24 plans · 8 products
Read from provider pages
AI coding plans compared
AI coding plans cost $8 to $500 a month across the 24 plans and 8 products we read from provider pages between October 16, 2026 and October 26, 2026. The cheapest is ChatGPT Go. The strongest model any plan includes, by BenchLM's coding score, is Claude Sonnet 5.5 (84.5, #1 of 154), from Claude Pro at $20. Most providers publish multiples or credits rather than a token cap, so the table shows each plan's meter as published.
Coding plans by monthly price
The coding score is the strongest model the provider lists for the plan, on BenchLM's coding leaderboard. The last numeric column is the plan price divided by that model's API output rate: arithmetic on list prices, not the plan's allowance.
| Plan | Price | Strongest model (coding score) | Coding tool | Published limits | Price in API output tokens | Source |
|---|---|---|---|---|---|---|
| ChatGPT GoOpenAICodex usage limits | $8/month | GPT-5.6 Terra61.8 · #16 of 154 | Codex | More messages with tools, more uploads, more image creation, more voice chats and longer memory than Free; limited Codex access, allowance not itemized on the page.5-hour window | 0.7M | ChatGPT: Codex pricing and plans Read 2026-10-16 |
| OpenCode GoOpenCode | $10/month | Gemini 4 Argon73.2 · #6 of 154Also lists Kimi K3.1 Pro (not yet scored) | OpenCode (single-member workspaces) | Per-model monthly allowances in dollars of usage; 20% of a model's monthly allowance is available per five hours and 50% per week.5-hour window, weekly cap | 1M | OpenCode Go docs Read 2026-10-26 |
| GLM Coding Plan LiteZ.ai | $18/month ($12.6/month billed annually) | GLM-5.356.2 · #29 of 154 | Bring your own tool: Claude Code, Codex, OpenCode, Cline and 20+ agent tools, plus Z.ai ZCode | 10,000 credits a week and 2,000 credits per five hours; credits are charged per token, so the token allowance depends on the model and the cache hit rate.5-hour window, weekly cap | No list price | GLM Coding Plan Read 2026-10-26 |
| Kimi PlusMoonshot AI | $19/month ($15/month billed annually) | Kimi K359 · #22 of 154 | Kimi Code (CLI, desktop and IDE plugins) | Kimi Code with a rolling five-hour limit and a monthly total quota, and no weekly limit; agent credits come from one monthly pool. Moonshot does not publish the quota in numbers.5-hour window, no weekly cap | 1.3M | Kimi membership pricing Read 2026-10-26 |
| Google AI ProGoogle | $19.99/month | Gemini 4 Argon73.2 · #6 of 154 | Jules and Google Antigravity (entry rate limits) | 4x the usage limits of Free. Usage limits in the Gemini app are compute-based (prompt complexity, features used and chat length count) and refresh every 5 hours until the weekly limit is reached.5-hour window, weekly cap | 2M | Gemini subscriptions (United States) Read 2026-10-21 |
| ChatGPT PlusOpenAICodex usage limits | $20/month | GPT-6 Astra75.5 · #4 of 154 | Codex | Estimated local Codex messages per five-hour window: 5 to 45 with GPT-6 Astra, 15 to 160 with GPT-6.1 Sol, 15 to 150 with GPT-6 Sol, 350 to 3,000 with GPT-6 Luna; weekly limits may also apply.5-hour window | 0.4M | ChatGPT: Codex pricing and plans Read 2026-10-16 |
| Claude ProAnthropicClaude plans in full | $20/month ($17/month billed annually) | Claude Sonnet 5.584.5 · #1 of 154 | Claude Code (terminal, IDE, desktop and web) | At least 5x more usage per five-hour session than Free, plus a weekly limit on paid plans.5-hour window, weekly cap | 2M | Claude pricing Read 2026-10-16 |
