OpenAI Codex vs Gemini CLI (Enterprise / API key only)

Verified 2026-10-27

OpenAI Codex lists 12 plans. 9 publish a monthly USD price, from $0 to $500. Verified 2026-10-27. Gemini CLI (Enterprise / API key only) lists 8 plans. 4 publish a monthly USD price, from $0 to $54. Verified 2026-10-18.

A plan with no status field is active. A status value of discontinued means that plan no longer works for the tool.

OpenAI Codex

Codex is OpenAI's coding agent that helps you write, review, and ship code from the ChatGPT desktop app, CLI, IDE extension, web, and Codex Cloud.

Summary source · verified 2026-10-18

Free

Audience: individual

Verified 2026-10-18

Price/mo (USD)
$0
source · verified 2026-10-18
Listed as $0/month.
Usage limits
Codex is included. Usage limits vary by plan. Codex Cloud is not included.
source · verified 2026-10-18
Numeric request, token, 5-hour, and weekly caps not published by vendor.
Overflow / pay-as-you-go
Credit purchases are available only to a limited group of Free users. If shown, credits apply after included usage and do not raise the included limit. Purchase amounts and prices vary by account, region, and plan. Credits last 12 months and are non-refundable except where required.
source · verified 2026-10-18
USD credit-pack prices not published by vendor.
Models
GPT-6 Luna
source · verified 2026-10-18
Desktop app when available. GPT-6.1 Sol is not included on Free at launch.

Try it (opens in a new tab)

Go

Audience: individual

Verified 2026-10-18

Price/mo (USD)
$8
source · verified 2026-10-18
Listed as $8/month for lightweight coding tasks.
Usage limits
Codex is included. Usage limits vary by plan. Codex Cloud is not included.
source · verified 2026-10-18
Numeric request, token, 5-hour, and weekly caps not published by vendor.
Overflow / pay-as-you-go
Credit purchases are available only to a limited group of Go users. If shown, credits apply after included usage and do not raise the included limit. Purchase amounts and prices vary by account, region, and plan. Credits last 12 months and are non-refundable except where required.
source · verified 2026-10-18
USD credit-pack prices not published by vendor.
Models
GPT-6 Luna
source · verified 2026-10-18
Desktop app when available. GPT-6.1 Sol is not included on Go at launch.

Get this plan (opens in a new tab)

Plus

Audience: individual

Verified 2026-10-27

Price/mo (USD)
$20
source · verified 2026-10-18
Listed as $20/month.
Usage limits
Local-message estimates per five-hour period, not fixed message limits: GPT-6 Astra 5-45; GPT-6.1 Sol 15-160; GPT-6.1 Terra 35-285; GPT-6 Sol 15-150; GPT-6 Luna 350-3,000. Local messages and cloud chats share the allowance. Weekly limits may also apply. Cloud tasks may use more than local messages. Fast mode uses included subscription usage at 2.5x the Standard rate. ChatGPT Work shares this usage. ChatGPT for Excel shares it on Plus once that pricing is effective.
source · verified 2026-10-27
Overflow / pay-as-you-go
If a limit is reached during an active turn, the agent can finish that turn subject to fair-use limits. Plus users can buy credits to continue without upgrading. Extra local chats can use an API key at standard API rates. On purchased credits, Fast mode is 2x the Standard rate.
source · verified 2026-10-18
USD credit-pack prices not published by vendor.
Models
GPT-6 Astra, GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Sol, GPT-6 Luna
source · verified 2026-10-27
Feature bullets name GPT-6.1 Sol and GPT-6 Luna. The usage table also gives Plus estimates for GPT-6 Astra and GPT-6 Sol. GPT-6.1 Terra is available in Work and Codex on Plus, Pro, Business, Enterprise, and Edu plans, with a Plus estimate of 35-285 local messages per five hours.

Get this plan (opens in a new tab)

Pro 100

Audience: individual

Verified 2026-10-27

Price/mo (USD)
$100
source · verified 2026-10-18
Billed monthly. Annual billing is not available. Ultrafast is not included. Pro 200 includes more usage than Pro 100.
Usage limits
No five-hour usage limit in Work and Codex. An included usage allowance still applies. Work and Codex share that allowance. Remaining allowance and reset times are in Settings → Usage. Ultrafast is not included.
source · verified 2026-10-18
Numeric message, token, and weekly caps not published by vendor.
Overflow / pay-as-you-go
Included usage is used first. After plan limits, Codex usage draws from the credit balance. Credits also cover ChatGPT Work, Word, Excel, and PowerPoint when those features are on the plan. Buy credits in Settings → Usage or Codex Usage & Billing. Automatic reload is available where shown. Credits last 12 months and are non-refundable except where required.
source · verified 2026-10-18
USD credit-pack prices not published by vendor.
Models
GPT-6 Astra, GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Sol, GPT-6 Luna
source · verified 2026-10-27
Pro includes everything in Plus. Those five models have Plus usage estimates on this page.

Get this plan (opens in a new tab)

Pro 200

Audience: individual

Verified 2026-10-27

Price/mo (USD)
$200
source · verified 2026-10-18
Billed monthly. Annual billing is not available. Ultrafast is not included. New subscriptions that are not grandfathered include a lower usage allowance than Pro 200 previously offered. Eligible subscribers who had Pro 200 between September 22, 2026 and 10 a.m. Pacific on September 29, 2026 keep the previous allowance through October 29, 2026. The price stays $200/month.
Usage limits
No five-hour usage limit in Work and Codex. An included usage allowance still applies. Work and Codex share that allowance. Remaining allowance and reset times are in Settings → Usage. Ultrafast is not included.
source · verified 2026-10-18
Numeric message, token, and weekly caps not published by vendor. This page does not state how Pro 200's allowance compares with Pro 100 or Pro 500.
Overflow / pay-as-you-go
Included usage is used first, then the credit balance. Credits support Codex, ChatGPT Work, Word, Excel, and PowerPoint where available on the account. Buy them in Settings → Usage or Codex Usage & Billing. Buying credits on Pro 200 does not unlock Ultrafast. Support cannot reset Codex limits.
source · verified 2026-10-18
USD credit-pack prices and credit expiration not published by vendor.
Models
GPT-6 Astra, GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Sol, GPT-6 Luna
source · verified 2026-10-27
Pro includes everything in Plus. Those five models have Plus usage estimates on this page. Ultrafast mode access is stated for Pro $500.

