Question 1

What is Claude Haiku 4.5?

Accepted Answer

Claude Haiku 4.5 is a model from Anthropic, released on Oct 15, 2025. Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. $1 per million input tokens, $5 per million output tokens. 200,000 token context window, maximum output of 64,000 tokens. Higher uptime with 4 providers. Includes independent benchmarks from Artificial Analysis.

Question 2

How much does Claude Haiku 4.5 cost?

Accepted Answer

On the Respan gateway, input starts at $1.00 per 1M tokens on every provider, and output starts at $5.00 per 1M tokens on every provider, after gateway discounts.

Question 3

Which providers serve Claude Haiku 4.5 on Respan?

Accepted Answer

7 providers serve Claude Haiku 4.5: Anthropic, Bedrock, DeepInfra, OpenRouter, Perplexity, and Google Vertex AI. Perplexity and Google Vertex AI require your own provider API key (BYOK).

Question 4

What is Claude Haiku 4.5's context window?

Accepted Answer

Claude Haiku 4.5 accepts up to 200K tokens of context on its largest provider route.

Question 5

How do I use Claude Haiku 4.5 with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "anthropic/claude-haiku-4-5-20251001". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Claude Haiku 4.5?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was Anthropic at 118 tokens per second, and the lowest response latency was 1.0 seconds on OpenRouter. Speed varies with request size and provider.

Question 7

Where does Claude Haiku 4.5 rank on the Respan Index?

Accepted Answer

Claude Haiku 4.5 scores 18.2 out of 100 on the Respan Index v1.1, ranking #105 of 138 models. By category: Coding 7.4, Agents 18.2, Reasoning 12.8, Knowledge & language 13.2, and Human preference 48.2. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

Question 8

How does Claude Haiku 4.5 score on benchmarks?

Accepted Answer

Claude Haiku 4.5 has 13 published benchmark scores, including SWE-bench Verified 73.3%, BALROG 31.2%, and GPQA Diamond 71.2%. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output
Anthropic`anthropic/claude-haiku-4-5`	200K	$1.00/M	$5.00/M
Anthropic`anthropic/claude-haiku-4-5-20251001`	200K	$1.00/M	$5.00/M
Bedrock`bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0`	200K	$1.00/M	$5.00/M
DeepInfra`deepinfra/anthropic/claude-haiku-4-5`	200K	$1.00/M	$5.00/M
OpenRouter`openrouter/anthropic/claude-haiku-4.5`	200K	$1.00/M	$5.00/M
PerplexityBYOK only`perplexity/anthropic/claude-haiku-4-5`	200K	$1.00/M	$5.00/M
Google Vertex AIBYOK only`vertex_ai/claude-haiku-4-5@20251001`	200K	$1.00/M	$5.00/M

Claude Haiku 4.5

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Time to first token

Response latency

Benchmarks

Respan Indexv1.1

Coding2

Agents

Apps

Claude Haiku 4.5 FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.

Reasoning2

Math2

Knowledge2

Arena2

Other1