Pricingby IbisWays to buy 10
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
The lab's own API · cached $0.01 | $0.1 | $0.5 | $0.1 / $0.5List price | $0.01 | List price |
 AWS BedrockDefault region · cached $0.01 | $0.1 | $0.5 | $0.1 / $0.5Same as list | $0.01 | Same as list |
global · cached $0.01 | $0.1 | $0.5 | $0.1 / $0.5Same as list | $0.01 | Same as list |
| Claude Platform on AWS Default region · cached $0.01 | $0.1 | $0.5 | $0.1 / $0.5Same as list | $0.01 | Same as list |
global · cached $0.01 | $0.1 | $0.5 | $0.1 / $0.5Same as list | $0.01 | Same as list |
| AWS Bedrock eu-west-1 · cached $0.011 | $0.11 | $0.55 | $0.11 / $0.55+10% vs list | $0.011 | +10% vs list |
| AWS Bedrock us-east-1 · cached $0.011 | $0.11 | $0.55 | $0.11 / $0.55+10% vs list | $0.011 | +10% vs list |
us · cached $0.011 | $0.11 | $0.55 | $0.11 / $0.55+10% vs list | $0.011 | +10% vs list |
europe · cached $0.011 | $0.11 | $0.55 | $0.11 / $0.55+10% vs list | $0.011 | +10% vs list |
us · cached $0.011 | $0.11 | $0.55 | $0.11 / $0.55+10% vs list | $0.011 | +10% vs list |
USD per 1M tokens; batch $0.05 in, $0.25 out on the lab's API. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $20.00 direct.
Kong AI Gateway$20.00+0%
LiteLLM$20.00+0%
Vercel AI Gateway$20.00+0%
Requesty$21.00+5%
Eden AI$21.10+5.5%
OpenRouter$21.10+5.5%
Cloudflare AI GatewayNot offeredNot offered
HeliconeNot offeredNot offered
Martian GatewayNot offeredNot offered
Neon AI GatewayNot offeredNot offered
A dash: not on that gateway's own model list. No published token fee: Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | ||||||
|---|---|---|---|---|---|---|---|
Anthropic · 1M | $2 | $10 | $2 / $10 | $4 | 1M | Lab list price | · |
Anthropic · 1M | $4 | $20 | $4 / $20 | $8 | 1M | Lab list price | · |
Anthropic · 1M | $10 | $50 | $10 / $50 | $20 | 1M | Lab list price | · |
Anthropic · 1M | $5 | $25 | $5 / $25 | $10 | 1M | Lab list price | · |
DeepSeek · 1MCheapest: $0.109 on InferenceNet (fp8) | $0.15 | $0.6 | $0.15 / $0.6 | $0.262 | 1M | $0.109 on InferenceNet (fp8) | · |
OpenAI · 1.05MCheapest: $0.1 on OpenAI (flex) | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1.05M | $0.1 on OpenAI (flex) | · |
OpenAI · 1.05MCheapest: $0.1 on OpenAI (flex) | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1.05M | $0.1 on OpenAI (flex) | · |
Qwen (Alibaba) · 1M | $0.15 | $0.47 | $0.15 / $0.47 | $0.23 | 1M | Lab list price | · |
About Claude Haiku 5.5
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.
Takes text, image, files in and returns text. First listed Oct 8, 2026. Up to 128K output tokens. Blended price $0.2 per 1M tokens at 3 input to 1 output. Model id claude-haiku-5-5.
Price history
List price since Oct 8, 2026, from daily reads of the OpenRouter catalog.
Questions
How much does Claude Haiku 5.5 cost?
$0.1 per million input tokens and $0.5 per million output tokens, with cached input at $0.01, or $0.05 and $0.25 through the Batch API.
What is the context window of Claude Haiku 5.5?
1M tokens, with up to 128K tokens of output.
Where is Claude Haiku 5.5 cheapest?
Of 10 routes tracked, AWS Bedrock is cheapest at $0.1 input and $0.5 output per million tokens.