Coding plans · prices from vendor pages, fetched 2026-10-30

Which AI coding plan should you buy?

Ten plans compared on price, free tier, models, platforms, stability and value. Speed is not independently benchmarked for any consumer plan here.

The short answer

Platform
Price

10 of 10 plans shown

Compare the plans

Each card shows price, what you get, platforms and a pricing link. Open the card for models, speed, stability and value.

Claude Code

Anthropic

Price

Pro $17/mo billed annually ($200 up front), $20 billed monthly · Max $100/mo · Ultra $200/mo

Free: $0, chat on web, desktop and mobile; Claude Code is listed under Pro

Claude Code in the terminal, VS Code, JetBrains, desktop app and web, included from Pro up

Platforms
  • app
  • web
  • CLI
  • IDE
  • Anthropic
  • Subscription
  • Terminal
Pricing →
Models, speed, stability, value
Models
  • Free: chat on web, desktop and mobile (model list not verified from the vendor page)
  • Pro and above: more Claude models (named list not verified)
  • Claude Fable 5 appears on the status page in an Oct 21 incident

Speed Speed is not independently benchmarked for this plan. See the stability note below for the status history.

Stability Status page (status.claude.com/history): Oct 16, 17, 18 and 19 show no reported incidents. Oct 21: investigating elevated errors on requests to Claude Fable 5, 20:29 UTC, resolved. The history page shows 25 incidents for the August to October window.

Value Good fit if you want Claude Code in the terminal or your editor and are ready to pay from the Pro tier.

GitHub Copilot

GitHub

Price

Free $0 · Pro $10/mo · Pro+ $39/mo · Max $100/mo

Free: $0, limited chat and agent usage

Editor, CLI and GitHub assistance, with agent mode on every plan

Platforms
  • app
  • web
  • CLI
  • IDE
  • GitHub
  • Editor and CLI
  • Credits
Pricing →
Models, speed, stability, value
Models
  • Model list not verified from the vendor page
  • Agent mode on all plans in VS Code, Visual Studio, JetBrains, Eclipse and Xcode
  • MCP server integration on Free, Pro and Pro+
  • GitHub AI Credits: Pro $15/mo (base $10, flex $5); Pro+ $70/mo (base $39, flex $31); Max $200/mo (base $100, flex $100)

Speed Speed is not independently benchmarked for this plan. See the stability note below for the only status facts we have.

Stability Status page (githubstatus.com/history): Oct 30 shows two incidents (17:50 to 19:23 UTC on Actions, Pages and Webhooks; 14:31 to 15:02 UTC general disruption) plus one under investigation. Sep 28: Copilot Code Review unable to complete reviews, about 70% of requested reviews did not complete.

Value A $10 Pro plan covers editors, CLI and GitHub, which makes it a simple budget pick if you already work on GitHub.

Cursor

Sold by X Subscription Corp

Price

Free $0 · Plus $8/mo · Premium $30/mo · Super $100/mo · Ultra $200/mo

Free: $0, limited agent and Chat requests

A shared usage pool; Plus includes only Grok models

Platforms

Not stated on the vendor page

  • Grok models
  • Usage pool
Pricing →
Models, speed, stability, value
Models
  • Plus: only Grok models are available on this plan
  • Premium: latest Grok models, cloud agents and automations. Super and Ultra add usage multipliers
  • Third-party models at API list price, billed separately from the monthly price

Speed Speed is not independently benchmarked for this plan. No measured data in our sources.

Stability no status data from the vendor page. The Cursor status link resolves to an xAI status page, so no Cursor uptime is claimed.

Value Pick it if you want Grok models on a paid tier. Cursor is now sold by X Subscription Corp, and its base plans list Grok models.

Windsurf

Devin/Cognition

Price

Free $0 · Pro $20/mo · Max $200/mo · Teams $80/mo + $40 per seat

Free: $0, light quota to code with agents

A light quota to code with agents, with frontier models and Devin Cloud on Pro

Platforms

Not stated on the vendor page

  • Devin
  • Frontier models
Pricing →
Models, speed, stability, value
Models
  • Free: limited model availability
  • Pro: frontier models from OpenAI, Claude, Gemini and SpaceXAI, plus leading open source models
  • Pro: full model availability and Devin Cloud access
  • Extra usage can be purchased at API pricing

Speed Speed is not independently benchmarked for this plan. No measured data in our sources.