| MiniMax M Plan GoMiniMax | $22/month ($18.33/month billed annually) | MiniMax M3.1 Flash58.9 · #23 of 154 | MiniMax Code, plus an API key for Claude Code, Codex, Cursor, OpenCode and other tools | The base tier; MiniMax does not publish the quota in numbers.Not published | 37M | MiniMax M Plan Read 2026-10-26 |
| Kimi ProMoonshot AI | $39/month ($31/month billed annually) | Kimi K359 · #22 of 154Also lists Kimi K3.1 Pro (not yet scored) | Kimi Code (CLI, desktop and IDE plugins) | 2x agent credits. Kimi Code with a rolling five-hour limit and a monthly total quota, and no weekly limit; agent credits come from one monthly pool. Moonshot does not publish the quota in numbers.5-hour window, no weekly cap | 2.6M | Kimi membership pricing Read 2026-10-26 |
| OpenCode Go PlusOpenCode | $40/month | Gemini 4 Argon73.2 · #6 of 154Also lists Kimi K3.1 Pro (not yet scored) | OpenCode (single-member workspaces) | Higher per-model allowances than Go across the same models, with the same five-hour (20%) and weekly (50%) shares.5-hour window, weekly cap | 4M | OpenCode Go docs Read 2026-10-26 |
| Alibaba Model Studio Coding Plan ProAlibaba Cloud | $50/month | Qwen3.7 Plus40.5 · #68 of 154 | API key for Claude Code, OpenCode, Cursor, Codex, Qwen Code, Cline and other tools; interactive use only | Up to 6,000 requests per five hours, 45,000 a week and 90,000 a month; Alibaba says a simple task uses 5 to 10 model calls and a complex one 10 to 30 or more.5-hour window, weekly cap | No list price | Alibaba Cloud Coding Plan overview Read 2026-10-26 |
| MiniMax M Plan ExploreMiniMax | $55/month ($45.83/month billed annually) | MiniMax M3.1 Flash58.9 · #23 of 154 | MiniMax Code, plus an API key for Claude Code, Codex, Cursor, OpenCode and other tools | 3x Go usage.Not published | 92M | MiniMax M Plan Read 2026-10-26 |
| GLM Coding Plan ProZ.ai | $80/month ($56/month billed annually) | GLM-5.356.2 · #29 of 154 | Bring your own tool: Claude Code, Codex, OpenCode, Cline and 20+ agent tools, plus Z.ai ZCode | 6x Lite usage: 60,000 credits a week and 12,000 per five hours.5-hour window, weekly cap | No list price | GLM Coding Plan Read 2026-10-26 |
| Kimi MaxMoonshot AI | $99/month ($79/month billed annually) | Kimi K359 · #22 of 154Also lists Kimi K3.1 Pro (not yet scored) | Kimi Code (CLI, desktop and IDE plugins) | 5x agent credits. Kimi Code with a rolling five-hour limit and a monthly total quota, and no weekly limit; agent credits come from one monthly pool. Moonshot does not publish the quota in numbers.5-hour window, no weekly cap | 6.6M | Kimi membership pricing Read 2026-10-26 |
| Google AI Ultra 5xGoogle | $99.99/month | Gemini 4 Argon73.2 · #6 of 154 | Jules and Google Antigravity (higher rate limits) | 5x the usage limits of Google AI Pro. Usage limits in the Gemini app are compute-based (prompt complexity, features used and chat length count) and refresh every 5 hours until the weekly limit is reached.5-hour window, weekly cap | 10M | Gemini subscriptions (United States) Read 2026-10-21 |
| ChatGPT Pro 100OpenAICodex usage limits | $100/month | GPT-6 Astra75.5 · #4 of 154 | Codex | The lowest Pro allowance; OpenAI publishes no multiple of Plus. The Codex pricing page says Pro plans currently have no five-hour limit and gives no Pro message estimates. Ultrafast is not included.Not published | 2M | ChatGPT: Codex pricing and plans Read 2026-10-16 |