Get this plan (opens in a new tab)

Pro 500

Audience: individual

Verified 2026-10-27

Price/mo (USD)
$500
source · verified 2026-10-18
Billed monthly. Annual billing is not available. Ultrafast is included. Pro 500 offers the highest included usage of the three Pro plans.
Usage limits
No five-hour usage limit in Work and Codex. An included usage allowance still applies. Work and Codex share that allowance. Ultrafast for GPT-6 Astra and GPT-6.1 Sol uses included usage first at 8x the Standard rate for the selected model, then credits at 6x the Standard credit rate.
source · verified 2026-10-18
Numeric message, token, and weekly caps not published by vendor.
Overflow / pay-as-you-go
Included usage is used first, then the credit balance. Among Pro plans, Ultrafast is only on Pro 500: it uses included usage at 8x the Standard rate, then credits at 6x the Standard credit rate for GPT-6 Astra or GPT-6.1 Sol. Credits can be purchased for eligible Codex usage. Support cannot reset Codex limits.
source · verified 2026-10-18
USD credit-pack prices not published by vendor.
Models
GPT-6 Astra, GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Sol, GPT-6 Luna
source · verified 2026-10-27
Everything in Plus, plus Ultrafast mode on Pro $500 for GPT-6 Astra and GPT-6.1 Sol. GPT-6.1 Terra is available in Work and Codex on Pro.

Get this plan (opens in a new tab)

Business Standard

Audience: team

Verified 2026-10-27

Price/mo (USD)
$25
source · verified 2026-10-18
Monthly billing: $25 per user per month. Annual billing: $20 per user per month, billed annually. Pricing may vary by country and currency. A workspace needs at least 2 Standard or Premium seats. Includes ChatGPT, ChatGPT Work, and Codex.
Usage limits
Standard Business local-message estimates per five hours, not fixed limits: GPT-6 Astra 5-45; GPT-6.1 Sol 15-160; GPT-6.1 Terra 35-285; GPT-6 Sol 15-150; GPT-6 Luna 350-3,000. Same ranges as Plus on this page. Local messages and cloud chats share the allowance. Weekly limits may also apply. Cloud tasks may use more than local messages. Fast mode uses included subscription usage at 2.5x the Standard rate.
source · verified 2026-10-27
GPT-5.6 message estimates are not published on this page.
Overflow / pay-as-you-go
Per-seat limits apply first. If the user exceeds a limit and the workspace has purchased credits, usage continues from the shared pool. Credits are optional. If no credits are available, the feature is blocked until an owner adds more. Owners can use automatic recharge. Business credits are valid for 12 months after purchase.
source · verified 2026-10-18
USD credit-pack prices not published by vendor.
Models
GPT-6 Sol, GPT-6.1 Sol, GPT-6 Luna, GPT-6 Astra, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna
source · verified 2026-10-18
GPT-6 Sol, GPT-6.1 Sol, and GPT-6 Luna are Work and Codex options. Astra and GPT-5.6 Sol, Terra, and Luna depend on the workspace. Standard seats include limited Astra usage inside the existing allowance.

Get this plan (opens in a new tab)

Business Premium

Audience: team

Verified 2026-10-18

Price/mo (USD)
$125
source · verified 2026-10-18
Monthly billing: $125 per user per month. Annual billing: $100 per user per month, billed annually. Same access as Standard with higher ChatGPT Work and Codex limits. Seats can be mixed with Standard.
Usage limits
Premium seats have 5x the included usage of Standard seats and no 5-hour limit. This page's Standard local-message estimates per 5-hour window are GPT-6 Astra 5-45; GPT-6.1 Sol and GPT-6 Sol 15-150; GPT-5.6 Sol 10-100; GPT-5.6 Terra 25-200; GPT-5.6 Luna 250-2,000. Cloud chats can use more than local messages. Premium seats can use their full existing allowance for Astra. Standard seats only include limited Astra usage.
source · verified 2026-10-18
The 5x Premium ranges are not published as their own numbers. A weekly numeric cap is not published by vendor.
Overflow / pay-as-you-go
After included usage is exhausted, eligible usage, including additional Astra usage, can continue on purchased workspace credits if credits are available and spending controls allow it. Otherwise wait for the allowance to reset. Workspace credit purchases are optional.
source · verified 2026-10-18
USD credit-pack prices not published by vendor.
Models
GPT-6 Sol, GPT-6.1 Sol, GPT-6 Luna, GPT-6 Astra, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna
source · verified 2026-10-18
Same Work and Codex model options as Standard. Premium seats can use their full existing allowance for Astra.

Get this plan (opens in a new tab)

Business legacy Codex seat

Audience: team

Verified 2026-10-18

Price/mo (USD)
$0
source · verified 2026-10-18
No fixed monthly or annual seat fee. Usage is paid from workspace credits, so this is not a free allowance. Not sold to new Business workspaces, or to workspaces that had not added a Codex seat or a pending Codex invite, as of June 24, 2026. Eligible workspaces can still add seats. Does not include ChatGPT chat and does not count toward the 2-seat minimum.
Usage limits
No included Codex allowance. Every Codex action draws on the workspace credit balance. If no credits are available, Codex is blocked until an owner adds credits. Owners and admins can set a monthly spending limit for legacy Codex seats or for a member; hitting that limit pauses Codex until the limit changes or resets.
source · verified 2026-10-18
Request, token, 5-hour, and weekly caps not published by vendor.
Overflow / pay-as-you-go
There is no included pool. Usage stops when credits run out or a spending limit is hit. It resumes when an owner adds credits, changes the limit, or the spending limit resets. Purchased credits last 12 months. Owners can turn on automatic reload. Used credits are not restored when a member is removed.
source · verified 2026-10-18
USD credit-pack prices not published by vendor.
Models
GPT-6.1 Sol, GPT-6 Astra, GPT-6 Sol, GPT-6 Luna, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, GPT-5.3-Codex, GPT-5.2, GPT-Image-2
source · verified 2026-10-18
Credit rates for Codex-only seats in eligible Business workspaces. Code review uses GPT-5.3-Codex. GPT-5.4 and GPT-5.4 mini are no longer available with ChatGPT sign-in. Daybreak and GPT-6 Astra Law need separate approval and are omitted.

