What models are supported?

We support the latest and most capable models from all leading platforms, including OpenAI, Anthropic, Google, Meta, and DeepSeek. Our system is designed to integrate new models within hours of their public release.

How does the credit system work?

Each plan comes with a set amount of monthly credits. Credits are consumed based on the token usage of the models you interact with. We bill in micro-credits to ensure you only pay for what you actually use.

How does the credit system translate to tokens?

Credits map directly to raw token consumption. For example, $10 of credits corresponds to roughly 1 million input tokens of GPT-4o, or up to 60 million input tokens on our open-source models. View the Benchmarks section for detailed conversion rates.

Is there a free trial?

Yes! Every new account automatically starts with a 7-day Developer plan trial at no cost — 200 credits included. You get full access to multi-model comparison, API key support, and cost visibility. After 7 days, choose Personal ($10/mo) or Developer ($20/mo) to continue.

Can I cancel my subscription at any time?

Absolutely. You can manage your subscription through our billing portal and cancel at any time. Your credits will remains active until the end of your billing cycle.

GPT-5.6 Luna vs GPT-OSS 120B — Price, Context, and Capability Compared

Verdict

GPT-5.6 Luna costs 1.7× more per blended million tokens than GPT-OSS 120B. GPT-5.6 Luna has the larger context window (400,000 tokens). Default to GPT-OSS 120B unless you specifically need GPT-5.6 Luna's edge. Only GPT-OSS 120B exposes an extended-thinking mode.

Spec comparison

	GPT-5.6 Luna	GPT-OSS 120B
Price (input)	$0.20/M	$0.15/M ✓
Price (output)	$1.20/M	$0.60/M ✓
Blended price	$0.45/M	$0.26/M ✓
Context window	400,000 tokens ✓	131,072 tokens
Max output	64,000 tokens ✓	32,768 tokens
Modalities	text, vision	text
Reasoning mode	No	Yes
Released	2026-06	2025-08
Speed	126 t/s	780 t/s ✓

Cost at scale (3:1 blended)

Tokens / month	GPT-5.6 Luna	GPT-OSS 120B	Delta
1,000,000	$0.45	$0.26	$0.19 (1.7×)
10,000,000	$4.50	$2.62	$1.88 (1.7×)
100,000,000	$45.00	$26.25	$18.75 (1.7×)

Choose GPT-5.6 Luna if…

✓Cheapest current GPT-5.6 tier
✓Low latency for high-volume calls
✓Vision input included
✓High-volume, latency-sensitive tasks like classification, extraction, and chat.

Choose GPT-OSS 120B if…

✓Open-weight MoE flagship
✓Ultra-fast on Groq LPUs
✓Strong agentic tool-use
✓Self-hostable or Groq-speed agentic workflows on open weights.

Run this exact matchup right now

Send the same prompt to GPT-5.6 Luna and GPT-OSS 120B side by side and see the outputs yourself.

Try GPT-5.6 Luna vs GPT-OSS 120B Free

FAQ

Is GPT-5.6 Luna cheaper than GPT-OSS 120B?

GPT-OSS 120B is cheaper, at $0.26 per million blended tokens vs $0.45 for GPT-5.6 Luna.

Which has the bigger context window, GPT-5.6 Luna or GPT-OSS 120B?

GPT-5.6 Luna has the larger context window: 400,000 tokens vs 131,072.

Can GPT-5.6 Luna replace GPT-OSS 120B for coding?

Both are viable for coding. Cheapest current GPT-5.6 tier (GPT-5.6 Luna) vs Open-weight MoE flagship (GPT-OSS 120B) — pick based on which strength matters more for your workload.

Which is faster, GPT-5.6 Luna or GPT-OSS 120B?

GPT-OSS 120B is faster: 780 t/s vs 126 t/s, measured on our speed benchmarks.

GPT-5.6 Luna pricing GPT-OSS 120B pricing vs DeepSeek V4 Pro vs GPT-4o Mini vs DeepSeek V4 Flash vs DeepSeek V4 Pro Cheap model tests

Pricing verified 2026-04-06. Specs verified 2026-08-08.