OpenMagic OpenMagic API Unified access for modern AI workflows
Login Get started
Pricing

Seven current Codex models on every plan. Pay less quota for lighter work.

Lite, Standard, and Pro share the same seven-model catalog. Plans differ by daily and weekly quota; model usage is metered at the disclosed reference rates from 2.00× down to 0.02×.

Get started View models

Choose your plan

Same model access on every tier. Higher plans provide more daily and weekly billed usage.

Start here

Lite

$4.99 / mo

Full model access with a starter usage allowance for trials and light personal projects.

  • All seven published models included; reference quota rates range from 2.00× to 0.02×.
  • $0.80 daily / $4.00 weekly billed-usage limit.
  • Best for evaluation, migration tests, and occasional use.

Included models · quota rate

GPT-6.1 Sol 0.40×
GPT-6 Astra 2.00×
GPT-6 Sol 0.40×
GPT-6 Luna 0.02×
GPT-5.6 Sol 1.00×
GPT-5.6 Terra 0.40×
GPT-5.6 Luna 0.04×
Subscribe
Most popular

Standard

$8.99 / mo

The everyday developer plan: the same full model set with 2.25× Lite usage capacity.

  • All seven published models included; reference quota rates range from 2.00× to 0.02×.
  • $1.80 daily / $9.00 weekly billed-usage limit.
  • Best for regular Codex, Claude Code, and Cursor work.

Included models · quota rate

GPT-6.1 Sol 0.40×
GPT-6 Astra 2.00×
GPT-6 Sol 0.40×
GPT-6 Luna 0.02×
GPT-5.6 Sol 1.00×
GPT-5.6 Terra 0.40×
GPT-5.6 Luna 0.04×
Subscribe
Best quota value

Pro

$18.99 / mo

The same full model set with 5.5× Lite usage capacity and the strongest quota-per-dollar value.

  • All seven published models included; reference quota rates range from 2.00× to 0.02×.
  • $4.40 daily / $22.00 weekly billed-usage limit.
  • Best for high-frequency agents and heavy individual use.

Included models · quota rate

GPT-6.1 Sol 0.40×
GPT-6 Astra 2.00×
GPT-6 Sol 0.40×
GPT-6 Luna 0.02×
GPT-5.6 Sol 1.00×
GPT-5.6 Terra 0.40×
GPT-5.6 Luna 0.04×
Subscribe

Seven models included in every plan

The reference multiplier compares input-token cost with GPT-5.6 Sol at 1.00×. Actual quota uses the exact input, cached-input, and output rates shown below.

Model Model ID Quota rate Input / 1M Cached / 1M Output / 1M
GPT-6.1 Sol gpt-6.1-sol 0.40× $2.00 $0.10 $10.00
GPT-6 Astra gpt-6-astra 2.00× $10.00 $1.00 $50.00
GPT-6 Sol gpt-6-sol 0.40× $2.00 $0.20 $10.00
GPT-6 Luna gpt-6-luna 0.02× $0.10 $0.01 $0.50
GPT-5.6 Sol gpt-5.6-sol 1.00× $5.00 $0.50 $30.00
GPT-5.6 Terra gpt-5.6-terra 0.40× $2.00 $0.20 $12.00
GPT-5.6 Luna gpt-5.6-luna 0.04× $0.20 $0.02 $1.20

gpt-5.6 is a legacy bare alias routed to gpt-5.6-terra. New configurations should use one of the seven current model IDs above.

How billing works

Subscription only. No wallet balance, no pay-as-you-go, no surprise bills.

Prepaid subscription

You pay a fixed price per cycle. There is no wallet to keep topped up and no per-token invoice — the plan price is the price.

Daily + weekly billed-usage limits

Both limits apply. When either window is used up, calls pause until that window resets automatically. The USD figure is metered API usage, not cash balance and not a fixed number of calls.

Transparent quota metering

GPT-5.6 Sol is the 1.00× reference. GPT-6 Astra is 2.00×, GPT-6.1 Sol and GPT-6 Sol are 0.40×, GPT-5.6 Terra is 0.40×, GPT-5.6 Luna is 0.04×, and GPT-6 Luna is 0.02×. Actual quota is calculated from the exact token rates in the table.

Upgrade amount versus quota

An upgrade checkout amount can be lower than the plan price because unused time on the current plan is credited. That amount is the payment due now; it is not the daily or weekly usage limit.

Enterprise route

High-volume teams move to enterprise pricing with dedicated channels, invoicing, and controlled model access.

Agent setup Start now