| Claude Max 5xAnthropicClaude plans in full | $100/month | Claude Sonnet 5.584.5 · #1 of 154 | Claude Code (terminal, IDE, desktop and web) | 5x more usage per five-hour session than Pro, higher output limits, priority access during high-traffic periods, and a weekly limit across all models.5-hour window, weekly cap | 10M | Claude Help: What is the Max plan Read 2026-10-16 |
| MiniMax M Plan BuildMiniMax | $132/month ($110/month billed annually) | MiniMax M3.1 Flash58.9 · #23 of 154 | MiniMax Code, plus an API key for Claude Code, Codex, Cursor, OpenCode and other tools | 7.5x Go usage, with priority access during peak hours.Not published | 220M | MiniMax M Plan Read 2026-10-26 |
| GLM Coding Plan MaxZ.ai | $168/month ($118/month billed annually) | GLM-5.356.2 · #29 of 154 | Bring your own tool: Claude Code, Codex, OpenCode, Cline and 20+ agent tools, plus Z.ai ZCode | 14x Lite usage: 140,000 credits a week and 28,000 per five hours.5-hour window, weekly cap | No list price | GLM Coding Plan Read 2026-10-26 |
| Kimi UltraMoonshot AI | $199/month ($159/month billed annually) | Kimi K359 · #22 of 154Also lists Kimi K3.1 Pro (not yet scored) | Kimi Code (CLI, desktop and IDE plugins) | 10x agent credits. Kimi Code with a rolling five-hour limit and a monthly total quota, and no weekly limit; agent credits come from one monthly pool. Moonshot does not publish the quota in numbers.5-hour window, no weekly cap | 13M | Kimi membership pricing Read 2026-10-26 |
| Google AI Ultra 20xGoogle | $200/month | Gemini 4 Argon73.2 · #6 of 154 | Jules and Google Antigravity (highest rate limits) | 20x the usage limits of Google AI Pro. Usage limits in the Gemini app are compute-based (prompt complexity, features used and chat length count) and refresh every 5 hours until the weekly limit is reached.5-hour window, weekly cap | 20M | Gemini subscriptions (United States) Read 2026-10-21 |
| ChatGPT Pro 200OpenAICodex usage limits | $200/month | GPT-6 Astra75.5 · #4 of 154 | Codex | More usage than Pro 100; OpenAI publishes no multiple of Plus. New Pro 200 subscriptions not eligible for grandfathering get a lower allowance than previously offered. Pro plans currently have no five-hour limit. Ultrafast is not included.Not published | 4M | ChatGPT: Codex pricing and plans Read 2026-10-16 |
| Claude Max 20xAnthropicClaude plans in full | $200/month | Claude Sonnet 5.584.5 · #1 of 154 | Claude Code (terminal, IDE, desktop and web) | 20x more usage per five-hour session than Pro, higher output limits, priority access during high-traffic periods, and a weekly limit across all models.5-hour window, weekly cap | 20M | Claude Help: What is the Max plan Read 2026-10-16 |
| ChatGPT Pro 500OpenAICodex usage limits | $500/month | GPT-6 Astra75.5 · #4 of 154 | Codex | The highest included usage of the three Pro plans. Ultrafast for GPT-6 Astra and GPT-6.1 Sol uses included usage at 8x the Standard rate, then credits at 6x. Pro plans currently have no five-hour limit.Not published | 10M | ChatGPT: Codex pricing and plans Read 2026-10-16 |
Plan notes: promotions, regions and what changed (22)
- OpenCode Go: Allowances are per model, in dollars of usage per month; for example $15 for Kimi K3.1 Pro or GLM-5.3 and $60 for GLM-5.3-Flash on the usage table. Free models stay available after a limit.
