Ask

GPT-5.6 Luna vs davinci-002

Detailed pricing comparison and cost analysis.

Updated September 2026

Cost Simulator

GPT-5.6 Luna Cost
$0.44
davinci-002 Cost
$2.40
GPT-5.6 Luna is 82% cheaper
FeatureGPT-5.6 Lunadavinci-002
ProviderOpenAIOpenAI
Input Price (1M)$0.20$2.00
Output Price (1M)$1.20$2.00
Context Window1,000,00016,384

Verdict

GPT-5.6 Luna costs $0.20 per 1M input tokens and $1.20 per 1M output tokens. davinci-002 costs $2.00 per 1M input tokens and $2.00 per 1M output tokens. GPT-5.6 Luna is 90% cheaper on input tokens than davinci-002. For output tokens, GPT-5.6 Luna is the more affordable option at $1.20/1M vs $2.00.

On context window, GPT-5.6 Luna supports 1,000,000 tokens — meaning it can fit more conversation history, documents, or code in a single request. This matters for RAG pipelines, long document analysis, and agentic workflows where context builds up over many turns.

When to choose GPT-5.6 Luna

  • ✓ You need the lowest input token cost ($ 0.20/1M)
  • ✓ Your workload is output-heavy — GPT-5.6 Luna generates text cheaper
  • ✓ You need a larger context window (1,000,000 tokens)
  • ✓ You are already integrated with OpenAI

When to choose davinci-002

  • ✓ You are already integrated with OpenAI

Use the calculator above to simulate your specific workload and find the exact break-even point. For most applications, the cheapest model is the one that minimises your total monthly bill given your input-to-output token ratio.

Frequently Asked Questions

Is GPT-5.6 Luna cheaper than davinci-002?

GPT-5.6 Luna is cheaper on input tokens at $0.20/1M vs $2.00/1M for davinci-002 — a 90% saving.

What is the context window of GPT-5.6 Luna vs davinci-002?

GPT-5.6 Luna has a 1,000,000-token context window. davinci-002 has a 16,384-token context window. GPT-5.6 Luna supports the larger context, suitable for longer documents and agentic workflows.

Which model is better: GPT-5.6 Luna or davinci-002?

The best choice depends on your use case. For cost efficiency on input tokens, GPT-5.6 Luna is the cheaper option. For maximum context length, GPT-5.6 Luna supports 1,000,000 tokens. Use the comparison table above to find the right fit for your workload.