Anthropic language model
Claude Haiku 5.5
Anthropic's small Claude model, with adaptive thinking, image input and a 1M-token context. it is the low-cost tier below Sonnet 5.5, priced at a tenth of Haiku 4.5's rates for prompts up to 100K tokens.
01
price
input tokens
output tokens
cached input
per 1M tokens. octomind bills the listed provider price, with no markup, on every plan, including the free one (pay as you go from credits).
- every rate rises 5x once a prompt passes 100K tokens, counting cache reads and writes; the listed price is the sub-100K rate.
- cache writes bill at $0.125 and cache hits at $0.01 per 1M tokens below 100K prompt tokens.
- its tokenizer counts the same text as about 30% more tokens than Claude Haiku 4.5.
02
what real work costs
| workload | cost |
|---|---|
| one chat reply 3,000 tokens in, 500 out | $0.00055 |
| summarise a 100-page report 50,000 tokens in, 1,500 out, one request | $0.0058 |
| 1,000 classification calls 500 tokens in, 20 out, per call | $0.06 |
| coding-agent session 2M tokens in across ~60 turns, 60,000 out, no cache | $0.23 |
| same session, cached 85% of input read from the prompt cache, the rest written to it | $0.08 |
at the listed rate. token counts are typical sizes, not measurements.
03
specs
- provider
- Anthropic
- context window
- 1M tokens — ≈ 1,500 pages of prose or 100,000 lines of code
- max output
- 128k tokens
- input
- text, images
- output
- text
- structured output
- yes — JSON schema
- reasoning mode
- yes
- prompt caching
- yes — cache hits at $0.01/M
- weights
- closed
- released
- October 7, 2026
- knowledge cutoff
- June 2026
- status
- live
- model id
claude-haiku-5-5
integration notes
- omit temperature, top_p and top_k; thinking with budget_tokens returns a 400 error, so use adaptive thinking steered by the effort parameter.
- assistant prefill is rejected with a 400 error even with thinking off; end messages with a user turn.
- adaptive thinking is on by default and its tokens count toward max_tokens, so a small max_tokens can stop before any text.
04
benchmarks
as published by the maker; not measured by octomind.
05
when to pick it
pick it if
- you run high-volume classification, extraction, routing or subagent tasks
- your prompts stay under 100K tokens, where every rate is lowest
- you resend long prompts, so cache hits bill at a tenth of input
skip it if
- you need complex agentic coding; Anthropic points to Sonnet 5.5 or Opus 5.5
- your prompts routinely pass 100K tokens, where every rate is 5x
06
where it sits on price
blended price $0.2/M at 3 input tokens per output token: 5 live language models cost less, 38 cost more.
- MiMo V2.6 Flash $0.175/M
- Beam $0.194/M
- Claude Haiku 5.5 $0.2/M
- Gemma 4 31B $0.2/M
- GPT-6 Luna $0.2/M
07
use Claude Haiku 5.5 in octomind
one octohub login reaches every model in the catalog. pick this one per run, per session, or as your default.
octomind login
octomind run -m octohub:claude-haiku-5-5/model octohub:claude-haiku-5-5[model]
name = "octohub:claude-haiku-5-5"08
compare Claude Haiku 5.5
- Claude Haiku 5.5 vs GPT-6 Luna
- Claude Haiku 5.5 vs Claude Sonnet 5.5
- Mercury 3 vs Claude Haiku 5.5
- Beam vs Claude Haiku 5.5
09
similar models
nearest live models by listed input price.
- GPT-6 Luna $0.1/M input
- Mercury 3 $0.1/M input
- Muse Spark 1.3 Contributor $0.1/M input
- Beam $0.125/M input
10
Claude Haiku 5.5 faq
how much does Claude Haiku 5.5 cost?
Claude Haiku 5.5 lists at $0.1/M input, $0.5/M output, $0.01/M cached input per 1M tokens. a typical coding-agent session (2M tokens in, 60,000 out) comes to $0.23, or $0.08 when 85% of the input is read from the prompt cache. octomind bills the listed provider price, with no markup, on every plan, including the free one (pay as you go from credits).
what is the context window of Claude Haiku 5.5?
1M tokens, ≈ 1,500 pages of prose or 100,000 lines of code. a single reply can run to 128k tokens.
does Claude Haiku 5.5 accept images?
yes. it takes text and images as input and returns text.
is Claude Haiku 5.5 open source?
no. Claude Haiku 5.5 is a closed-weights model, available only through Anthropic's api and hosted gateways such as octohub.
when was Claude Haiku 5.5 released?
October 7, 2026, by Anthropic.
is Claude Haiku 5.5 free?
no. Claude Haiku 5.5 bills per token at $0.1/M input, $0.5/M output, $0.01/M cached input per 1M. octomind's free plan reaches it pay as you go from credits, so you pay only for the tokens you use, at the provider price. credits carry a 3% top-up fee.
how do i use Claude Haiku 5.5 in octomind?
run octomind login once, then octomind run -m octohub:claude-haiku-5-5. inside a running session, /model octohub:claude-haiku-5-5 switches to it without losing context.
use Claude Haiku 5.5 in octomind
choose a model when you start, then switch mid-session when the work changes.