Stability no status data from the vendor page

Value A $20 Pro plan adds frontier models from several vendors and Devin Cloud access; Max at $200 offers significantly higher quotas.

Cline

Cline

Price

Open Source plan: free for individual developers, you pay for inference only

Open Source plan: $0, bring your own key

Open-source VS Code extension, CLI and desktop app; pay only for inference

Platforms
  • app
  • CLI
  • IDE
  • BYOK
  • Open source
  • VS Code
Pricing →
Models, speed, stability, value
Models
  • Whatever you bring: BYOK supported
  • Providers named on the pricing page: Anthropic, Gemini, OpenAI, OpenRouter, AWS Bedrock, GCP Vertex, Groq, Cerebras, Vercel AI Gateway, DeepSeek and more
  • Enterprise: custom, with SSO, SLA and a JetBrains extension

Speed Speed is not independently benchmarked for this plan. No measured data in our sources.

Stability no status data from the vendor page

Value Best value if you want to pay only for inference and bring your own key; the Open Source plan itself is free for individuals.

Zed

Zed

Price

Personal $0 · Pro $10/mo · Business $30 per seat per month

Personal: $0 forever, unlimited with your own keys or external agents

Editor that runs your own API keys or external agents such as Claude Agent and Codex CLI

Platforms

Not stated on the vendor page

  • Editor
  • BYOK
  • Personal free
Pricing →
Models, speed, stability, value
Models
  • Personal: your own API keys or external agents such as Claude Agent, Codex CLI and more
  • Pro: unlimited edit predictions, $5 of tokens included, usage-based billing beyond that
  • Business: org-wide AI model policies; no fixed LLM credit allotment per seat

Speed Speed is not independently benchmarked for this plan. No measured data in our sources.

Stability no status data from the vendor page

Value Best value if you want a free editor and already hold API keys or external agents; Business adds org-wide controls at $30 a seat.

Kilo Code

Kilo

Price

Free & Open Source $0 · Teams $15/user/mo

Free & Open Source: $0, Auto Free is $0/mo with no hosted credit required

Open-source agentic coding in VS Code, JetBrains and the CLI

Platforms
  • CLI
  • IDE
  • Open source
  • Gateway
  • Teams
Pricing →
Models, speed, stability, value
Models
  • Auto Free: routes to free models through Kilo Gateway
  • BYOK, local models, pay-as-you-go through Kilo Gateway, or Kilo Pass
  • Works with any AI model; usage is billed separately

Speed Speed is not independently benchmarked for this plan. No measured data in our sources.

Stability no status data from the vendor page

Value Best value for a free start: the open-source extensions cost $0 and Auto Free needs no hosted credit.

OpenAI Codex

OpenAI

Price

Free $0 · Go $8/month · Plus $20/month · Pro from $100/month ($100, $200 or $500 tiers) · Business $20/user/month billed annually, $25 billed monthly · Enterprise and Edu: contact sales

Free: $0 with limited Codex access. Codex Cloud is not included on Free or Go.

Codex in the CLI, the IDE extension, the ChatGPT desktop and mobile apps, and on the web from Plus up

Platforms
  • app
  • web
  • CLI
  • IDE
  • OpenAI
  • Subscription
  • CLI and IDE
Pricing →
Models, speed, stability, value
Models
  • Codex models named on the pricing page: GPT-6 Astra, GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Sol, GPT-6 Luna, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna and GPT-Image-2
  • Plus usage estimates run 350 to 3,000 local GPT-6 Luna messages per five-hour period and 5 to 45 for GPT-6 Astra. These are estimates, not fixed limits, and weekly limits may also apply
  • Pro plans currently have no five-hour limit. Pro API credits are $100, $200 or $500 a month depending on the tier, and Ultrafast mode is on the $500 tier
  • Model changes: GPT-5.4 and GPT-5.4 mini were removed from Codex on August 31, 2026, and GPT-5.5 retired on October 14, 2026
  • The $8 Go price appears only on the Codex pricing page. openai.com/codex did show Plus, Pro and Business amounts, but it is client-rendered and returns 403 to a plain fetch, so we read its page text through an extractor and take the prices from the Codex pricing page at developers.openai.com

Speed Speed is not independently benchmarked for this plan. No vendor latency figure is published.

