GPT-5.4 nano vs Claude Haiku 4.5: Pricing Comparison

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

OpenAI

GPT-5.4 nano

Pricing (per 1M tokens)

Input$0.2000
Output$1.25
Cached Input$0.0200
Batch Input$0.1000
Batch Output$0.6250

Context & Output

Context Window400K tokens
Max Output128K tokens

Capabilities

Categorybudget
Multimodaltext + image
Fine-tuningNo
StreamingYes

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

Quick Verdict

Cheaper Input Price

GPT-5.4 nano

80.0% cheaper

Cheaper Output Price

GPT-5.4 nano

75.0% cheaper

Larger Context Window

GPT-5.4 nano

+200K tokens

Cost Comparison

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

GPT-5.4 nano

$1.45

$0.2000/1M input + $1.25/1M output

Claude Haiku 4.5

$6.00

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

GPT-5.4 nano is 75.8% cheaper for this workload.

Frequently Asked Questions

Which is cheaper, GPT-5.4 nano or Claude Haiku 4.5?
For input tokens, GPT-5.4 nano is cheaper at $0.2000 per 1M tokens. For output tokens, GPT-5.4 nano is cheaper at $1.25 per 1M tokens. The overall cost depends on your workload's input/output ratio.
What is the context window size of GPT-5.4 nano vs Claude Haiku 4.5?
GPT-5.4 nano has a context window of 400K tokens, while Claude Haiku 4.5 has 200K tokens. GPT-5.4 nano supports a larger context window of 400K tokens, which is beneficial for processing longer documents.
How do GPT-5.4 nano and Claude Haiku 4.5 compare for batch processing?
Both models support batch processing with discounted rates. GPT-5.4 nano offers a better batch rate at $0.1000 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.