About Claude Haiku 5.5
Claude Haiku 5.5 is Anthropic's fast, low-cost Multimodal LLM for high-volume, latency-sensitive work. It suits classification, routing, extraction, and subagent tasks, and succeeds Claude Haiku 4.5 with a much larger context window and output limit at a lower price.
Adaptive thinking is on by default and steered by the effort parameter (low through max, default medium). Sampling parameters such as temperature are not supported. Its tokenizer counts the same text as about 30% more tokens than Claude Haiku 4.5's. Prompts over 100,000 tokens cost five times as much per token as shorter ones. Safety classifiers may decline requests in sensitive domains, returning a refusal stop reason. It accepts text and images and has a reliable knowledge cutoff of June 2026.
| Metric | Value |
|---|---|
| Context Length | 1,000,000 tokens |
| Max Output | 128,000 tokens |
| Multilingual | Yes |
Ready to build with Claude Haiku 5.5?
Try Claude Haiku 5.5 in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "claude-haiku-5-5",
"messages": [
{
"role": "user",
"content": "Try sending a message."
}
]
}'API endpoint
See the API reference for request and response formats.
https://hub.oxen.ai/api/ai/chat/completions