Stability status.openai.com read "We're fully operational" when fetched on 2026-10-30, with component uptimes such as 99.97% and 99.998%. No SLA was found for the consumer plans.

Value Plus at $20 a month includes Codex Cloud, and so does Business at $20 per user. The CLI also runs on an API key if you would rather pay per token.

xAI Grok

Sold by X Subscription Corp

Price

Free $0/month · Plus $8/month · Premium $30/month · Super $100/month · Ultra $200/month · Teams $30+/user/month · Enterprise custom

Free: $0 with limited chat requests and limited agent requests, plus posting, replying and following on X

Grok Chat, Voice, Imagine and Build, on a shared AI usage pool that refreshes weekly and covers Grok and Cursor alike. Plus is confirmed to include Build; which higher tiers include it is not verified

Platforms
  • app
  • web
  • X Subscription Corp
  • Free tier
  • Cursor included
Pricing →
Models, speed, stability, value
Models
  • Premium adds 4x the Plus usage, the latest Grok models, faster chat responses, code hosting and AI code reviews, and cloud agents and automations. Super is 15x Plus and Ultra is 50x
  • API usage is billed separately at standard model rates and does not draw from the plan pool
  • API rates under 200k context: grok-4.7 is $2.00 input, $0.50 cached and $6.00 output per 1M tokens, and grok-build-0.1 is $1.00, $0.20 and $2.00. Long context (200k and up) roughly doubles both
  • Which tier gets Grok Build is not unambiguous on the pricing page, and no absolute request caps are published, only multiples of Plus

Speed Speed is not independently benchmarked for this plan. No vendor latency figure is published.

Stability status.x.ai is reachable but showed no uptime percentage or SLA in the fetched page.

Value Plus at $8 a month is one of the cheapest entries here and bundles Cursor. The same seller, X Subscription Corp, now runs the Cursor plans on this page.

Antigravity

Google

Price

Individual $0 · Google AI Pro and AI Ultra price not verified

Individual: $0, generally available

Google agent app, CLI and IDE extensions; Gemini CLI and Gemini Code Assist have been replaced

Platforms
  • app
  • CLI
  • IDE
  • Google
  • Free tier
  • Successor to Gemini CLI
Pricing →
Models, speed, stability, value
Models
  • Individual: a variety of agent models (named list not from the vendor pages we checked)
  • Google AI Ultra: latest Gemini models
  • Business plan via Google Cloud, contact sales

Speed Speed is not independently benchmarked for this plan. No measured data in our sources.

Stability no status data from the vendor page

Value Individual is $0 and generally available; Gemini CLI and the Gemini Code Assist IDE extensions were replaced by Antigravity for unpaid-tier and Google One users on June 18, 2026.

Price band by platform

Read across to find what is cheap and runs where you code. Cells list providers with a plan in that band that includes the platform.

Price band by platform, providers listed per cell
Price bandAppWebCLIIDE
Free: $0 tier Claude (chat only), GitHub Copilot, Cline, Antigravity, xAI Grok, OpenAI Codex (limited) Claude (chat only), GitHub Copilot, xAI Grok GitHub Copilot, Cline, Kilo Code, Antigravity GitHub Copilot, Cline, Kilo Code, Antigravity
Budget: $8 to $20 a month Claude Code, GitHub Copilot, xAI Grok, OpenAI Codex Claude Code, GitHub Copilot, xAI Grok, OpenAI Codex Claude Code, GitHub Copilot, Kilo Code, OpenAI Codex Claude Code, GitHub Copilot, Kilo Code, OpenAI Codex
Premium: $30 a month and up Claude Code (Max, Ultra), GitHub Copilot (Pro+, Max), xAI Grok (Premium), OpenAI Codex (Pro) Claude Code (Max, Ultra), GitHub Copilot (Pro+, Max), xAI Grok (Premium), OpenAI Codex (Pro) Claude Code (Max, Ultra), GitHub Copilot (Pro+, Max), OpenAI Codex (Pro) Claude Code, GitHub Copilot, OpenAI Codex (Pro)
Price not verified Antigravity None listed in our sources Antigravity Antigravity