Try it (opens in a new tab)

Enterprise

Audience: enterprise

Verified 2026-10-27

Price/mo (USD)
Not published
source · verified 2026-10-18
not published by vendor. Page says custom pricing and to contact sales. Credit-based and token-based pricing are available.
Usage limits
Enterprise/Edu users with flexible pricing have no fixed rate limits; usage scales with credits. Enterprise and Edu plans without flexible pricing have the same per-seat usage limits as Plus for most features. Plus local-message estimates per five hours on this page: GPT-6 Astra 5-45; GPT-6.1 Sol 15-160; GPT-6.1 Terra 35-285; GPT-6 Sol 15-150; GPT-6 Luna 350-3,000. Weekly limits may also apply. If the agreement specifies usage-based billing in USD, the Enterprise USD rate card and the agreement apply instead of credit rates.
source · verified 2026-10-27
Overflow / pay-as-you-go
Credit-based Enterprise workspaces buy a shared credit pool at the contract level. There are no per-seat usage caps by default; admins can set spend controls by group. When the pool is exhausted, advanced features pause unless owners enable overages or buy more credits. An overage limit of 0 blocks new credit-using requests. Token-based Enterprise agreements are charged in USD at contracted rates. Credit expiration and seat true-ups follow the order form.
source · verified 2026-10-18
Public USD price per credit not published by vendor.
Models
GPT-6.1 Sol, GPT-6 Astra, GPT-6 Sol, GPT-6 Luna, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, GPT-5.3-Codex, GPT-5.2, GPT-Image-2, GPT-Rosalind-Research
source · verified 2026-10-18
Work and Codex credit-rate models for credit-based Enterprise. GPT-Rosalind-Research is only on select Enterprise plans. Ultrafast credit rates apply on eligible Enterprise plans. Daybreak and GPT-6 Astra Law need separate approval and are omitted. A small subset of Enterprise customers remains on a legacy rate card. Which models are enabled by default is not published on this page.

Get this plan (opens in a new tab)

Edu

Audience: enterprise

Verified 2026-10-27

Price/mo (USD)
Not published
source · verified 2026-10-18
not published by vendor. Page calls ChatGPT Edu an affordable plan for universities and says to contact sales. No USD amount is shown.
Usage limits
Enterprise/Edu users with flexible pricing have no fixed rate limits; usage scales with credits. Enterprise and Edu plans without flexible pricing have the same per-seat usage limits as Plus for most features. Plus local-message estimates per five hours on this page: GPT-6 Astra 5-45; GPT-6.1 Sol 15-160; GPT-6.1 Terra 35-285; GPT-6 Sol 15-150; GPT-6 Luna 350-3,000. Weekly limits may also apply.
source · verified 2026-10-27
Edu-only numeric caps beyond the Plus comparison are not published by vendor.
Overflow / pay-as-you-go
Edu workspaces on credit-based flexible pricing use a shared credit pool purchased at the contract level. There are no per-seat caps by default. When the pool is exhausted, advanced features pause unless owners enable overages or buy more credits through the account team. Credit expiration is defined in the order form.
source · verified 2026-10-18
Public USD price per credit not published by vendor.
Models
GPT-6.1 Sol, GPT-6 Astra, GPT-6 Sol, GPT-6 Luna, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, GPT-5.3-Codex, GPT-5.2, GPT-Image-2
source · verified 2026-10-18
Work and Codex credit-rate models for credit-based Edu. Ultrafast credit rates apply on eligible Edu plans. GPT-Rosalind-Research is select Enterprise only and is omitted. Daybreak and GPT-6 Astra Law need separate approval and are omitted. Default enablement is not published on this page.

Get this plan (opens in a new tab)

API Key

Audience: individual

Verified 2026-10-18

Price/mo (USD)
Not published
source · verified 2026-10-18
not published by vendor. No monthly fee is stated. Pay for Codex usage based on API pricing.
Usage limits
No included subscription allowance is stated. Usage is billed at API pricing. Codex is available in the CLI, SDK, or IDE extension. Cloud features such as GitHub code review and Slack are not included.
source · verified 2026-10-18
The API price table is not published on this page.
Overflow / pay-as-you-go
All usage is pay-as-you-go at API rates. There is no included pool to exceed. ChatGPT-signed-in users can also run extra local chats with an API key after they hit plan limits, charged at standard API rates.
source · verified 2026-10-18
Models
Model availability follows the API models available to your key.
source · verified 2026-10-18
A fixed model list is not published by vendor. GPT-5.5 retirement on October 14, 2026 does not apply to API-key Codex sessions.

Get this plan (opens in a new tab)

OpenAI Codex plans
PlanPrice/mo (USD)Usage limitsOverflow / pay-as-you-goModels

Free

Audience: individual

Verified 2026-10-18

Try it (opens in a new tab)

$0

source · verified 2026-10-18

Listed as $0/month.

Codex is included. Usage limits vary by plan. Codex Cloud is not included.

source · verified 2026-10-18

Numeric request, token, 5-hour, and weekly caps not published by vendor.

Credit purchases are available only to a limited group of Free users. If shown, credits apply after included usage and do not raise the included limit. Purchase amounts and prices vary by account, region, and plan. Credits last 12 months and are non-refundable except where required.

source · verified 2026-10-18

USD credit-pack prices not published by vendor.

GPT-6 Luna

source · verified 2026-10-18

Desktop app when available. GPT-6.1 Sol is not included on Free at launch.

Go

Audience: individual

Verified 2026-10-18

Get this plan (opens in a new tab)

$8

source · verified 2026-10-18

Listed as $8/month for lightweight coding tasks.

Codex is included. Usage limits vary by plan. Codex Cloud is not included.

source · verified 2026-10-18

Numeric request, token, 5-hour, and weekly caps not published by vendor.

Credit purchases are available only to a limited group of Go users. If shown, credits apply after included usage and do not raise the included limit. Purchase amounts and prices vary by account, region, and plan. Credits last 12 months and are non-refundable except where required.

source · verified 2026-10-18

USD credit-pack prices not published by vendor.

GPT-6 Luna

source · verified 2026-10-18

Desktop app when available. GPT-6.1 Sol is not included on Go at launch.

Plus

Audience: individual

Verified 2026-10-27

Get this plan (opens in a new tab)

$20

source · verified 2026-10-18

Listed as $20/month.

Local-message estimates per five-hour period, not fixed message limits: GPT-6 Astra 5-45; GPT-6.1 Sol 15-160; GPT-6.1 Terra 35-285; GPT-6 Sol 15-150; GPT-6 Luna 350-3,000. Local messages and cloud chats share the allowance. Weekly limits may also apply. Cloud tasks may use more than local messages. Fast mode uses included subscription usage at 2.5x the Standard rate. ChatGPT Work shares this usage. ChatGPT for Excel shares it on Plus once that pricing is effective.

source · verified 2026-10-27

If a limit is reached during an active turn, the agent can finish that turn subject to fair-use limits. Plus users can buy credits to continue without upgrading. Extra local chats can use an API key at standard API rates. On purchased credits, Fast mode is 2x the Standard rate.

source · verified 2026-10-18

USD credit-pack prices not published by vendor.

