claude-haiku-4-5Claude Haiku 4.5 is Anthropic's fastest near-frontier model, supporting 200K context, 64K max output, and extended thinking for low-latency, high-volume use. Di Hostlinku: Performance mulai 0.88/1M input · Low-Cost mulai 0.177/1M input. Harga Original $1/1M input.
Hostlinku price · per 1M token
PerformancePerformance · Hemat hingga 50% · Kualitas & stabilitas terbaik
Input
/ 1M token
Output
/ 1M token
Cache read
per 1M token
0.088
$0.10Cache write (5m)
per 1M token
1.1
$1.25Cache write (1h)
per 1M token
1.76
$2Web search
per 1K calls
11
$10Billing dalam (1 = $1). Coret = harga resmi vendor (hanya bila harga lebih murah). Service Mode dipilih per API key.
Dapatkan API Key + freeContext window
200.0K
200,000 tokens
Max output
64.0K
64,000 tokens
7-day uptime
100.00%
180 probes · 0 failed
Measured throughput
32.2 tok/s
Real traffic, last 7 days · output side · 5.93s avg
What this model can do through the Hostlinku gateway.
Vision
Reads images, screenshots, and diagrams alongside text. Send image inputs directly in the messages payload.
Function calling
The model calls tools you define and folds their results into the reply. Required for agentic workflows and multi-step automation.
Reasoning
Prompt caching
Response schema
Guarantees JSON output that matches a schema you provide. No brittle post-parsing on your side.
Streaming
Streams tokens as they are generated for real-time UX. Supported on every Hostlinku protocol.
Web search
Audio
Video
File input
Realtime
Session
Media
Multipart form
Binary response
Hostlinku probes this model on a schedule: measured, not self-reported.
100.00%
180 probes in 7 days, 0 failed · automatic failover to backup channels
Latency diukur dari probe terjadwal melalui supply chain nyata; throughput dari traffic user 7 hari terakhir (sisi output).
Swap the base URL and everything else stays the same. Native protocols pass through, adapted protocols are translated by the Hostlinku gateway.
curl https://api.hostlinku.com/v1/messages \
-H "x-api-key: $HOSTLINKU_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "content-type: application/json" \
-d '{
"model": "claude-haiku-4-5",
"max_tokens": 1024,
"messages": [
{ "role": "user", "content": "Explain edge failover in one paragraph." }
]
}'Setiap dimensi yang ditagih, dengan harga resmi vendor (dicoret bila lebih mahal) di sebelah harga per Service Mode.
| Item | Unit | Original ($) | Performance () | Low-Cost () | Dedicated () |
|---|---|---|---|---|---|
| Input (prompt) | per 1M tokens | $1 | 0.88 | 0.177 | — |
| Output (completion) | per 1M tokens | $5 | 4.4 | 0.885 | — |
| Cache read | per 1M tokens | $0.10 | 0.088 | 0.0177 | — |
| Cache write (5m) | per 1M tokens | $1.25 | 1.1 | 0.2213 | — |
| Cache write (1h) | per 1M tokens | $2 | 1.76 | 0.354 | — |
| Web search | per 1K calls | $10 | 11 | 11.8 | — |
Harga resmi vendor dicoret bila setidaknya satu Service Mode lebih murah. Dimensi tanpa coretan (mis. web search) tidak didiskon upstream. 1 = $1.
Model lain dari vendor yang sama, dengan harga dan konteks pembanding.
Pertanyaan umum soal Claude Haiku 4.5: harga, kapabilitas, dan cara mengukurnya.
Anthropic
Satu API key untuk semua model. Ganti base URL, pakai SDK yang sudah kamu gunakan sekarang, dan bayar per token dalam (1 = $1). Pilih Service Mode Performance atau Low-Cost per API key.