.11
$0.55
$0.011
Reasoning · Tools · JSON · Cache · Vision · Web
Google Cloud (United States)vertex/claude-haiku-5-5@us
United States
1M
$0.11
$0.55
$0.011
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
1.01 s
Databricks (Europe)
Lowest latency
1.87 s
Amazon Web Services (Europe)
Highest throughput
197.06 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
Databricks (Europe)
1.01 s
2.02 s
3.99 s
110.95 tok/s
100%
0.53%
2.01%
0%
Databricks
1.05 s
1.99 s
4.05 s
109.14 tok/s
100%
0.4%
5.02%
47.06%
Amazon Web Services
2.05 s
1.9 s
8.31 s
99.03 tok/s
100%
73.45%
0.11%
2.72%
Anthropic (United States)
2.6 s
3.21 s
22.95 s
150.36 tok/s
99.92%
63.67%
2.03%
0.21%
Google Cloud
1.27 s
3.72 s
24.9 s
194.83 tok/s
99.99%
74.31%
0.22%
0.16%
Amazon Web Services (Europe)
2.03 s
1.87 s
7.92 s
98.53 tok/s
100%
71.67%
0.06%
2.73%
Amazon Web Services (United States)
1.03 s
5.41 s
7.06 s
96.46 tok/s
100%
11.4%
0%
0%
Google Cloud (Europe)
1.29 s
3.9 s
25 s
197.06 tok/s
100%
69.44%
0.18%
0.1%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

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

Questions about ~claude Haiku Latest

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. Above 100K tokens: $0.5 input / $2.5 output per 1M.

Up to 1M tokens, depending on the endpoint.

9 endpoints from 4 providers, available in: Global, Europe, United States. All of them are called with the same Eden AI API key.

Can I run ~claude Haiku 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 Haiku Latest? Over the last 30 days, the fastest first token was 1.01 s (Databricks (Europe)) and the highest throughput was 197.06 tokens per second (Google Cloud (Europe)).