GPT-6 Astra, GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Sol, GPT-6 Luna

source · verified 2026-10-27

Feature bullets name GPT-6.1 Sol and GPT-6 Luna. The usage table also gives Plus estimates for GPT-6 Astra and GPT-6 Sol. GPT-6.1 Terra is available in Work and Codex on Plus, Pro, Business, Enterprise, and Edu plans, with a Plus estimate of 35-285 local messages per five hours.

Pro 100

Audience: individual

Verified 2026-10-27

Get this plan (opens in a new tab)

$100

source · verified 2026-10-18

Billed monthly. Annual billing is not available. Ultrafast is not included. Pro 200 includes more usage than Pro 100.

No five-hour usage limit in Work and Codex. An included usage allowance still applies. Work and Codex share that allowance. Remaining allowance and reset times are in Settings → Usage. Ultrafast is not included.

source · verified 2026-10-18

Numeric message, token, and weekly caps not published by vendor.

Included usage is used first. After plan limits, Codex usage draws from the credit balance. Credits also cover ChatGPT Work, Word, Excel, and PowerPoint when those features are on the plan. Buy credits in Settings → Usage or Codex Usage & Billing. Automatic reload is available where shown. Credits last 12 months and are non-refundable except where required.

source · verified 2026-10-18

USD credit-pack prices not published by vendor.

GPT-6 Astra, GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Sol, GPT-6 Luna

source · verified 2026-10-27

Pro includes everything in Plus. Those five models have Plus usage estimates on this page.

Pro 200

Audience: individual

Verified 2026-10-27

Get this plan (opens in a new tab)

$200

source · verified 2026-10-18

Billed monthly. Annual billing is not available. Ultrafast is not included. New subscriptions that are not grandfathered include a lower usage allowance than Pro 200 previously offered. Eligible subscribers who had Pro 200 between September 22, 2026 and 10 a.m. Pacific on September 29, 2026 keep the previous allowance through October 29, 2026. The price stays $200/month.

No five-hour usage limit in Work and Codex. An included usage allowance still applies. Work and Codex share that allowance. Remaining allowance and reset times are in Settings → Usage. Ultrafast is not included.

source · verified 2026-10-18

Numeric message, token, and weekly caps not published by vendor. This page does not state how Pro 200's allowance compares with Pro 100 or Pro 500.

Included usage is used first, then the credit balance. Credits support Codex, ChatGPT Work, Word, Excel, and PowerPoint where available on the account. Buy them in Settings → Usage or Codex Usage & Billing. Buying credits on Pro 200 does not unlock Ultrafast. Support cannot reset Codex limits.

source · verified 2026-10-18

USD credit-pack prices and credit expiration not published by vendor.

GPT-6 Astra, GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Sol, GPT-6 Luna

source · verified 2026-10-27

Pro includes everything in Plus. Those five models have Plus usage estimates on this page. Ultrafast mode access is stated for Pro $500.

Pro 500

Audience: individual

Verified 2026-10-27

Get this plan (opens in a new tab)

$500

source · verified 2026-10-18

Billed monthly. Annual billing is not available. Ultrafast is included. Pro 500 offers the highest included usage of the three Pro plans.

No five-hour usage limit in Work and Codex. An included usage allowance still applies. Work and Codex share that allowance. Ultrafast for GPT-6 Astra and GPT-6.1 Sol uses included usage first at 8x the Standard rate for the selected model, then credits at 6x the Standard credit rate.

source · verified 2026-10-18

Numeric message, token, and weekly caps not published by vendor.

Included usage is used first, then the credit balance. Among Pro plans, Ultrafast is only on Pro 500: it uses included usage at 8x the Standard rate, then credits at 6x the Standard credit rate for GPT-6 Astra or GPT-6.1 Sol. Credits can be purchased for eligible Codex usage. Support cannot reset Codex limits.

source · verified 2026-10-18

USD credit-pack prices not published by vendor.

GPT-6 Astra, GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Sol, GPT-6 Luna

source · verified 2026-10-27

Everything in Plus, plus Ultrafast mode on Pro $500 for GPT-6 Astra and GPT-6.1 Sol. GPT-6.1 Terra is available in Work and Codex on Pro.

Business Standard

Audience: team

Verified 2026-10-27

Get this plan (opens in a new tab)

$25

source · verified 2026-10-18

Monthly billing: $25 per user per month. Annual billing: $20 per user per month, billed annually. Pricing may vary by country and currency. A workspace needs at least 2 Standard or Premium seats. Includes ChatGPT, ChatGPT Work, and Codex.

Standard Business local-message estimates per five hours, not fixed limits: GPT-6 Astra 5-45; GPT-6.1 Sol 15-160; GPT-6.1 Terra 35-285; GPT-6 Sol 15-150; GPT-6 Luna 350-3,000. Same ranges as Plus on this page. Local messages and cloud chats share the allowance. Weekly limits may also apply. Cloud tasks may use more than local messages. Fast mode uses included subscription usage at 2.5x the Standard rate.

source · verified 2026-10-27

GPT-5.6 message estimates are not published on this page.

Per-seat limits apply first. If the user exceeds a limit and the workspace has purchased credits, usage continues from the shared pool. Credits are optional. If no credits are available, the feature is blocked until an owner adds more. Owners can use automatic recharge. Business credits are valid for 12 months after purchase.

source · verified 2026-10-18

USD credit-pack prices not published by vendor.

GPT-6 Sol, GPT-6.1 Sol, GPT-6 Luna, GPT-6 Astra, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna

source · verified 2026-10-18

GPT-6 Sol, GPT-6.1 Sol, and GPT-6 Luna are Work and Codex options. Astra and GPT-5.6 Sol, Terra, and Luna depend on the workspace. Standard seats include limited Astra usage inside the existing allowance.

Business Premium

Audience: team

Verified 2026-10-18

Get this plan (opens in a new tab)

$125

source · verified 2026-10-18

Monthly billing: $125 per user per month. Annual billing: $100 per user per month, billed annually. Same access as Standard with higher ChatGPT Work and Codex limits. Seats can be mixed with Standard.

Premium seats have 5x the included usage of Standard seats and no 5-hour limit. This page's Standard local-message estimates per 5-hour window are GPT-6 Astra 5-45; GPT-6.1 Sol and GPT-6 Sol 15-150; GPT-5.6 Sol 10-100; GPT-5.6 Terra 25-200; GPT-5.6 Luna 250-2,000. Cloud chats can use more than local messages. Premium seats can use their full existing allowance for Astra. Standard seats only include limited Astra usage.

source · verified 2026-10-18

The 5x Premium ranges are not published as their own numbers. A weekly numeric cap is not published by vendor.