Kilo Code Teams at $15 per user and OpenAI Codex Business at $20 per seat sit in the budget row. Zed Business at $30 per seat and Windsurf Teams at $80 plus $40 per seat are team plans. xAI Grok is listed under App and Web only because its pricing page names no standalone CLI or IDE extension. Empty cells mean no listed plan.

Which plan is for me?

  1. 1

    Do you need to pay anything today?

  2. 2

    Is your budget under $20 a month?

  3. 3

    Do you code in a terminal or in an editor?

  4. 4

    Are you buying for a team?

  5. 5

    Check the rows marked price not verified

    • Antigravity: the Google AI Pro and AI Ultra prices are not verified here. Check the vendor page before buying.

API plans we run: the routes our own agents call

The plans above are consumer subscriptions with seats. These seven are API-first plans: you buy tokens, credits or monthly allowance, and you drive them from your own agent. They are the routes behind our own tooling, which is why we track them closely. Prices, limits and terms come from each vendor's own pages, fetched 2026-10-30. Model ids come from each provider's model catalogue the same day: six of the seven expose one over their API, and CommandCode's list comes from the catalogue its CLI cached that day.

Our call counts and success rates in the last card line are our own traffic over 30 days, not a vendor claim. Where a vendor does not publish latency, we say so rather than filling the gap with our own measurements, which would describe our prompts rather than the plan.

OpenCode Go

OpenCode

Price

Go $10/month · Go Plus $40/month · Go Teams $20 per member per month

Our traffic

2,414 calls in 30 days · 92.9% OK

  • Subscription
  • Token prices
  • Any agent
Free tier

No free plan on Go itself. Two models are listed as free with unlimited monthly usage, limited time: Beam Free and Iceman Contributor Free.

What you get

A curated model lineup with rolling quotas: 20% of each model's monthly allowance per 5 hours, 50% per week, 100% per month.

Speed

No vendor latency figure is published. Go publishes request budgets per 5-hour window instead, which is a quota, not a speed measure.

Stability

Status page (opencode.ai/status) read "All systems operational" when fetched on 2026-10-30. No uptime percentage or SLA is published.

Models, value and full plan details
Models
  • 28 model ids in the live catalog
  • Example per-1M-token rates: GLM-5.3-Flash input $0.15, output $0.50, cached read $0.03; Claude Haiku 5.5 (up to 100K tokens) input $0.10, output $0.50
  • Estimated requests per 5 hours on Go: Kimi K3.1 Pro 147, Gemini 4 Argon 440, GLM-5.3-Flash 6,320
  • Privacy: Muse Spark 1.3 and 1.2 Contributor are marked "Used" for training and "Not ZDR"; most other listed models are "Not used" with 0-day retention
Value

A flat monthly plan that reaches a mixed lineup of frontier and open models, and the only one of these seven whose fetched docs list retention per model.

What you get

A curated model lineup with rolling quotas: 20% of each model's monthly allowance per 5 hours, 50% per week, 100% per month. Token prices are identical on Go, Go Plus and Go Teams, so a higher plan buys more allowance, not a cheaper rate. Example monthly limits (Go / Go Plus / Go Teams): GLM-5.3-Flash $60 / $180 / $65, Claude Haiku 5.5 $15 / $60 / $20, DeepSeek V4.1 Flash $100 / $200 / $105.

Free tier

No free plan on Go itself. Two models are listed as free with unlimited monthly usage, limited time: Beam Free and Iceman Contributor Free. Beam Free is not served in some regions, including China, Russia, Iran and Nigeria.

Speed

No vendor latency figure is published. Go publishes request budgets per 5-hour window instead, which is a quota, not a speed measure.

