Claude Haiku 4.5 vs GPT-5: Pricing Comparison

Compare pricing, capabilities, and costs for your LLM workloads.

Anthropic

Claude Haiku 4.5

Pricing (per 1M tokens)

Input$1.00
Output$5.00
Cached Input$0.1000
Batch Input$0.5000
Batch Output$2.50

Context & Output

Context Window200K tokens
Max Output64K tokens

Capabilities

Categorybudget
Multimodaltext + image
Fine-tuningNo
StreamingYes

OpenAI

GPT-5

Pricing (per 1M tokens)

Input$1.25
Output$10.00
Cached Input$0.1250
Batch Input$0.6250
Batch Output$5.00

Context & Output

Context Window400K tokens
Max Output128K tokens

Capabilities

Categoryflagship
Multimodaltext + image + audio
Fine-tuningNo
StreamingYes

Quick Verdict

Cheaper Input Price

Claude Haiku 4.5

20.0% cheaper

Cheaper Output Price

Claude Haiku 4.5

50.0% cheaper

Larger Context Window

GPT-5

+200K tokens

Cost Comparison

Sample workload: 1,000,000 input tokens + 1,000,000 output tokens

Claude Haiku 4.5

$6.00

$1.00/1M input + $5.00/1M output

GPT-5

$11.25

$1.25/1M input + $10.00/1M output

Claude Haiku 4.5 is 46.7% cheaper for this workload.

Frequently Asked Questions

Which is cheaper, Claude Haiku 4.5 or GPT-5?
For input tokens, Claude Haiku 4.5 is cheaper at $1.00 per 1M tokens. For output tokens, Claude Haiku 4.5 is cheaper at $5.00 per 1M tokens. The overall cost depends on your workload's input/output ratio.
What is the context window size of Claude Haiku 4.5 vs GPT-5?
Claude Haiku 4.5 has a context window of 200K tokens, while GPT-5 has 400K tokens. GPT-5 supports a larger context window of 400K tokens, which is beneficial for processing longer documents.
How do Claude Haiku 4.5 and GPT-5 compare for batch processing?
Both models support batch processing with discounted rates. Claude Haiku 4.5 offers a better batch rate at $0.5000 per 1M input tokens. Batch processing is ideal for non-time-sensitive workloads where you can wait for processing.

Need more tools?

Explore our complete suite of LLM calculators and comparison tools.