After included usage is exhausted, eligible usage, including additional Astra usage, can continue on purchased workspace credits if credits are available and spending controls allow it. Otherwise wait for the allowance to reset. Workspace credit purchases are optional.

source · verified 2026-10-18

USD credit-pack prices not published by vendor.

GPT-6 Sol, GPT-6.1 Sol, GPT-6 Luna, GPT-6 Astra, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna

source · verified 2026-10-18

Same Work and Codex model options as Standard. Premium seats can use their full existing allowance for Astra.

Business legacy Codex seat

Audience: team

Verified 2026-10-18

Try it (opens in a new tab)

$0

source · verified 2026-10-18

No fixed monthly or annual seat fee. Usage is paid from workspace credits, so this is not a free allowance. Not sold to new Business workspaces, or to workspaces that had not added a Codex seat or a pending Codex invite, as of June 24, 2026. Eligible workspaces can still add seats. Does not include ChatGPT chat and does not count toward the 2-seat minimum.

No included Codex allowance. Every Codex action draws on the workspace credit balance. If no credits are available, Codex is blocked until an owner adds credits. Owners and admins can set a monthly spending limit for legacy Codex seats or for a member; hitting that limit pauses Codex until the limit changes or resets.

source · verified 2026-10-18

Request, token, 5-hour, and weekly caps not published by vendor.

There is no included pool. Usage stops when credits run out or a spending limit is hit. It resumes when an owner adds credits, changes the limit, or the spending limit resets. Purchased credits last 12 months. Owners can turn on automatic reload. Used credits are not restored when a member is removed.

source · verified 2026-10-18

USD credit-pack prices not published by vendor.

GPT-6.1 Sol, GPT-6 Astra, GPT-6 Sol, GPT-6 Luna, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, GPT-5.3-Codex, GPT-5.2, GPT-Image-2

source · verified 2026-10-18

Credit rates for Codex-only seats in eligible Business workspaces. Code review uses GPT-5.3-Codex. GPT-5.4 and GPT-5.4 mini are no longer available with ChatGPT sign-in. Daybreak and GPT-6 Astra Law need separate approval and are omitted.

Enterprise

Audience: enterprise

Verified 2026-10-27

Get this plan (opens in a new tab)

Not published

source · verified 2026-10-18

not published by vendor. Page says custom pricing and to contact sales. Credit-based and token-based pricing are available.

Enterprise/Edu users with flexible pricing have no fixed rate limits; usage scales with credits. Enterprise and Edu plans without flexible pricing have the same per-seat usage limits as Plus for most features. Plus local-message estimates per five hours on this page: GPT-6 Astra 5-45; GPT-6.1 Sol 15-160; GPT-6.1 Terra 35-285; GPT-6 Sol 15-150; GPT-6 Luna 350-3,000. Weekly limits may also apply. If the agreement specifies usage-based billing in USD, the Enterprise USD rate card and the agreement apply instead of credit rates.

source · verified 2026-10-27

Credit-based Enterprise workspaces buy a shared credit pool at the contract level. There are no per-seat usage caps by default; admins can set spend controls by group. When the pool is exhausted, advanced features pause unless owners enable overages or buy more credits. An overage limit of 0 blocks new credit-using requests. Token-based Enterprise agreements are charged in USD at contracted rates. Credit expiration and seat true-ups follow the order form.

source · verified 2026-10-18

Public USD price per credit not published by vendor.

GPT-6.1 Sol, GPT-6 Astra, GPT-6 Sol, GPT-6 Luna, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, GPT-5.3-Codex, GPT-5.2, GPT-Image-2, GPT-Rosalind-Research

source · verified 2026-10-18

Work and Codex credit-rate models for credit-based Enterprise. GPT-Rosalind-Research is only on select Enterprise plans. Ultrafast credit rates apply on eligible Enterprise plans. Daybreak and GPT-6 Astra Law need separate approval and are omitted. A small subset of Enterprise customers remains on a legacy rate card. Which models are enabled by default is not published on this page.

Edu

Audience: enterprise

Verified 2026-10-27

Get this plan (opens in a new tab)

Not published

source · verified 2026-10-18

not published by vendor. Page calls ChatGPT Edu an affordable plan for universities and says to contact sales. No USD amount is shown.

Enterprise/Edu users with flexible pricing have no fixed rate limits; usage scales with credits. Enterprise and Edu plans without flexible pricing have the same per-seat usage limits as Plus for most features. Plus local-message estimates per five hours on this page: GPT-6 Astra 5-45; GPT-6.1 Sol 15-160; GPT-6.1 Terra 35-285; GPT-6 Sol 15-150; GPT-6 Luna 350-3,000. Weekly limits may also apply.

source · verified 2026-10-27

Edu-only numeric caps beyond the Plus comparison are not published by vendor.

Edu workspaces on credit-based flexible pricing use a shared credit pool purchased at the contract level. There are no per-seat caps by default. When the pool is exhausted, advanced features pause unless owners enable overages or buy more credits through the account team. Credit expiration is defined in the order form.

source · verified 2026-10-18

Public USD price per credit not published by vendor.

GPT-6.1 Sol, GPT-6 Astra, GPT-6 Sol, GPT-6 Luna, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, GPT-5.3-Codex, GPT-5.2, GPT-Image-2

source · verified 2026-10-18

Work and Codex credit-rate models for credit-based Edu. Ultrafast credit rates apply on eligible Edu plans. GPT-Rosalind-Research is select Enterprise only and is omitted. Daybreak and GPT-6 Astra Law need separate approval and are omitted. Default enablement is not published on this page.

API Key

Audience: individual

Verified 2026-10-18

Get this plan (opens in a new tab)

Not published

source · verified 2026-10-18

not published by vendor. No monthly fee is stated. Pay for Codex usage based on API pricing.

No included subscription allowance is stated. Usage is billed at API pricing. Codex is available in the CLI, SDK, or IDE extension. Cloud features such as GitHub code review and Slack are not included.

source · verified 2026-10-18

The API price table is not published on this page.

All usage is pay-as-you-go at API rates. There is no included pool to exceed. ChatGPT-signed-in users can also run extra local chats with an API key after they hit plan limits, charged at standard API rates.

source · verified 2026-10-18

Model availability follows the API models available to your key.

source · verified 2026-10-18

A fixed model list is not published by vendor. GPT-5.5 retirement on October 14, 2026 does not apply to API-key Codex sessions.

Gemini CLI (Enterprise / API key only)

Open-source terminal AI agent for querying and editing large codebases, generating apps from images or PDFs, and automating workflows with Gemini.

