claude-haiku-5-5Claude Haiku 5.5 pricing (October 2026)
Anthropic lists Claude Haiku 5.5 at $0.10 per 1M input tokens and $0.50 per 1M output tokens.
On Crazyrouter the same model is $0.10 / $0.50.
That is $0.0001 / $0.0005 per 1K tokens. Claude Haiku 5.5 is the #1 cheapest of the 38 chat models we track, by input price. 10× cheaper than Claude Haiku 4.5.
Base-tier rates shown; longer requests can cost more. Monthly estimates assume every request stays in the first tier.
Call Claude Haiku 5.5 at $0.10 in / $0.50 out per 1M tokens. Same model, same API, no plan — pay per token.
Looking for the ChatGPT / Claude app subscription price? That is a separate consumer product sold by Anthropic. This page is the developer API price per token.
The 100,000-token boundary applies per request
At 100,000 input tokens the first tier applies; at 100,001 the second tier applies to the request rates, including output and caching. Splitting a document changes context and may require repeated instructions, so a cheaper token tier alone is not evidence that splitting produces equivalent results.
Illustrative token counts, not measured lengths of the request example. USD at current default-group rates, 500 output tokens, no cache hits or writes. Each request uses its applicable tier; character count is not token count.
| Input tokens | Output tokens | Estimated USD |
|---|---|---|
| 2,000 | 500 | $0.00045 |
| 100,001 | 500 | $0.05125 |
Source and scope
Gateway catalogue and billing schedule, reviewed 2026-10-11. This confirms published configuration, not end-to-end feature tests or vendor release claims.
Crazyrouter · Token pricing tiers
USD / 1M tokens. Base-tier rates shown; longer requests can cost more. Monthly estimates assume every request stays in the first tier.
| Input tokens per request | Input | Output | Cache read | Cache write | Cache write (1h) |
|---|---|---|---|---|---|
| ≤ 100,000 | $0.10 | $0.50 | $0.01 | $0.125 | $0.20 |
| > 100,000 | $0.50 | $2.50 | $0.05 | $0.625 | $1.00 |
Anthropic · Token pricing tiers
USD / 1M tokens. Base-tier rates shown; longer requests can cost more. Monthly estimates assume every request stays in the first tier.
| Input tokens per request | Input | Output | Cache read | Cache write | Cache write (1h) |
|---|---|---|---|---|---|
| ≤ 100,000 | $0.10 | $0.50 | $0.01 | $0.125 | $0.20 |
| > 100,000 | $0.50 | $2.50 | $0.05 | $0.625 | $1.00 |
Claude Haiku 5.5 price by provider
USD per 1M tokens. Cloud prices are the base tier in the default region; the linked source is authoritative.
Base-tier rates shown; longer requests can cost more. Monthly estimates assume every request stays in the first tier.
| Provider | Input | Cached input | Output | Context | Source |
|---|---|---|---|---|---|
| Anthropic | $0.10 | $0.01 | $0.50 | 1M | Anthropic |
| Azure | $0.10 | $0.01 | $0.50 | 1M | Azure AI Foundry |
| AWS Bedrock | $0.10 | $0.01 | $0.50 | 1M | AWS Bedrock |
| Google Vertex AI | $0.10 | $0.01 | $0.50 | 1M | Google Vertex AI |
| OpenRouter | No verified quote | ||||
| Crazyrouter | $0.10 | $0.01 | $0.50 | 1M | crazyrouter.com |
per 1M tokens · Snapshot Oct 24, 2026
What Claude Haiku 5.5 costs per month
Three typical workloads, priced on each provider from the table above.
Base-tier rates shown; longer requests can cost more. Monthly estimates assume every request stays in the first tier.
| Workload | Anthropic | Azure | AWS Bedrock | Google Vertex AI | Crazyrouter |
|---|---|---|---|---|---|
| Prototype: 10M in / 2M out | $2.00 | $2.00 | $2.00 | $2.00 | $2.00 |
| Product: 100M in / 20M out | $20.00 | $20.00 | $20.00 | $20.00 | $20.00 |
| Scale: 1B in / 200M out | $200.00 | $200.00 | $200.00 | $200.00 | $200.00 |
Price changes
Tracked daily since Oct 5, 2025; no list-price changes recorded yet.
Alternatives to Claude Haiku 5.5
Same-family models and cheaper options for similar tasks.
Claude Haiku 5.5 pricing FAQ
How much does Claude Haiku 5.5 cost?
Anthropic charges $0.10 per 1M input tokens and $0.50 per 1M output tokens. Through Crazyrouter the same model is $0.10 / $0.50. Base-tier rates shown; longer requests can cost more. Monthly estimates assume every request stays in the first tier.
What is cached input pricing?
Tokens that repeat an earlier prompt prefix are billed at the cached rate ($0.01 per 1M when supported) instead of the full input price. Base-tier rates shown; longer requests can cost more. Monthly estimates assume every request stays in the first tier.
Is there a batch discount?
Yes. Anthropic offers batch pricing at $0.05 in / $0.25 out per 1M tokens for asynchronous jobs. Base-tier rates shown; longer requests can cost more. Monthly estimates assume every request stays in the first tier.
Is Claude Haiku 5.5 cheaper on Azure, Bedrock or Vertex?
Cloud providers usually match the list price and add regional or provisioned tiers; see the table above for the base rate on each. Crazyrouter applies its discount on top of list. Base-tier rates shown; longer requests can cost more. Monthly estimates assume every request stays in the first tier.
Sources and method
Provider reference prices use LiteLLM data and maintained entries. Provider links are references, not proof of daily official verification. Snapshot: Oct 24, 2026. Crazyrouter rates come from our billing table; confirm current prices, region and terms with the provider before purchase.
- Anthropic — www.anthropic.com/pricing
- Azure — azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service
- AWS Bedrock — aws.amazon.com/bedrock/pricing
- Google Vertex AI — cloud.google.com/vertex-ai/generative-ai/pricing
- Crazyrouter — crazyrouter.com/pricing
- LiteLLM