Home / Models / Anthropic / Claude Haiku 4.5

Claude Haiku 4.5 pricing and routing profile

Claude Haiku 4.5 from Anthropic lists at $1.00 per million input tokens and $5.00 per million output tokens, with a 200,000-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$1.00

Output, per 1M tokens$5.00

Cached input, per 1M$0.10

Context window200K

Confidence signalNot exposed

Tool callingStructured outputReasoning control

Cost per 1,000 requests

Request shape	List cost
Classification or routing (600 tokens in, 10 out)	$0.65
Chat reply (2,000 in, 400 out)	$4.00
Retrieval-augmented answer (8,000 in, 500 out)	$10.50

Before prompt caching. Try your own shape in the cost calculator.

Can Gimbix route to it first?

Not as a first-answer model through OpenRouter: no host returns token log probabilities for Claude Haiku 4.5. It can still be the model Gimbix falls back to when a cheaper model is unsure.

Measured by Gimbix

On 400 real BANKING77 customer messages, Claude Haiku 4.5 answered 301 correctly (95% interval 70.8%–79.2%), with 2 invalid answers, at $0.691 per 1,000 requests and a median of 986 ms. See all 22 models.

Who serves Claude Haiku 4.5

Host	Input / output per 1M	Log probabilities	Uptime, last 30 min
Azure	$1.00 / $5.00	no	100.0%
Amazon Bedrock	$1.00 / $5.00	no	99.8%
Google	$1.00 / $5.00	no	98.8%
Anthropic	$1.00 / $5.00	no	99.9%
Amazon Bedrock	$1.10 / $5.50	no	—
Google	$1.10 / $5.50	no	—
Amazon Bedrock	$1.10 / $5.50	no	100.0%
Google	$1.10 / $5.50	no	—

A host that lists log probabilities may still omit them; Gimbix checks each one before relying on it.

Cheaper models that can answer first

Models priced below Claude Haiku 4.5 that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.

Model	Input / output per 1M	Cheaper on a chat reply
Qwen3 Max Thinking	$0.78 / $3.90	22%
Qwen3 Max	$0.78 / $3.90	22%
DeepSeek V4 Pro 0423	$0.955 / $1.91	33%
Kimi K2.6	$0.65 / $3.41	33%
Kimi K2.7 Code	$0.656 / $3.30	34%
Qwen3 Coder Plus	$0.65 / $3.25	35%

Compare Claude Haiku 4.5

Questions

How much does Claude Haiku 4.5 cost?

Claude Haiku 4.5 lists at $1.00 per million input tokens and $5.00 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $4.00 per 1,000 requests.

What is the context window of Claude Haiku 4.5?

200,000 tokens.

Can a cheaper model replace Claude Haiku 4.5?

Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Claude Haiku 4.5 on one half of your requests and make at most three answers worse on the other.