Summary source · verified 2026-10-18

Gemini Code Assist Standard

Audience: team

Verified 2026-10-18

Price/mo (USD)
$22.80
source · verified 2026-10-18
Monthly commitment is $22.80 per license per month. 12-month commitment is $19.00 per license per month. The same page also lists $0.031232877 per hour (monthly commitment) and $0.026027397 per hour (12-month commitment). All subscriptions are billed monthly.
Usage limits
1500 maximum requests per user per day, combined with Gemini Code Assist agent mode. One prompt may count as multiple model requests. Daily limits are aggregated across model families (for example, Pro, Flash). Also limited per user per minute; the per-minute count is not published. Local codebase awareness quota: 1,000,000 token context window.
source · verified 2026-10-18
Quota page last updated 2026-10-13. No 5-hour or weekly cap is published. Developers Blog says Standard and Enterprise license access to Gemini CLI remains unchanged after June 18, 2026.
Overflow / pay-as-you-go
Once the daily maximum is reached, no further Gemini CLI or agent-mode requests can be made to any model until the quota resets. Most quotas can be adjusted by requesting a quota increase in the Google Cloud console.
source · verified 2026-10-18
Gemini CLI quota page also says that if daily limits are hit after upgrading, switch to pay-as-you-go with a Gemini API key or Vertex AI.
Models
Gemini model family as determined by Gemini CLI
source · verified 2026-10-18
Model-selection page lists Auto (Gemini 3): gemini-3-pro-preview and gemini-3-flash-preview; Auto (Gemini 2.5): gemini-2.5-pro and gemini-2.5-flash; Manual: any available model. Gemini 3 Pro for Standard requires the Preview release channel. Business page: Gemini 3 and a 1M token context window. Site banner: not optimized for Gemini 4 Argon.

Get this plan (opens in a new tab)

Gemini Code Assist Enterprise

Audience: enterprise

Verified 2026-10-18

Price/mo (USD)
$54
source · verified 2026-10-18
Monthly commitment is $54.00 per license per month. 12-month commitment is $45.00 per license per month. The same page also lists $0.073972603 per hour (monthly commitment) and $0.061643836 per hour (12-month commitment). All subscriptions are billed monthly. Pricing page says Enterprise includes increased daily usage limits for agent mode and Gemini CLI versus Standard.
Usage limits
2000 maximum requests per user per day, combined with Gemini Code Assist agent mode. One prompt may count as multiple model requests. Daily limits are aggregated across model families (for example, Pro, Flash). Also limited per user per minute; the per-minute count is not published. Local codebase awareness quota: 1,000,000 token context window.
source · verified 2026-10-18
Quota page last updated 2026-10-13. No 5-hour or weekly cap is published. Developers Blog says Enterprise license access to Gemini CLI remains unchanged after June 18, 2026.
Overflow / pay-as-you-go
Once the daily maximum is reached, no further Gemini CLI or agent-mode requests can be made to any model until the quota resets. Most quotas can be adjusted by requesting a quota increase in the Google Cloud console.
source · verified 2026-10-18
Gemini CLI quota page also says that if daily limits are hit after upgrading, switch to pay-as-you-go with a Gemini API key or Vertex AI.
Models
Gemini model family as determined by Gemini CLI
source · verified 2026-10-18
Model-selection page lists Auto (Gemini 3): gemini-3-pro-preview and gemini-3-flash-preview; Auto (Gemini 2.5): gemini-2.5-pro and gemini-2.5-flash; Manual: any available model. Gemini 3 Pro for Enterprise requires the Preview release channel. Business page: Gemini 3 and a 1M token context window. Site banner: not optimized for Gemini 4 Argon.

Get this plan (opens in a new tab)

Workspace AI Ultra

Audience: enterprise

Verified 2026-10-18

Price/mo (USD)
Not published
source · verified 2026-10-18
not published by vendor. The quota page links to https://workspace.google.com/products/ai-ultra/, which redirects to a Workspace AI page that does not list a USD price or Gemini CLI.
Usage limits
2000 maximum requests per user per day
source · verified 2026-10-18
Quota table row under Google Workspace. The same page's Gemini for workspace plans section says those plans do not apply to the API usage that powers Gemini CLI and that support is under consideration. Per-minute count, token caps, and 5-hour or weekly caps are not published for this row. Workspace AI Standard, Plus, and AI Expanded are stated as not supported.
Overflow / pay-as-you-go
Not published
source · verified 2026-10-18
not published by vendor
Models
Not published
source · verified 2026-10-18
not published by vendor

Get this plan (opens in a new tab)

Google Developer Program

Audience: team

Verified 2026-10-18

Price/mo (USD)
Not published
source · verified 2026-10-18
Plans card does not state a USD price. Linked Developer Program page lists Standard at no cost and Premium at $19.99/month included with Google AI Pro, and that page does not mention Gemini CLI.
Usage limits
Higher usage limits for Gemini CLI. Also lists access to Gemini Code Assist, Cloud and GenAI monthly credits, and use with a corporate Workspace account.
source · verified 2026-10-18
Numeric request, token, 5-hour, or weekly caps are not published. The linked Developer Program pricing page does not mention Gemini CLI; it lists $10 GenAI and Cloud monthly credit on Premium.
Overflow / pay-as-you-go
Not published
source · verified 2026-10-18
not published by vendor
Models
Not published
source · verified 2026-10-18
not published by vendor

Get this plan (opens in a new tab)

Gemini API key (unpaid)

Audience: individual

Verified 2026-10-18

Price/mo (USD)
$0
source · verified 2026-10-18
Described as a free tier when using a Gemini API key.
Usage limits
250 maximum model requests per user per day. Model requests to Flash model only.
source · verified 2026-10-18
Gemini API rate-limits page (updated 2026-10-15) does not publish numeric RPM, TPM, or RPD; it says limits vary by model and usage tier and are viewed in AI Studio. Spend-based limit per rolling 10 minutes: Free N/A. No 5-hour or weekly cap is published for CLI.
Overflow / pay-as-you-go
If daily request limits are hit, switch to pay-as-you-go with a paid Gemini API key or Vertex AI. With an API key you pay per token or call.
source · verified 2026-10-18
Developers Blog says Gemini CLI remains accessible via paid Gemini API keys. It does not say the unpaid API-key tier continues after June 18, 2026.
Models
Flash model only
source · verified 2026-10-18
No specific Flash model ID is published for this tier.

