Models

gemini-3.1-pro-preview vs gpt-5.6-luna

Output tokens cost $12.00 per million on gemini-3.1-pro-preview and $1.20 per million on gpt-5.6-luna. Input tokens cost $2.00 per million on gemini-3.1-pro-preview and $0.20 per million on gpt-5.6-luna. Cached input tokens are billed at $0.50 per million on gemini-3.1-pro-preview and $0.02 per million on gpt-5.6-luna. Context windows are 1,000,000 tokens on gemini-3.1-pro-preview and 1,050,000 tokens on gpt-5.6-luna. First-token latency measured on AIHubMix is 5.9s on gemini-3.1-pro-preview and 3.1s on gpt-5.6-luna. Measured output throughput is 79.5 tokens/s on gemini-3.1-pro-preview and 93.6 tokens/s on gpt-5.6-luna.

Googlegemini-3.1-pro-previewOpenAIgpt-5.6-luna
Google
gemini-3.1-pro-preview
Google · text, image, audio, video → text

Gemini 3.1 Pro Preview is designed to further optimize the performance and reliability of the Gemini 3 Pro series, offering improved reasoning capabilities, greater token efficiency, and a more robust, factually consistent user experience. It is optimized for software-engineering behaviors and usability, and is also suitable for agent workflows that require precise tool invocation and reliable multi-step execution, enabling stable operation across a variety of real-world scenarios.

Input$2.00 /M
Output$12.00 /M
OpenAI
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$0.20 /M
Output$1.20 /M

Specs & Pricing

Prices are per million tokens. Latency and throughput are rolling averages measured on AIHubMix.

gemini-3.1-pro-preview
gpt-5.6-luna
Input price
$2.00
$0.20
Output price
$12.00
$1.20
Cache read
$0.50
$0.02
Context window
1,000,000
1,050,000
Max output
64,000
128,000
Latency (first token)
5.9 s
3.1 s
Throughput
79.5 TPS
93.6 TPS
Modalities
textimageaudiovideo
textimage
Features
thinkingtoolsfunction callingstructured outputswebdeepsearchlong context
toolsthinkingstructured outputs
Endpoints
chat_completions · gemini_api · claude_api
chat_completions · responses

Promotional prices show the discounted rate; see each model page for promotion windows.

Usage on AIHubMix last 30 days

Daily traffic served through AIHubMix — how demand for each model is trending.

gemini-3.1-pro-previewgpt-5.6-luna

Tokens / day

-

Requests / day

-

Live Performance last 3 days

Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.

gemini-3.1-pro-previewgpt-5.6-luna

Throughput (TPS)

-

Latency (s)

-

Uptime (%)

-

Cost Calculator

Estimate your monthly bill for the same workload on each model.

gpt-5.6-luna
$30.00 /mo
gemini-3.1-pro-preview
$300 /mo

Monthly = daily × 30. Discounted rates applied where a promotion is active.

FAQ

Which is cheaper: gemini-3.1-pro-preview, gpt-5.6-luna?

gpt-5.6-luna: $1.20/M output tokens; gemini-3.1-pro-preview: $12.00/M. Use the cost calculator above to estimate your own workload.

Which responds faster?

gpt-5.6-luna: 3.1s first-token latency measured on AIHubMix; see the live performance charts above for how each model behaves across the day.

How large is each context window?

gemini-3.1-pro-preview accepts 1,000,000 and gpt-5.6-luna accepts 1,050,000 input tokens. Maximum output per request is 64,000 tokens on gemini-3.1-pro-preview and 128,000 tokens on gpt-5.6-luna.

Which one generates tokens faster?

gpt-5.6-luna at 93.6 tokens/s and gemini-3.1-pro-preview at 79.5 tokens/s, measured as output throughput on AIHubMix — a separate metric from first-token latency.

What inputs and capabilities does each model support?

gemini-3.1-pro-preview accepts text, image, audio and video input and supports thinking, tool calling, function calling, structured outputs, web search, deep search and long context; gpt-5.6-luna accepts text and image input and supports tool calling, thinking and structured outputs.

Can I call gemini-3.1-pro-preview 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.