Skip to content
CallMissed
Book a demo

Explore CallMissed

Back to all models
LLM Chatnewreasoningtoolsvision
Anthropic — claude-haiku-5-5 logo

Claude Haiku 5.5

by Anthropic · Released 2026

For high-volume, latency-sensitive tasks such as classification, extraction, and routing. 1M-token context, image input, tool calling and reasoning. Pro plan and up.

Anthropic — claude-haiku-5-5 logo
LLM Chat

Claude Haiku 5.5

Powered by Anthropic · Not disclosed

Context Window

1M

Parameters

Not disclosed

Max Output

128K

Category

LLM Chat

Overview

Claude Haiku 5.5 is an Anthropic model for high-volume, latency-sensitive tasks such as classification, extraction, and routing. On CallMissed you call it with the id `claude-haiku-5-5` on the OpenAI-compatible `/v1/chat/completions` endpoint with your `cm_` API key.

Anthropic documents a 1,000,000-token context window, up to 128,000 output tokens, image and text input with text output, tool calling, and a reasoning effort setting with levels low, medium, high, xhigh and max. The knowledge cutoff is June 2026.

Pricing on CallMissed is $0.10 per million input tokens and $0.50 per million output tokens for prompts up to 100K tokens, and $0.50 / $2.50 per million for prompts above 100K tokens. Claude Haiku 5.5 is available on the Pro plan and up.

Pricing

MetricPrice
Input /1M tokens₹10.0000
Output /1M tokens₹50.0000

1 credit = ₹1 ≈ US$0.0104 (US$1 = ₹96). Transparent per-call pricing — you pay only for what you call, with no seat fees or minimums.

Key Highlights

  • Made for high-volume, latency-sensitive tasks: classification, extraction and routing
  • 1M-token context window and up to 128K output tokens
  • Image and text input, text output
  • Reasoning effort control: low, medium, high, xhigh, max
  • Pro plan and up

Technical Details

  • Context window: 1,000,000 tokens
  • Max output: 128,000 tokens
  • Input: image and text; output: text
  • Tool calling and streaming on the OpenAI-compatible gateway
  • Reasoning effort: low, medium, high, xhigh, max
  • Knowledge cutoff: June 2026
  • Available on the Pro plan and up

Strengths

  • Lowest price of the Claude 5.5 models
  • Fast enough for latency-sensitive pipelines
  • Native tool calling and image understanding

Limitations

  • Prompts above 100K tokens are billed at the higher rate ($0.50 / $2.50)
  • Less depth than Sonnet or Opus on hard problems
  • Pro plan and up only

Use Cases

Classification and routingData extractionHigh-volume support triageLow-latency agent steps

API Example

curl https://api.callmissed.com/v1/chat/completions \
  -H "Authorization: Bearer cm_YOUR_KEY" \
  -d '{"model": "claude-haiku-5-5", "messages": [{"role": "user", "content": "Classify this message as billing, support or sales"}]}'

Endpoint: POST /v1/chat/completions · Model ID: claude-haiku-5-5

Try Claude Haiku 5.5 now

Get 1000 free API credits on signup. No credit card required.

Start free Book a DemoRead docs