- GLM Coding Plan Lite: Five-hour credit figures and the credit formula are from the GLM Coding Plan overview (https://docs.z.ai/devpack/overview): credits = (input tokens x 6.9 + cached input x 1.7 + output x 24) / 10,000 for GLM-5.3, and a third of that for GLM-5.3-Flash. Peak hours are 14:00-18:00 UTC+8 on weekdays.
- Kimi Plus: Kimi Code limits are from the Kimi Code membership benefits page (https://www.kimi.com/en/help/kimi-code/benefits). The Go plan has no Kimi Code quota and is not listed. Chinese-mainland prices are in CNY and differ.
- Google AI Pro: Read from Google's United States subscriptions page; Google sets plan prices by country, and its plan pages show a reader the prices for their own region.
- ChatGPT Plus: Codex local message estimates per five-hour window from the same page
- MiniMax M Plan Go: First month 50% off until Oct 31, 2026 (UTC+8). MiniMax publishes the tiers as multiples of Go usage, not as request or token counts.
- Kimi Pro: Kimi Code limits are from the Kimi Code membership benefits page (https://www.kimi.com/en/help/kimi-code/benefits). The Go plan has no Kimi Code quota and is not listed. Chinese-mainland prices are in CNY and differ.
- OpenCode Go Plus: Allowances are per model, in dollars of usage per month; for example $15 for Kimi K3.1 Pro or GLM-5.3 and $60 for GLM-5.3-Flash on the usage table. Free models stay available after a limit.
- Alibaba Model Studio Coding Plan Pro: Non-refundable. The Lite plan closed to new subscribers on March 20, 2026. The plan key may not power scripts or application backends.
- MiniMax M Plan Explore: First month 50% off until Oct 31, 2026 (UTC+8). MiniMax publishes the tiers as multiples of Go usage, not as request or token counts.
- GLM Coding Plan Pro: Five-hour credit figures and the credit formula are from the GLM Coding Plan overview (https://docs.z.ai/devpack/overview): credits = (input tokens x 6.9 + cached input x 1.7 + output x 24) / 10,000 for GLM-5.3, and a third of that for GLM-5.3-Flash. Peak hours are 14:00-18:00 UTC+8 on weekdays.
- Kimi Max: Kimi Code limits are from the Kimi Code membership benefits page (https://www.kimi.com/en/help/kimi-code/benefits). The Go plan has no Kimi Code quota and is not listed. Chinese-mainland prices are in CNY and differ.
- Google AI Ultra 5x: Read from Google's United States subscriptions page; Google sets plan prices by country, and its plan pages show a reader the prices for their own region.
- ChatGPT Pro 100: Plan renamed from the earlier Pro 5x listing; the 5x multiple is no longer published. Plan names, the Pro 200 grandfathering terms and the Ultrafast rates are from OpenAI Help, About ChatGPT Pro tiers (help.openai.com/en/articles/9793128), read the same day.
- Claude Max 5x: Max includes $100 a month in Claude Platform API credits for the subscriber's own apps (Messages and Batches API, Console Playground, Managed Agents, Agent SDK). The credits do not apply to Claude, interactive Claude Code or usage credits and do not roll over; source: Claude Help, Monthly API credits for Max and Team plans.
- MiniMax M Plan Build: First month 50% off until Oct 31, 2026 (UTC+8). MiniMax publishes the tiers as multiples of Go usage, not as request or token counts.
- GLM Coding Plan Max: Five-hour credit figures and the credit formula are from the GLM Coding Plan overview (https://docs.z.ai/devpack/overview): credits = (input tokens x 6.9 + cached input x 1.7 + output x 24) / 10,000 for GLM-5.3, and a third of that for GLM-5.3-Flash. Peak hours are 14:00-18:00 UTC+8 on weekdays.
- Kimi Ultra: Kimi Code limits are from the Kimi Code membership benefits page (https://www.kimi.com/en/help/kimi-code/benefits). The Go plan has no Kimi Code quota and is not listed. Chinese-mainland prices are in CNY and differ.