Stability

Status page (opencode.ai/status) read "All systems operational" when fetched on 2026-10-30. No uptime percentage or SLA is published.

CommandCode

CommandCode

Price

Go $1/month + processing fee ($10 of credits included) · GOAT $10/month + fee (up to $100 credits) · Pro $20 (up to $110 credits) · Max $100/month + fee ($150 credits) · Max 20x $200/month ($300 credits) · Provider API $15/month + fee, pay as you go · Teams $40/month + fee · Enterprise custom

Our traffic

1,225 calls in 30 days · 95.8% OK

  • Subscription
  • Pay as you go
  • CLI and API
Free tier

Free models on every plan: Laguna S 2.1 and Beam 1.0 while capacity lasts, Glyph Cluster while the stealth preview lasts (up to 100 requests a day), and Ling 3.1 Flash 1019 (up to 100 requests a day) until 16:00 UTC on November 3.

What you get

Credits plus a monthly budget.

Speed

No vendor latency figure is published.

Stability

There is no public status page: https://commandcode.ai/status returns 404. An SLA is listed only under the Enterprise plan.

Models, value and full plan details
Models
  • 107 model ids in the CLI catalog
  • Example per-1M-token rate on Go: GLM-5.3 Flash input $0.15, output $0.50, cache read $0.03
  • Go carries open models plus some closed ones (GPT-5.6 Luna, Grok 4.5, Qwen Max and Plus, Muse Spark Contributor tiers)
  • The pricing page and the limits page disagree on Max request counts (~219K and ~437K on one, ~230K and ~370K on the other); both are shown here because we could not resolve which is current
Value

Go costs $1 a month and still covers a broad model list, and the Provider plan has no markup, which makes the API route the interesting one for volume work.

What you get

Credits plus a monthly budget. Go is the cheapest entry: $1 buys $10 of credits, with usage capped at $3 in any 5 hours, $6 in any 7 days and $10 per month. From 28 September 2026 new Go subscribers get per-model credits instead of the flat $10; existing subscribers keep the flat $10 until their next renewal. Go is the only plan without API access; every other plan can call the Provider API on OpenAI and Anthropic compatible endpoints.

Free tier

Free models on every plan: Laguna S 2.1 and Beam 1.0 while capacity lasts, Glyph Cluster while the stealth preview lasts (up to 100 requests a day), and Ling 3.1 Flash 1019 (up to 100 requests a day) until 16:00 UTC on November 3.

Speed

No vendor latency figure is published.

Stability

There is no public status page: https://commandcode.ai/status returns 404. An SLA is listed only under the Enterprise plan.

ClinePass

Cline

Price

$9.99/month, which may be promotional. The standard rate after the promotion period is not published

Our traffic

719 calls in 30 days · 96.0% OK

  • Subscription
  • Open-weight models
  • IDE and CLI
Free tier

No free credits are stated for ClinePass. The separate Cline extension, which bills per usage rather than by subscription, is free for individual developers.

What you get

A flat subscription over a curated set of open-weight coding models, with "2-5x the API rate limits" compared with the standard API rate.

Speed

No latency percentile is published. The vendor status dashboard showed the API health check "Healthy" at about 51ms when fetched on 2026-10-30, which is a single health-check reading rather than a p95.

Stability

status.cline.bot showed the API health check "Healthy" at about 51ms when fetched on 2026-10-30. No uptime percentage or SLA figure was found for ClinePass.

Models, value and full plan details
Models
  • 439 model ids in the api.cline.bot catalog, which is the general Cline API catalogue rather than the ClinePass plan itself
  • ClinePass serves its own curated set of 15 ids, all prefixed cline-pass/: deepseek-v4.1-flash-1017, deepseek-v4.1-flash, deepseek-v4-pro, glm-5.3-flash, glm-5.3, kimi-k3.1-pro, kimi-k3, muse-spark-1.3-contributor, minimax-m3.1-flash, minimax-m3, mimo-v2.6-pro, mimo-v2.6-flash, qwen3.7-max, qwen3.7-plus and qwen3.8-max
  • Those cline-pass/ prefixed ids do not appear in the 439-id catalogue, so the catalogue size is not the size of the plan
  • The marketing page and the docs list different sets: the docs say GLM-5.2, Kimi K2.6, Kimi K2.7 Code and DeepSeek V4 Flash are no longer available on ClinePass
  • Reference rate shown on the docs page: GLM 5.3 Flash input $0.15, output $0.50, cached read $0.03 per 1M
Value

A flat $9.99 a month subscription. The vendor describes the set as open-weight coding models, and it is far narrower than the 439 ids the API catalogue exposes.

