claude-haiku-5-5
claude-haiku-5-5Samples: 1
Anthropic Haiku 5.5, the fast low-cost Claude for high-volume, routing and sub-agent work. 1M context, 128K output. Prompts over 100K tokens are billed on the long-context rate card ($0.50 / $2.50 per 1M input / output tokens).
- Input / 1M tokens
- $0.06–$0.15
- Output / 1M tokens
- $0.3–$0.75
- Context window
- 1,000,000
- Route
- claude_plusPlus routes
Variable pricing
Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.
Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.
LiveBench · Story constraint following
claude-haiku-5-5-xhigh-effort: 73.6
claude-haiku-5-5-max-effort: 64.53
71 Models · 2026-10-25
LiveBench · Theory of mind
claude-haiku-5-5-xhigh-effort: 76.92
claude-haiku-5-5-max-effort: 86.54
71 Models · 2026-10-25
Routes
Ability score divided by token cost, ranked across measured model routes. Cost uses equal input and output token counts; higher is better value.
| Use this model | ||||||
|---|---|---|---|---|---|---|
| claude_official | $0.24–$0.6 | $1.2–$3 | $0.024–$0.06 | 6.9/10 | Not measured | Plans and tiers |
| claude_plus | $0.06–$0.15 | $0.3–$0.75 | $0.006–$0.015 | 6.9/10 | Not measured | Plans and tiers |
| claude_sales | $0.06–$0.15 | $0.3–$0.75 | $0.006–$0.015 | 6.9/10 | Not measured | Plans and tiers |
| devin | $0.1–$0.25 | $0.5–$1.25 | $0.01–$0.025 | 6.9/10 | Not measured | Plans and tiers |
devinQuick start
Access and billingcurl --fail-with-body 'https://api.tokenreply.com/v1/chat/completions' \
-H "Authorization: Bearer $TOKENREPLY_API_KEY" \
-H 'Content-Type: application/json' \
--data '{
"model": "claude-haiku-5-5",
"messages": [
{
"role": "user",
"content": "Reply with hello."
}
]
}'