LLM

Claude Haiku 5.5

by Anthropic

Prices last updated November 22, 2026

Anthropic's Claude Haiku 5.5 (October 2026) — its fastest, cheapest model for high-volume work such as classification, extraction, routing and subagents, with a 1M-token context window and vision input.

Context
1M
Max Output
128k
Providers
7
Cheapest Input
$0.060
Vision Function Calling JSON Mode Streaming Chat / InstructVision

Price Comparison

Compare pricing across 7 providers serving Claude Haiku 5.5

Provider Input $/1M Output $/1M Context Speed TTFT Status
KIE AI
KIE AI
$0.060 ● $0.300 — — — Live
OpenRouter
OpenRouter
$0.100 $0.500 1M — — Live
Venice AI
Venice AI
$0.100 $0.500 1M — — Live
WaveSpeed AI
WaveSpeed AI
$0.100 $0.500 1M — — Live
Infron
Infron
$0.100 $0.500 1M — — Live
Anthropic
Anthropic
$0.100 $0.500 — — — Live
Token Harbor
Token Harbor
$0.100 $0.500 1M — — Live
● Cheapest ● Fastest Prices in USD per 1M tokens

Benchmarks

Independent results for Claude Haiku 5.5, as each source publishes them. Where a source tested several versions (effort levels, thinking modes, dated snapshots), the best one is shown and named under "As tested". Scores from different sources use different scales and aren't comparable with each other.

BenchmarkScoreRankAs tested
Overall
One score combining a model's results across many benchmarks, on a common scale.
160.3±2.3
#20 of 258
Claude Haiku 5.5
Reasoning
GPQA DiamondEpoch AI
Graduate-level multiple-choice questions in biology, physics and chemistry, written to be hard to look up.
89.7%±3.9
#56 of 232
claude-haiku-5-5_max
Oct 2026
Math
Unpublished research-level maths problems with automatically checkable answers.
75.1%±5.0
#27 of 95
claude-haiku-5-5_max
Oct 2026
FrontierMath's hardest tier: problems that take specialist mathematicians days.
46.3%±15.5
#28 of 77
claude-haiku-5-5_max
Oct 2026
Competition maths problems from the OTIS mock AIME exams (2024-2025).
98.9%±1.0
#28 of 215
claude-haiku-5-5_xhigh
Oct 2026
Coding
Text Arena votes on coding prompts only.
1,487±10
4,142 votes
#108 of 421
Claude Haiku 5.5 (High)
Nov 2026
Human votes on web apps the models build from a prompt.
1,595±8
8,448 votes
#44 of 161
Claude Haiku 5.5 (High)
Nov 2026
Knowledge
Short factual questions answered without search, measuring what the model knows and whether it makes things up.
23.8%±2.6
#80 of 97
claude-haiku-5-5_max
Oct 2026
Chat
Text ArenaLMArena
Human votes on chat answers across all kinds of prompts (style-controlled).
1,421±6
17,433 votes
#139 of 426
Claude Haiku 5.5 (High)
Nov 2026

Epoch AI: Epoch runs each benchmark itself on the models it evaluates, with the same harness for every model. The Epoch Capabilities Index combines many benchmarks into one score. Data: Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks (CC BY 4.0).

LMArena: People compare two anonymous models side by side and vote for the better answer; ratings come from those votes (Bradley-Terry, style-controlled for text and vision). Data: LMArena (arena.ai) leaderboard dataset (CC BY 4.0).

Rank is among all models the source ranks, including ones we don't list.

Subscribe to our newsletter

News and updates, 1–2 emails per month. No spam.