Back to the service list
Model provider / Model API

OpenCode Console

An optional model provider offering models the OpenCode team has verified. It is a separate contract from OpenCode itself, with usage-based pricing and the flat-rate Go plan.

Platforms: API

Also listed separately: OpenCode

Plans and what they cover

Not disclosed means the official page states no figure; not researched means we have not checked the item yet. Neither is the same as "no limit".

Usage-based

Usage-based

Usage-based (no monthly fee)

No monthly equivalent; check the official page for pricing details

Billed per model and input/output tokens. For example GPT 6.1 Sol (input up to 272K) costs $2 per million input tokens and $10 per million output tokens. There is no monthly fee. Buying credits adds a 4.6% + $0.31 fee.

Models and their allowances

Listed models are those we could confirm. When a model has no individual figure, check the shared plan allowance or separate contract terms as well.

  • GPT 6.1 SolAvailable

    Usage-based. The price changes with the input context length.

    This model’s own allowance: not researched, or shared across the plan. See the usage limits below.

Usage limit details

AllowanceNot researched
Scope
Whole plan
Window
Not researched
Resets
Not researched
On overage
Not researched
Rollover
Not researched

Budgets can be set. A fixed overall allowance has not been researched.

Official source for this limit

Officially confirmed · Checked

Official plan page for the latest terms
Official sources read (1)

Go

Subscription

$10.00 / month

Tax treatment not researched

For a single member. Only some supported models are listed. The official model list and limits may change. The USD figure is the unit for calculating the allowance, not a cash balance or an extra charge.

Models and their allowances

Listed models are those we could confirm. When a model has no individual figure, check the shared plan allowance or separate contract terms as well.

  • GLM-5.3-FlashAvailable

    The listed allowance is this model’s own spend equivalent. It is not an amount charged on top of the monthly fee.

    • Per-model spend equivalent cap: 60 USD equivalent / month

      GLM-5.3-Flash: $60 per month, $12 per 5 hours and $30 per week equivalent. The official estimate is 6,320 requests per 5 hours, 15,790 per week and 31,580 per month. It assumes 1,000 input, 55,000 cache-read and 200 output tokens per request and is not a guaranteed value. The allowance calculation uses $0.15 input, $0.50 output and $0.03 cache-read per million tokens.

      Resets: Separate 20% / 50% / 100% windows for 5 hours, a week and a month. Start times not researched / On overage: With Extra Usage enabled, usage is billed from the Console balance; otherwise free models remain available

      Official source for the per-model allowance
  • GPT 6 LunaAvailable

    The listed allowance is this model’s own spend equivalent. It is not an amount charged on top of the monthly fee.

    • Per-model spend equivalent cap: 15 USD equivalent / month

      GPT 6 Luna: $15 per month, $3 per 5 hours and $7.50 per week equivalent. The official estimate is 4,230 requests per 5 hours, 10,560 per week and 21,130 per month. It assumes 1,000 input, 50,000 cache-read and 220 output tokens per request and is not a guaranteed value. For input up to 272K, the allowance calculation uses $0.10 input, $0.50 output, $0.01 cache-read and $0.125 cache-write per million tokens.

      Resets: Separate 20% / 50% / 100% windows for 5 hours, a week and a month. Start times not researched / On overage: With Extra Usage enabled, usage is billed from the Console balance; otherwise free models remain available

      Official source for the per-model allowance

Usage limit details

Plan-wide limits have not been researched. Per-model allowances are shown above.

Officially confirmed · Checked

Official plan page for the latest terms
Official sources read (1)

Go Plus

Subscription

$40.00 / month

Tax treatment not researched

For a single member. Only some supported models are listed. The spend equivalent is the unit for calculating allowance use, not an extra charge.

Models and their allowances

Listed models are those we could confirm. When a model has no individual figure, check the shared plan allowance or separate contract terms as well.

  • GLM-5.3-FlashAvailable

    This model’s own spend equivalent allowance.

    • Per-model spend equivalent cap: 180 USD equivalent / month

      $36 per 5 hours and $90 per week equivalent. The official estimate is 18,960 requests per 5 hours, 47,370 per week and 94,740 per month, assuming 1,000 input, 55,000 cache-read and 200 output tokens per request.

      Resets: Separate 20% / 50% / 100% windows for 5 hours, a week and a month. Start times not researched / On overage: With Extra Usage enabled, usage is billed from the Console balance

      Official source for the per-model allowance
  • GPT 6 LunaAvailable

    This model’s own spend equivalent allowance.

    • Per-model spend equivalent cap: 60 USD equivalent / month

      $12 per 5 hours and $30 per week equivalent. The official estimate is 16,920 requests per 5 hours, 42,240 per week and 84,520 per month, assuming 1,000 input, 50,000 cache-read and 220 output tokens per request.

      Resets: Separate 20% / 50% / 100% windows for 5 hours, a week and a month. Start times not researched / On overage: With Extra Usage enabled, usage is billed from the Console balance

      Official source for the per-model allowance

Usage limit details

Plan-wide limits have not been researched. Per-model allowances are shown above.

Officially confirmed · Checked

Official plan page for the latest terms
Official sources read (1)

Go Teams

Subscription

$20.00 / month

Tax treatment not researched

$20 per member per month. Only some supported models are listed. The spend equivalent is the unit for calculating allowance use, not an extra charge.

Models and their allowances

Listed models are those we could confirm. When a model has no individual figure, check the shared plan allowance or separate contract terms as well.

  • GLM-5.3-FlashAvailable

    Each member has their own per-model allowance.

    • Per-member spend equivalent cap by model: 65 USD equivalent / month

      $13 per 5 hours and $32.50 per week equivalent. The official estimate is 6,847 requests per 5 hours, 17,110 per week and 34,210 per month, assuming 1,000 input, 55,000 cache-read and 200 output tokens per request.

      Resets: Separate 20% / 50% / 100% windows for 5 hours, a week and a month. Start times not researched / On overage: Extra Usage is on by default and can be disabled. Overage is billed from the Console balance

      Official source for the per-model allowance
  • GPT 6 LunaAvailable

    Each member has their own per-model allowance.

    • Per-member spend equivalent cap by model: 20 USD equivalent / month

      $4 per 5 hours and $10 per week equivalent. The official estimate is 5,640 requests per 5 hours, 14,080 per week and 28,170 per month, assuming 1,000 input, 50,000 cache-read and 220 output tokens per request.

      Resets: Separate 20% / 50% / 100% windows for 5 hours, a week and a month. Start times not researched / On overage: Extra Usage is on by default and can be disabled. Overage is billed from the Console balance

      Official source for the per-model allowance

Usage limit details

Plan-wide limits have not been researched. Per-model allowances are shown above.

Officially confirmed · Checked

Official plan page for the latest terms
Official sources read (1)

Sources for this service