- Google AI Ultra 20x: Read from Google's United States subscriptions page; Google sets plan prices by country, and its plan pages show a reader the prices for their own region.
- ChatGPT Pro 200: Subscribers active on Pro 200 between September 22 and September 29, 2026 keep the previous allowance through October 29, 2026; the price stays $200. Plan names, the Pro 200 grandfathering terms and the Ultrafast rates are from OpenAI Help, About ChatGPT Pro tiers (help.openai.com/en/articles/9793128), read the same day.
- Claude Max 20x: Max includes $200 a month in Claude Platform API credits for the subscriber's own apps (Messages and Batches API, Console Playground, Managed Agents, Agent SDK). The credits do not apply to Claude, interactive Claude Code or usage credits and do not roll over; source: Claude Help, Monthly API credits for Max and Team plans.
- ChatGPT Pro 500: Plan names, the Pro 200 grandfathering terms and the Ultrafast rates are from OpenAI Help, About ChatGPT Pro tiers (help.openai.com/en/articles/9793128), read the same day.
Each provider meters usage differently
Five-hour windows
Most plans cap usage in a rolling five-hour window. Claude, ChatGPT, Gemini, GLM, Kimi Code, Alibaba and OpenCode Go all publish one; the size of the window is usually a multiple or a credit count, not a token number.
Weekly and monthly caps
Claude, Gemini, GLM, Alibaba and OpenCode Go add a weekly cap on top of the window. Kimi Code has no weekly cap but a monthly total. Alibaba also caps the month at 90,000 requests.
What one unit buys
The meters differ: GLM charges credits per token, Alibaba counts requests (a task can use 5 to 30 or more), OpenCode Go gives dollars of usage per model, and Claude, Kimi and MiniMax publish multiples of a base tier.
Reset rules and what shares a limit live on the Claude usage-limits page and the Codex usage-limits page. This page does not show any account's remaining allowance.
Sources
- 01ChatGPT: Codex pricing and plansRead 2026-10-16
- 02OpenCode Go docsRead 2026-10-26
- 03GLM Coding PlanRead 2026-10-26
- 04Kimi membership pricingRead 2026-10-26
- 05Gemini subscriptions (United States)Read 2026-10-21
- 06Claude pricingRead 2026-10-16
- 07MiniMax M PlanRead 2026-10-26
- 08Alibaba Cloud Coding Plan overviewRead 2026-10-26
- 09Claude Help: What is the Max planRead 2026-10-16
API list rates from the BenchLM pricing registry, updated October 26, 2026.
Questions
What is an AI coding plan?
A monthly subscription that pays for model usage inside a coding tool, instead of per-token API billing. Some plans come with the provider's own tool, such as Claude Code, Codex, Kimi Code or MiniMax Code. Others give you an API key and base URL for tools you already run, such as Claude Code, OpenCode or Cline.
Which coding plan is cheapest?
ChatGPT Go at $8 a month is the lowest list price in the table. 7 plans cost $20 a month or less. A low price buys different things: dollars of usage per model, credits, requests or an unpublished multiple, so compare the meter as well as the price.
Which coding plan includes the strongest model?
By BenchLM's coding score, Claude Sonnet 5.5 (84.5) is the strongest model a plan in the table includes. The cheapest plan with it is Claude Pro at $20. A plan that lists a strong model can still give it a small share of the allowance, so check that model's limit on the provider page.
Are coding plans cheaper than the API?
It depends on your usage, and most providers do not publish plan limits in tokens. The table shows how many output tokens each plan price buys at API list rates. A real API bill also counts input tokens, which coding agents send in volume, so price your own input and output mix before comparing.
Do these plans work with Claude Code?
Claude Pro and Max include Claude Code. The GLM Coding Plan, MiniMax M Plan and Alibaba's Coding Plan each publish an Anthropic-compatible endpoint, so Claude Code can run their models with the plan's key. Kimi Code and OpenCode Go use their own tools.