token.app › Compare › Claude Haiku 4.5 (batch) vs GPT-5.6 Luna

Claude Haiku 4.5 (batch) vs GPT-5.6 Luna

GPT-5.6 Luna is 4.4× cheaper per token on a blended 3:1 basis. GPT-5.6 Luna accepts the larger context window (1.1M).

Head to head
Blended price uses a 3:1 input:output mix
Claude Haiku 4.5 (batch)GPT-5.6 Luna
ProviderAnthropicOpenAI
Input $/1M$0.500$0.100
Output $/1M$2.50$0.600
Blended $/1M$1.00$0.225
Context window200K1.1M
Max output64K128K
ReleasedOct 2025Jul 2026
LicenceProprietaryProprietary
Choose Claude Haiku 4.5 (batch) if…
  • No clear advantage on the data we hold.
Choose GPT-5.6 Luna if…
  • Costs less per token — $0.225 vs $1.00 blended
  • Larger context window (1.1M)
  • Newer model (released Jul 2026)
FAQ
Which is better, Claude Haiku 4.5 (batch) or GPT-5.6 Luna?
We do not hold independently-run benchmark scores covering both Claude Haiku 4.5 (batch) and GPT-5.6 Luna, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Claude Haiku 4.5 (batch) cheaper than GPT-5.6 Luna?
GPT-5.6 Luna is cheaper: $0.225 versus $1.00 per million tokens blended at 3:1 input:output. Input alone: $0.500 vs $0.100. Output alone: $2.50 vs $0.600.
What context windows do Claude Haiku 4.5 (batch) and GPT-5.6 Luna have?
Claude Haiku 4.5 (batch): 200,000 tokens. GPT-5.6 Luna: 1,050,000 tokens.
Who makes Claude Haiku 4.5 (batch) and GPT-5.6 Luna?
Claude Haiku 4.5 (batch) is made by Anthropic. GPT-5.6 Luna is made by OpenAI.
Related comparisons
Claude Haiku 4.5 (batch) full details GPT-5.6 Luna full details Claude Haiku 4.5 (batch) vs Ling 3.0 Tiny (free) Claude Haiku 4.5 (batch) vs Muse Spark 1.2 Claude Haiku 4.5 (batch) vs Qwen3.8 Max Claude Haiku 4.5 (batch) vs DeepSeek V4 Flash Latest Claude Haiku 4.5 (batch) vs DeepSeek V4 Flash 0731 Claude Haiku 4.5 (batch) vs Inkling Small