Try it (opens in a new tab)

Gemini API key (pay-as-you-go)

Audience: individual

Verified 2026-10-18

Price/mo (USD)
Not published
source · verified 2026-10-18
not a fixed monthly subscription. Cost varies by pricing tier and model and token usage. A single monthly USD price is not published. Plans page: pay as you go for privacy, higher rate limits, and access to advanced paid-only models.
Usage limits
Quota varies by pricing tier.
source · verified 2026-10-18
Quota table says Pay-as-you-go (Paid) maximum requests per user per day: Varies. Gemini API rate-limits page does not publish numeric RPM, TPM, or RPD. Spend-based limits per rolling 10 minutes: Tier 1 $10, Tier 2 $50, Tier 3 $200. Tier qualification dollar amounts are not published on that page.
Overflow / pay-as-you-go
You pay per token or call. This is described as the way to keep a workflow from stopping when a quota limit is reached.
source · verified 2026-10-18
Developers Blog: Gemini CLI remains accessible via paid Gemini API keys. Hitting a Gemini API spend limit returns 429 RESOURCE_EXHAUSTED; the rate-limits page says wait and retry, reduce request cost, or request a rate-limit increase.
Models
advanced paid only models
source · verified 2026-10-18
Plans page does not name the models. Gemini API pricing lists many models and per-1M-token prices; that page does not state which models Gemini CLI includes.

Get this plan (opens in a new tab)

Vertex AI (Express mode)

Audience: individual

Verified 2026-10-18

Price/mo (USD)
$0
source · verified 2026-10-18
New Google Cloud users can use express mode free for up to 90 days without billing, within quotas. Gemini CLI quota page says 90 days before billing must be enabled, and that quotas vary by account.
Usage limits
Free for up to 90 days. gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite, and gemini-2.5-flash-image: 10 requests per minute. gemini-3-pro-image, gemini-3.1-flash-image, gemini-3.1-pro-preview, and gemini-3-flash-preview: dynamic throughput.
source · verified 2026-10-18
These are Gemini Enterprise Agent Platform express-mode limits, which the Gemini CLI quota page links. The CLI quota table only says Express mode (Free) daily requests: Varies. No 5-hour or weekly cap is published.
Overflow / pay-as-you-go
Enabling billing removes the 90-day limit and increases quotas. After that you pay only for what you use.
source · verified 2026-10-18
Models
gemini-3-pro-image, gemini-3.1-flash-image, gemini-3.1-pro-preview, gemini-3-flash-preview, gemini-2.5-pro, gemini-2.5-flash-image, gemini-2.5-flash, gemini-2.5-flash-lite
source · verified 2026-10-18
Page says only these models are supported in express mode. Gemini CLI quota page says express-mode models vary by account and does not repeat this list.

Try it (opens in a new tab)

Vertex AI (pay-as-you-go)

Audience: enterprise

Verified 2026-10-18

Price/mo (USD)
Not published
source · verified 2026-10-18
not a fixed monthly subscription. Cost is based on model and token usage. A single monthly USD price is not published.
Usage limits
Quota is governed by a dynamic shared quota system or pre-purchased provisioned throughput.
source · verified 2026-10-18
Quota table says Vertex AI pay-as-you-go daily requests: Varies. Numeric RPM, token, 5-hour, and weekly caps are not published on the Gemini CLI quota page.
Overflow / pay-as-you-go
You pay based on model and token usage. Described as the flexible option when daily request limits or Gemini Pro quota are exhausted.
source · verified 2026-10-18
Developers Blog: Gemini CLI remains accessible via Gemini Enterprise Agent Platform API keys. Plans page lists enterprise security and compliance, Google Cloud terms, SLA, and regional data residency, with no prices.
Models
Not published
source · verified 2026-10-18
not published by vendor. CLI page says cost depends on the model but does not name models for regular-mode Vertex AI.

Get this plan (opens in a new tab)

Gemini CLI (Enterprise / API key only) plans
PlanPrice/mo (USD)Usage limitsOverflow / pay-as-you-goModels

Gemini Code Assist Standard

Audience: team

Verified 2026-10-18

Get this plan (opens in a new tab)

$22.80

source · verified 2026-10-18

Monthly commitment is $22.80 per license per month. 12-month commitment is $19.00 per license per month. The same page also lists $0.031232877 per hour (monthly commitment) and $0.026027397 per hour (12-month commitment). All subscriptions are billed monthly.

1500 maximum requests per user per day, combined with Gemini Code Assist agent mode. One prompt may count as multiple model requests. Daily limits are aggregated across model families (for example, Pro, Flash). Also limited per user per minute; the per-minute count is not published. Local codebase awareness quota: 1,000,000 token context window.

source · verified 2026-10-18

Quota page last updated 2026-10-13. No 5-hour or weekly cap is published. Developers Blog says Standard and Enterprise license access to Gemini CLI remains unchanged after June 18, 2026.

Once the daily maximum is reached, no further Gemini CLI or agent-mode requests can be made to any model until the quota resets. Most quotas can be adjusted by requesting a quota increase in the Google Cloud console.

source · verified 2026-10-18

Gemini CLI quota page also says that if daily limits are hit after upgrading, switch to pay-as-you-go with a Gemini API key or Vertex AI.

Gemini model family as determined by Gemini CLI

source · verified 2026-10-18

Model-selection page lists Auto (Gemini 3): gemini-3-pro-preview and gemini-3-flash-preview; Auto (Gemini 2.5): gemini-2.5-pro and gemini-2.5-flash; Manual: any available model. Gemini 3 Pro for Standard requires the Preview release channel. Business page: Gemini 3 and a 1M token context window. Site banner: not optimized for Gemini 4 Argon.

Gemini Code Assist Enterprise

Audience: enterprise

Verified 2026-10-18

Get this plan (opens in a new tab)

$54

source · verified 2026-10-18

Monthly commitment is $54.00 per license per month. 12-month commitment is $45.00 per license per month. The same page also lists $0.073972603 per hour (monthly commitment) and $0.061643836 per hour (12-month commitment). All subscriptions are billed monthly. Pricing page says Enterprise includes increased daily usage limits for agent mode and Gemini CLI versus Standard.

2000 maximum requests per user per day, combined with Gemini Code Assist agent mode. One prompt may count as multiple model requests. Daily limits are aggregated across model families (for example, Pro, Flash). Also limited per user per minute; the per-minute count is not published. Local codebase awareness quota: 1,000,000 token context window.

source · verified 2026-10-18

Quota page last updated 2026-10-13. No 5-hour or weekly cap is published. Developers Blog says Enterprise license access to Gemini CLI remains unchanged after June 18, 2026.

Once the daily maximum is reached, no further Gemini CLI or agent-mode requests can be made to any model until the quota resets. Most quotas can be adjusted by requesting a quota increase in the Google Cloud console.

source · verified 2026-10-18

Gemini CLI quota page also says that if daily limits are hit after upgrading, switch to pay-as-you-go with a Gemini API key or Vertex AI.

