Skip to main content
Dawloom

Claude Haiku 5.5 vs GPT-6 Luna

At 10,000 requests a month of 5,000 input and 500 output tokens, GPT-6 Luna costs about $7.50 a month and Claude Haiku 5.5 about $9.75, so GPT-6 Luna is 23% cheaper. Claude Haiku 5.5 has a context window of 1,000,000 tokens and GPT-6 Luna has 1,050,000 tokens. Claude Haiku 5.5 has no announced retirement. Anthropic says it will not retire it before Oct 7, 2027. GPT-6 Luna has no announced retirement. Prices checked 2026-10-21.

Prices are USD per 1M tokens, standard tier, checked 2026-10-21. Monthly cost uses the workload below.

  • Claude Haiku 5.5 Anthropic

    Input per 1M
    $0.10
    Output per 1M
    $0.50
    Monthly cost
    $9.75
    $0.98 per 1,000 requests
    Context
    1M
    Retirement
    Active
    Anthropic says not retired before Oct 7, 2027
    API ID:
    claude-haiku-5-5
    Max output:
    128K
    Inputs:
    Text, Images
    Released:
    Oct 7, 2026
    Knowledge cutoff:
    Jun 2026

  • GPT-6 Luna OpenAI

    Input per 1M
    $0.10
    Output per 1M
    $0.50
    Monthly cost
    $7.50Cheapest
    $0.75 per 1,000 requests
    Context
    1.05M
    Retirement
    Active
    No retirement date listed
    API ID:
    gpt-6-luna
    Max output:
    128K
    Inputs:
    Text, Images
    Released:
    Not published
    Knowledge cutoff:
    May 18, 2026
Compare with other models

Monthly cost estimate

Example sizes are our round numbers. Set your own below.

  • Claude Haiku 5.5 $9.75 a month

    $0.98 per 1,000 requests

  • GPT-6 Luna Cheapest $7.50 a month

    $0.75 per 1,000 requests

List prices checked 2026-10-21, standard tier, no caching, no batch discount. Claude 4.7 and later count about 30% more tokens for the same text, so their rows include that. Long-prompt prices apply where the vendor sets them.

The facts side by side

Each model page lists every fact with its source: Claude Haiku 5.5 and GPT-6 Luna.

Prices are USD per 1M tokens, standard tier. Monthly cost is 10,000 requests of 5,000 input and 500 output tokens. Checked 2026-10-21 on each vendor's own pages.

  • Claude Haiku 5.5 Anthropic

    Input per 1M
    $0.10
    Output per 1M
    $0.50
    Monthly cost
    $9.75
    $0.98 per 1,000 requests
    Context
    1M
    Retirement
    Active
    Anthropic says not retired before Oct 7, 2027
    API ID:
    claude-haiku-5-5
    Max output:
    128K
    Inputs:
    Text, Images
    Released:
    Oct 7, 2026
    Knowledge cutoff:
    Jun 2026

  • GPT-6 Luna OpenAI

    Input per 1M
    $0.10
    Output per 1M
    $0.50
    Monthly cost
    $7.50Cheapest
    $0.75 per 1,000 requests
    Context
    1.05M
    Retirement
    Active
    No retirement date listed
    API ID:
    gpt-6-luna
    Max output:
    128K
    Inputs:
    Text, Images
    Released:
    Not published
    Knowledge cutoff:
    May 18, 2026

Benchmark scores side by side

Independent scores from Epoch AI, which scores every vendor's models the same way. Ranks compare each model with the others on our AI models page.

Benchmark Claude Haiku 5.5GPT-6 Luna
Epoch Capabilities Index One score that combines many benchmarks, such as math, science, and coding tests, into a single scale. Epoch sets Claude 3.5 Sonnet at 130 and GPT-5 at 150. 159.32 Rank 9 of 17 models here 156.75 Rank 11 of 17 models here
GPQA Diamond 198 hard multiple-choice questions in biology, chemistry, and physics, written by PhD-level experts. Guessing scores 25%. We show the highest score for each model across the reasoning settings Epoch ran. 89.6% Rank 12 of 16 models here 90.5% Rank 11 of 16 models here

Scores are Epoch AI's, not ours. Source: Epoch AI, Capabilities and benchmarking, from its public data download, checked 2026-10-21. Used under CC BY 4.0. We drew the charts. A benchmark is one test, so run your own inputs before you choose.

What each vendor says

"For high-volume, latency-sensitive tasks such as classification, extraction, and routing"
"Our most efficient model for focused, high-volume tasks."

Want a different pair? Use the AI model compare tool, or get a shortlist for your job from the AI model picker. For older models with shutdown dates, see our AI model retirement dates calendar.

Questions clients ask

Short answers, no sales language. If yours isn't here, ask an engineer directly.

Ask us anything
Which is cheaper, Claude Haiku 5.5 or GPT-6 Luna?

They have the same list price: $0.10 in and $0.50 out per 1M tokens. At 10,000 requests a month of 5,000 input and 500 output tokens, Claude Haiku 5.5 costs about $9.75 a month and GPT-6 Luna about $7.50. The monthly figures add about 30% to Claude 4.7 and later rows, because Anthropic says they count more tokens for the same text. Checked 2026-10-21.

Which has the larger context window?

Claude Haiku 5.5: 1,000,000 tokens. GPT-6 Luna: 1,050,000 tokens.

Is either model being retired?

Claude Haiku 5.5 has no announced retirement. Anthropic says it will not retire it before Oct 7, 2027. GPT-6 Luna has no announced retirement.

Which should I use?

Run 20 to 50 of your real inputs through both and compare the answers and the token counts. Price per token is only half of the cost. The other half is how many tokens each model uses for your task.

Want both tested on your data?

Send us 20 real inputs. An engineer runs them through both models and replies with the results. We bill hourly or by milestone.

Start a project Book a meeting
Search the whole site