Models/Claude Haiku 5.5 (Max)

Claude Haiku 5.5 (Max)Ready

claude-haiku-5-5

Serverless APILLMReasoningVisionPrompt cachingClosed

The fastest Claude tier, built for high-volume production traffic and latency-sensitive products. It ranks #15 of the top 20 frontier models on the Artificial Analysis Intelligence Index with a score of 43.4. Released October 7, 2026.

Context

—

Parameters

#15

Intelligence rank · 43.4

Closed

Weights

View full spec

ReleasedOct 7, 2026

Knowledge cutoff—

Size classmedium

Input modalitiestext, image

Output modalitiestext

Median output speed235 tok/s

Median time to first token336.4s

Usage guide

1. Choose how you'd like to use Claude Haiku 5.5 (Max)

☁️ Serverless

Use with pay-per-token pricing. Zero setup, no cold starts, automatic failover between upstream routes.

Usage tiers · Standard • Priority

Try it — sign in

curl https://tokenhub.coality.io/v1/chat/completions \
  -H "Authorization: Bearer $TOKEN_HUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-haiku-5-5",
    "messages": [{"role": "user", "content": "Explain vector databases in one paragraph"}]
  }'

Pricing

Bucket	Price	Notes
Input tokens	$0.1250	per 1M tokens
Output tokens	$0.6250	per 1M tokens
Cache read	$0.0125	cached input · 90% off
Cache write	$0.1563	per 1M tokens

Billed per token with micro-dollar precision · effective Oct 27, 2026 · default key limits 600 req/min · 200K tokens/min

Benchmarks

Humanity's Last Exam

44.4

SciCode

55.0

Terminal-Bench 4.0

32.8

Long Context Reasoning

82.7

Frontier Code

41.8

Scores from the Artificial Analysis evaluation suite (0–100 scale).

About this model

Closed model, with a 1M context window, native image input, visible reasoning traces, prompt caching at a 90% discount on cached input, 235 output tokens/s median serving speed and 336.4s to first token.