Claude Haiku 5.5
Save 70%Officialanthropic/claude-haiku-5-5
Anthropic's latest Haiku — the fastest model in its current lineup, built for high-volume classification, extraction and routing.
- Context window
- 1M
- Max output
- 128K
- Input modalities
- text · image
- Output modalities
- text
- Capabilities
- Vision · Reasoning · Tool calling · Coding · Prompt cache · Paid cache writes
- Upstream release
- 2026-10-07
- RouteMux name
- anthropic/claude-haiku-5-5
Try Claude Haiku 5.5 here
Tune the request, see the current price ceiling, and inspect the real response without leaving this model page.
Sign in first to upload images to this vision model.
Your result will appear here
Enter an input on the left. The same RouteMux Playground execution and billing path powers this embedded test.
What is Claude Haiku 5.5
Claude Haiku 5.5 is Anthropic's newest Haiku, released on October 7, 2026 as the successor to Claude Haiku 4.5. Anthropic builds it for high-volume, latency-sensitive work such as classification, routing, extraction and sub-agent tasks, and lists it as the fastest model in its current lineup. It carries a 1M-token context window and up to 128K output tokens, takes image input, and runs adaptive thinking by default at a default effort of "medium."
Anthropic prices Haiku 5.5 by prompt length, and RouteMux follows the same two tiers. For prompts up to 100K tokens it costs $0.03 per 1M input tokens against Anthropic's $0.10, and $0.15 per 1M output against $0.50. When a prompt goes over 100K tokens, the whole request moves to the higher tier: $0.15 input and $0.75 output per 1M, against Anthropic's $0.50 and $2.50. Prompt caching follows the same split; up to 100K, cache reads are $0.003 per 1M tokens and writes are $0.0375 (5-minute) or $0.06 (1-hour). Failed and timed-out requests are not billed.
Moving over from Haiku 4.5 is more than a model-name change: Anthropic lists several request shapes that Haiku 4.5 accepted and Haiku 5.5 rejects. They are covered in the FAQ below.
Claude Haiku 5.5 API pricing
Prices verified 2026-10-10
Cache read $0.003/M · Cache write $0.0375/M
| Tier | Input | Cache read | Cache write | Output |
|---|---|---|---|---|
| Standard ≤100K | $0.03 | $0.003 | $0.0375 | $0.15 |
| Standard >100K | $0.15 | $0.015 | $0.1875 | $0.75 |
Estimate cost
Limited time10% extra Credits on your first top-up — up to 200 bonus Credits
Applies to your first top-up within 72 hours of signing up. Minimum $20, once per account.
Key capabilities
Fastest in Anthropic's lineup
Anthropic rates Haiku 5.5 the fastest current Claude model and positions it for classification, routing, extraction and sub-agent work.
Two price tiers by prompt length
$0.03 / 1M input and $0.15 / 1M output up to 100K prompt tokens; $0.15 and $0.75 above that.
1M-token context, 128K output
Up from Haiku 4.5's 200K context — though prompts past 100K tokens are billed at the higher tier.
Adaptive thinking, steered by effort
Thinking is on by default at medium effort. Anthropic suggests low for chat and simple high-volume requests, and high for knowledge work and strict instruction following.
Interface and protocols
Use any of these IDs to call this model via the API.
anthropic/claude-haiku-5-5Replace the ROUTEMUX_KEY placeholder with your API key. Create one →
from anthropic import Anthropic
client = Anthropic(
base_url="https://api.routemux.com/anthropic",
api_key="<ROUTEMUX_KEY>",
)
message = client.messages.create(
model="anthropic/claude-haiku-5-5",
max_tokens=1024,
messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(message.content[0].text)Performance (last 30 days)
Claude Haiku 5.5 FAQ
›What is Claude Haiku 5.5?
Anthropic's latest Haiku — the fastest model in its current lineup, built for high-volume classification, extraction and routing.
›How large is the context window of Claude Haiku 5.5?
Claude Haiku 5.5 supports a context window of up to 1M tokens, with up to 128K output tokens per request.
›How much does the Claude Haiku 5.5 API cost?
Through RouteMux, Claude Haiku 5.5 costs $0.03 for input and $0.15 for output (USD per 1M tokens), below the official list price.
›How do I call Claude Haiku 5.5 via API?
Claude Haiku 5.5 is OpenAI-compatible: point your base URL at RouteMux and set the model field to anthropic/claude-haiku-5-5 — no code changes needed.
›Which input and output modalities does Claude Haiku 5.5 support?
Claude Haiku 5.5 accepts text, image as input and produces text as output.
›When was Claude Haiku 5.5 released?
Claude Haiku 5.5 was released on October 7, 2026.
›Is this the same Claude Haiku 5.5 as Anthropic's?
Yes — same model, same Anthropic Messages API surface. RouteMux routes your request through and bills your prepaid wallet instead of an Anthropic account.
›How is the 100K tier decided?
Per request, by the size of its prompt. RouteMux adds up uncached input tokens, cache reads and cache writes; if the total is over 100,000 tokens, every part of that request — input, output and cache — is billed at the higher tier.
›What breaks when I switch from Haiku 4.5?
Per Anthropic: a manual thinking budget (thinking type "enabled" with budget_tokens) now returns an error — use adaptive thinking and the effort parameter instead — and an assistant prefill (a final assistant message for the model to continue) is rejected. Non-default temperature, top_p and top_k are also rejected by Anthropic on this model; RouteMux drops those three parameters before forwarding, so SDKs that set them by default keep working. Thinking is now on by default, so a response can begin with a thinking block, and a small max_tokens can be used up by thinking before any text.
›Should I use Haiku 5.5 or Haiku 4.5?
Haiku 5.5 is Anthropic's current Haiku. Haiku 4.5 remains available if an existing integration relies on temperature, assistant prefill or budget_tokens and you cannot change that yet.
Sources
Reviewed by Jerry Fan on 2026-10-10