Claude Haiku 4.5
Model id: anthropic/claude-haiku-4-5
- Agentic
- Cost
- Fast
- Vision
Anthropic’s fast, economical Claude Haiku tier with strong near-frontier intelligence.
Best for
real-time apps, high-volume processing, and cost-sensitive sub-agents.
- Provider
- Anthropic
- Context window
- 200,000
- Release date
- 2025-10-15
Pricing
Web search
Billed on top of tokens when the model uses web search.
Amounts in Canadian dollars, converted at the Bank of Canada indicative rate (2026-11-06).
Performance
Reading
Last 7 days
Not enough data to display the chart.
- Time to first byte (p95)
- Not published
- Output speed (p95)
- 105.2 tok/s
- Samples
- 253 over 7 days
Measured on real traffic at Pass egress — not a synthetic benchmark.
Activity
Tokens
Top 5 tools · last 7 days
Tool activity appears only when at least 2 workspaces have used this model recently.
Availability
Availability (%)
Last 7 days
- Operational probes
- 99.97% over 7 days
- Samples
- 8,916
Quick start
Call the API with a tonia_ key and the exact model id below.
curl
curl https://pass.tonia.ca:8443/v1/chat/completions \
-H "Authorization: Bearer $TONIA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-haiku-4-5",
"messages": [
{
"role": "user",
"content": "Bonjour"
}
]
}'Python (OpenAI SDK)
import os
from openai import OpenAI
client = OpenAI(
base_url="https://pass.tonia.ca:8443/v1",
api_key=os.environ["TONIA_API_KEY"],
)
response = client.chat.completions.create(
model="anthropic/claude-haiku-4-5",
messages=[{"role": "user", "content": "Bonjour"}],
)TypeScript (OpenAI SDK)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://pass.tonia.ca:8443/v1",
apiKey: process.env.TONIA_API_KEY,
});
const response = await client.chat.completions.create({
model: "anthropic/claude-haiku-4-5",
messages: [{ role: "user", content: "Bonjour" }],
});With the Anthropic API (/v1/messages), Claude models are used without the anthropic/ prefix.