Claude Haiku 5.5 API pricing

5 providers serve Claude Haiku 5.5. Claude Haiku 5.5 is a proprietary API model, up to 1000K context. Prices below are per 1M tokens, cheapest input first.

Refreshed 2026-10-08 · list prices from provider APIs
Input floor $0.100/1M at OpenRouter, Anthropic, AWS Bedrock and 2 more Output floor $0.500/1M at OpenRouter, Anthropic, AWS Bedrock and 2 more Find your workload winner →
Provider Input $/1M Output $/1M Cache read $/1M Context
OpenRouter $0.100 $0.500output floor $0.010 1000K Use
Anthropic $0.100 $0.500 $0.010 1000K Use
AWS Bedrock $0.100 $0.500 $0.010 1000K Use
Azure AI Foundry $0.100 $0.500 $0.010 1000K Use
Google Vertex AI $0.100 $0.500 $0.010 1000K Use

The cheapest way to run Claude Haiku 5.5

On an illustrative 70M-input / 30M-output monthly workload, today's lowest listed cost is roughly $22.00/month — the same at OpenRouter, Anthropic, AWS Bedrock and 2 more. Input-heavy, output-heavy and cache-heavy workloads can produce different winners. Use the live mix calculator below rather than combining floors from two different providers. It is API-only, so the table above is your full set of options. Run your own numbers in the breakeven calculator, or read the breakeven math.

Your actual monthly cost

Uses today's list prices

Cache read uses the listed cache rate where available; otherwise it falls back to normal input price. Batch, write-cache, volume and negotiated discounts are excluded.

Related models

ModelCheapest in $/1MCheapest out $/1MProviders
Claude Haiku 4.5 $1.00 $5.00 12
Claude Sonnet 4.5 $3.00 $15.00 10
Claude Sonnet 4 $3.00 $15.00 9
Claude Opus 4.5 $5.00 $25.00 8
Claude Fable 5 $10.00 $50.00 8
Claude Opus 5 $5.00 $25.00 8

FAQ

What is the cheapest API for Claude Haiku 5.5?

As of 2026-10-08, the lowest input price for Claude Haiku 5.5, $0.100 per 1M tokens, is the same list price at OpenRouter, Anthropic, AWS Bedrock and 2 more. The lowest output price, $0.500 per 1M tokens, is likewise shared by the same providers. The cheapest provider for a real workload depends on its input/output mix.

← All models · GPU rental prices · Breakeven calculator · Get this data as JSON