Gemini model family as determined by Gemini CLI

source · verified 2026-10-18

Model-selection page lists Auto (Gemini 3): gemini-3-pro-preview and gemini-3-flash-preview; Auto (Gemini 2.5): gemini-2.5-pro and gemini-2.5-flash; Manual: any available model. Gemini 3 Pro for Enterprise requires the Preview release channel. Business page: Gemini 3 and a 1M token context window. Site banner: not optimized for Gemini 4 Argon.

Workspace AI Ultra

Audience: enterprise

Verified 2026-10-18

Get this plan (opens in a new tab)

Not published

source · verified 2026-10-18

not published by vendor. The quota page links to https://workspace.google.com/products/ai-ultra/, which redirects to a Workspace AI page that does not list a USD price or Gemini CLI.

2000 maximum requests per user per day

source · verified 2026-10-18

Quota table row under Google Workspace. The same page's Gemini for workspace plans section says those plans do not apply to the API usage that powers Gemini CLI and that support is under consideration. Per-minute count, token caps, and 5-hour or weekly caps are not published for this row. Workspace AI Standard, Plus, and AI Expanded are stated as not supported.

Not published

source · verified 2026-10-18

not published by vendor

Not published

source · verified 2026-10-18

not published by vendor

Google Developer Program

Audience: team

Verified 2026-10-18

Get this plan (opens in a new tab)

Not published

source · verified 2026-10-18

Plans card does not state a USD price. Linked Developer Program page lists Standard at no cost and Premium at $19.99/month included with Google AI Pro, and that page does not mention Gemini CLI.

Higher usage limits for Gemini CLI. Also lists access to Gemini Code Assist, Cloud and GenAI monthly credits, and use with a corporate Workspace account.

source · verified 2026-10-18

Numeric request, token, 5-hour, or weekly caps are not published. The linked Developer Program pricing page does not mention Gemini CLI; it lists $10 GenAI and Cloud monthly credit on Premium.

Not published

source · verified 2026-10-18

not published by vendor

Not published

source · verified 2026-10-18

not published by vendor

Gemini API key (unpaid)

Audience: individual

Verified 2026-10-18

Try it (opens in a new tab)

$0

source · verified 2026-10-18

Described as a free tier when using a Gemini API key.

250 maximum model requests per user per day. Model requests to Flash model only.

source · verified 2026-10-18

Gemini API rate-limits page (updated 2026-10-15) does not publish numeric RPM, TPM, or RPD; it says limits vary by model and usage tier and are viewed in AI Studio. Spend-based limit per rolling 10 minutes: Free N/A. No 5-hour or weekly cap is published for CLI.

If daily request limits are hit, switch to pay-as-you-go with a paid Gemini API key or Vertex AI. With an API key you pay per token or call.

source · verified 2026-10-18

Developers Blog says Gemini CLI remains accessible via paid Gemini API keys. It does not say the unpaid API-key tier continues after June 18, 2026.

Flash model only

source · verified 2026-10-18

No specific Flash model ID is published for this tier.

Gemini API key (pay-as-you-go)

Audience: individual

Verified 2026-10-18

Get this plan (opens in a new tab)

Not published

source · verified 2026-10-18

not a fixed monthly subscription. Cost varies by pricing tier and model and token usage. A single monthly USD price is not published. Plans page: pay as you go for privacy, higher rate limits, and access to advanced paid-only models.

Quota varies by pricing tier.

source · verified 2026-10-18

Quota table says Pay-as-you-go (Paid) maximum requests per user per day: Varies. Gemini API rate-limits page does not publish numeric RPM, TPM, or RPD. Spend-based limits per rolling 10 minutes: Tier 1 $10, Tier 2 $50, Tier 3 $200. Tier qualification dollar amounts are not published on that page.

You pay per token or call. This is described as the way to keep a workflow from stopping when a quota limit is reached.

source · verified 2026-10-18

Developers Blog: Gemini CLI remains accessible via paid Gemini API keys. Hitting a Gemini API spend limit returns 429 RESOURCE_EXHAUSTED; the rate-limits page says wait and retry, reduce request cost, or request a rate-limit increase.

advanced paid only models

source · verified 2026-10-18

Plans page does not name the models. Gemini API pricing lists many models and per-1M-token prices; that page does not state which models Gemini CLI includes.

Vertex AI (Express mode)

Audience: individual

Verified 2026-10-18

Try it (opens in a new tab)

$0

source · verified 2026-10-18

New Google Cloud users can use express mode free for up to 90 days without billing, within quotas. Gemini CLI quota page says 90 days before billing must be enabled, and that quotas vary by account.

Free for up to 90 days. gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite, and gemini-2.5-flash-image: 10 requests per minute. gemini-3-pro-image, gemini-3.1-flash-image, gemini-3.1-pro-preview, and gemini-3-flash-preview: dynamic throughput.

source · verified 2026-10-18

These are Gemini Enterprise Agent Platform express-mode limits, which the Gemini CLI quota page links. The CLI quota table only says Express mode (Free) daily requests: Varies. No 5-hour or weekly cap is published.

Enabling billing removes the 90-day limit and increases quotas. After that you pay only for what you use.

source · verified 2026-10-18

gemini-3-pro-image, gemini-3.1-flash-image, gemini-3.1-pro-preview, gemini-3-flash-preview, gemini-2.5-pro, gemini-2.5-flash-image, gemini-2.5-flash, gemini-2.5-flash-lite

source · verified 2026-10-18

Page says only these models are supported in express mode. Gemini CLI quota page says express-mode models vary by account and does not repeat this list.

Vertex AI (pay-as-you-go)

Audience: enterprise

Verified 2026-10-18

Get this plan (opens in a new tab)

Not published

source · verified 2026-10-18

not a fixed monthly subscription. Cost is based on model and token usage. A single monthly USD price is not published.

Quota is governed by a dynamic shared quota system or pre-purchased provisioned throughput.

source · verified 2026-10-18

Quota table says Vertex AI pay-as-you-go daily requests: Varies. Numeric RPM, token, 5-hour, and weekly caps are not published on the Gemini CLI quota page.

You pay based on model and token usage. Described as the flexible option when daily request limits or Gemini Pro quota are exhausted.

source · verified 2026-10-18

Developers Blog: Gemini CLI remains accessible via Gemini Enterprise Agent Platform API keys. Plans page lists enterprise security and compliance, Google Cloud terms, SLA, and regional data residency, with no prices.

Not published

source · verified 2026-10-18

not published by vendor. CLI page says cost depends on the model but does not name models for regular-mode Vertex AI.

More pages