Claude 3 Haiku 20240307
Anthropic · text, image → text
Input$0.275 /M
Output$1.375 /M
← ModelsClaude 3 Haiku 20240307
GPT 5.6 Luna
Claude 3 Haiku 20240307 vs GPT 5.6 Luna
Compare Claude 3 Haiku 20240307 from Anthropic and GPT 5.6 Luna from OpenAI on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.
Claude 3 Haiku 20240307GPT 5.6 Luna+ Add model · 2/4
GPT 5.6 Luna
OpenAI · text, image → text
GPT-5.6 Luna is designed for cost-sensitive, high-volume workloads. It roughly corresponds to the nano model tier used in earlier GPT-5 families.
Input$0.2 /M
Output$1.2 /M
Cache read$0.02 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Claude 3 Haiku 20240307
GPT 5.6 Luna
Input /M
$0.275
$0.2
Output /M
$1.375
$1.2
Cache read /M
-
$0.02
Context length
0
1,050,000
Max output
0
128,000
Time to First Token
4.5 s
5.1 s
Throughput
79.8 tok/s
47.6 tok/s
Modalities
textimage
textimage
Supported Parameters
toolsthinkingstructured outputs
API Formats
chat_completions · responses
Released
March 7, 2024
July 9, 2026
Promotional prices show the discounted rate; see each model page for promotion windows.
Activity Past 30 Days
Daily traffic served through AIHubMix — how demand for each model is trending.
claude-3-haiku-20240307gpt-5.6-luna
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
claude-3-haiku-20240307gpt-5.6-luna
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
Cost calculator
Estimate your monthly bill for the same workload on each model.
GPT 5.6 Luna
$30.00 /mo
Claude 3 Haiku 20240307
$37.13 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Claude 3 Haiku 20240307, GPT 5.6 Luna?
GPT 5.6 Luna: $1.2/M output tokens; Claude 3 Haiku 20240307: $1.375/M. Use the cost calculator above to estimate your own workload.
Which responds faster?
Claude 3 Haiku 20240307: 4.5s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
Which one generates tokens faster?
Claude 3 Haiku 20240307 at 79.8 tok/s and GPT 5.6 Luna at 47.6 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
What inputs and capabilities does each model support?
Claude 3 Haiku 20240307 accepts text and image input; GPT 5.6 Luna accepts text and image input and supports tool calling, thinking and structured outputs.
Can I call Claude 3 Haiku 20240307 and GPT 5.6 Luna with the same API key?
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Popular comparisons
Related model match-ups readers also look at.
