Read the limits in order

Read the windows before the model table

Token capacity in each model row is a conversion. What you can actually use is first shaped by these three windows and the plan allowance.

per month$10
  1. 01

    Rolling 5 hours

    A rolling five-hour window; concentrated usage can reach this ceiling first.

    $14
  2. 02

    Rolling week

    A rolling weekly window with its own ceiling; concentrated usage may reach it before the monthly allowance.

    $35
  3. 03

    Monthly plan limit

    The plan’s shared monthly credits pool.

    $70
Model options
48
Free models
2

02Complete model index

Every model, in one working table

All 48 options are listed here. Search, calculate the same workload, or open a model detail page.

Current comparison
Same workload · 12,000 tokens/request · 83% cache read

Higher CP means more Coding score for the same cost.

More options

Workload basis

Comparison mode

Filters

Edit the four-part token mix +

View data

Mobile view

Showing 48 plan options

Capacity estimates use model allowances. Check plan pools and time windows for your usage. View methodology
SelectNext
Qwen 3.7 FlashCommand GOAT
1.1BCalculate ↗
MiMo V2.5Command GOAT
803.6M15.256.8Calculate ↗
Tencent Hy3Command GOAT
785.0M6.658.8Calculate ↗
757.9M8.769.1Calculate ↗
Muse Spark 1.2 ContributorCommand GOATScores from Muse Spark 1.2
750.0M27.172.2Calculate ↗
Muse Spark 1.3 ContributorCommand GOATScores from Muse Spark 1.3
750.0M28.676.3Calculate ↗
GLM-5.3 FlashCommand GOAT
505.3M9.071.5Calculate ↗
Step 3.5 FlashCommand GOAT
400.0MCalculate ↗
Qwen 3.8 FlashCommand GOAT
303.8MCalculate ↗
MiniMax M3Command GOAT
268.6M3.358.6Calculate ↗
252.6M8.265.0Calculate ↗
Qwen 3.8 27BCommand GOAT
221.1M2.268.1Calculate ↗
MiMo V2.5 ProCommand GOAT
179.0M5.460.2Calculate ↗
DeepSeek V4 Flash FastCommand GOATScores from DeepSeek V4 Flash (latest)
155.8M5.469.1Calculate ↗
GPT-5.6 LunaCommand GOAT
150.0M5.471.4Calculate ↗
Qwen 3.7 PlusCommand GOAT
141.4M2.455.9Calculate ↗
Step 3.7 FlashCommand GOAT
137.1M2.739.6Calculate ↗
MiniMax M2.5Command GOAT
133.3MCalculate ↗
MiniMax M2.7Command GOAT
114.3M3.052.6Calculate ↗
Kimi K2.7 CodeCommand GOAT
105.1M1.160.8Calculate ↗
GLM-5.2Command GOAT
100.0M1.068.8Calculate ↗
Inkling SmallCommand GOAT
88.9M2.452.9Calculate ↗
Qwen 3.6 PlusCommand GOAT
88.0M1.554.5Calculate ↗
83.9M2.968.8Calculate ↗
63.9MCalculate ↗
57.1M1.449.3Calculate ↗
Kimi K2.5Command GOAT
52.2M1.246.8Calculate ↗
45.7M0.976.1Calculate ↗
45.7M0.976.3Calculate ↗
GLM-5Command GOAT
38.7MCalculate ↗
Kimi K2.6Command GOAT
36.6M1.161.8Calculate ↗
InklingCommand GOAT
35.5M0.952.1Calculate ↗
Muse Spark 1.2Command GOAT
34.3M1.272.2Calculate ↗
Muse Spark 1.3Command GOAT
34.3M1.376.3Calculate ↗
GLM-5.1Command GOAT
28.6M0.855.8Calculate ↗
GLM-5.3Command GOAT
28.6M1.174.8Calculate ↗
Qwen 3.7 MaxCommand GOAT
26.4M0.566.0Calculate ↗
Qwen 3.8 MaxCommand GOAT
22.8M0.871.8Calculate ↗
22.8M0.871.8Calculate ↗
GPT-5.6 SolCommand GOAT
21.0M0.277.4Calculate ↗
20.5MCalculate ↗
Grok 4.5Command GOAT
18.5M0.772.4Calculate ↗
Grok 4.6Command GOAT
18.5M0.776.8Calculate ↗
Kimi K2.7 Code HighSpeedCommand GOATScores from Kimi K2.7 Code
17.5M0.560.8Calculate ↗
GLM-5.2 FastCommand GOATScores from GLM-5.2
13.1M0.568.8Calculate ↗
Kimi K3Command GOAT
11.4M0.476.2Calculate ↗
Laguna S 2.1Command GOAT · Free
Calculate ↗
LongCat 2.0Command GOAT · Free
45.3Calculate ↗

Compare your shortlist

Same workload · 12,000 tokens / request

Metric
Estimated capacity / month
CP value
coding
Model monthly allowance
Cost per 1M equivalent tokens
Input / 1M
Cache read / 1M
Output / 1M
Cache write / 1M
intelligence
agentic

Capacity uses model allowances; plan pools and time windows also apply.

03Free models

Free access still has conditions

Free models do not consume model allowance, but start-up credits and plan or capacity conditions may still apply; see the official plan document. Official source ↗

04Billing conditions

Conditions to read with the plan limits

These conditions affect plan choice and usage estimates.

  1. 01

    How model allowances and shared plan pools work

    Command Code GOAT uses one shared credit pool; OpenCode Go lists a usage equivalent for each model. Model allowances cannot be added together as plan capacity.

  2. 02

    Per-request usage changes the available count

    The reference request is an estimate basis. Five-hour and weekly windows limit concentrated use; Command Code GOAT rolls its window from the first request.

  3. 03

    Read discounted and list prices separately

    The GOAT page shows discounted prices for MiMo V2.5, MiMo V2.5 Pro and MiniMax M3. This site keeps list price, current price and the deal note in separate columns.

  4. 04

    Prices and allowances for speed variants

    Command's GLM-5.2 Fast and Kimi K2.7 Code HighSpeed are separate models; compare the price and allowance listed for each one.

  5. 05

    Conditions for free models

    Command's free models do not consume a model allowance, but starting a session may still require USD 1 of credits, and capacity limits still apply.

  6. 06

    Included capacity and purchased credits

    Command pay-as-you-go credits are not bound by the windows, and OpenCode's Use balance may fall back to Zen balance after the Go limits. Both are listed separately from included capacity.

  7. 07

    Model lists and prices are updated

    Official documentation can change its model list or prices. This page shows the current data date; comparable later snapshots will be listed in the update history.