What you get

A flat subscription over a curated set of open-weight coding models, with "2-5x the API rate limits" compared with the standard API rate. Limits run on three windows: 5-hour rolling, weekly and monthly. The exact caps are not published; usage is visible in the dashboard. The docs show reference API prices but state that you are not charged them on the subscription.

Free tier

No free credits are stated for ClinePass. The separate Cline extension, which bills per usage rather than by subscription, is free for individual developers.

Speed

No latency percentile is published. The vendor status dashboard showed the API health check "Healthy" at about 51ms when fetched on 2026-10-30, which is a single health-check reading rather than a p95.

Stability

status.cline.bot showed the API health check "Healthy" at about 51ms when fetched on 2026-10-30. No uptime percentage or SLA figure was found for ClinePass.

Token Harbor

Token Harbor

Price

Free $0/month · Agent Pass $1.99/month (first month $0.99) · Office Pass $9.99/month · Frontier Pass $99/month. Yearly prices were not published in the text we could read

Our traffic

633 calls in 30 days · 93.2% OK

  • Free tier
  • Published uptime
  • One endpoint
Free tier

Every account gets a free allowance that resets on a rolling 7-day period, including DeepSeek V4.1 Flash, MiMo V2.6 Flash and TH-Rudder. No card required.

What you get

Passes buy usage, not credit: Agent Pass $10 included usage with selected models boosted to $20 and 5% off pay-as-you-go; Office Pass $35 boosted to $70 and 10% off; Frontier Pass $180 boosted to $360 and 15% off.

Speed

The status page publishes 90-day p95 latency: 7.4s to first byte and 27s for a full response. Token Harbor is the only one of these seven with a published latency percentile.

Stability

90-day uptime from the status page: API Gateway 99.87%, web 99.96%, dashboard 99.98%, authentication 99.97%, database 99.69%, Rudder chat 100.00%. Twelve-month API Gateway uptime is 99.93%, and the gateway API success rate is 99.71% over 90 days.

Models, value and full plan details
Models
  • 75 model ids in the live catalog
  • Agent Pass adds DeepSeek V4.1 Flash 1017 and its Fast variant and Minimax M3.1 Flash
  • Office Pass adds Claude Sonnet 5.5, Grok 4.7 and Qwen3.8 Max
  • Frontier Pass adds Claude Fable 5.1, GPT-6 Astra and Claude Opus 5.5
  • The provider states: "No silent model swaps. The model ID you pass is exactly what runs."
Value

It has a standing free allowance on every account and it is the only one of these seven that publishes uptime figures. The CLI wires it into Claude Code, Codex CLI, Cursor and other agents in one command.

What you get

Passes buy usage, not credit: Agent Pass $10 included usage with selected models boosted to $20 and 5% off pay-as-you-go; Office Pass $35 boosted to $70 and 10% off; Frontier Pass $180 boosted to $360 and 15% off. A month is four 7-day windows, and when the allowance runs out calls pause until it resets unless you keep going from your balance.

Free tier

Every account gets a free allowance that resets on a rolling 7-day period, including DeepSeek V4.1 Flash, MiMo V2.6 Flash and TH-Rudder. No card required.

Speed

The status page publishes 90-day p95 latency: 7.4s to first byte and 27s for a full response. Token Harbor is the only one of these seven with a published latency percentile.

Stability

90-day uptime from the status page: API Gateway 99.87%, web 99.96%, dashboard 99.98%, authentication 99.97%, database 99.69%, Rudder chat 100.00%. Twelve-month API Gateway uptime is 99.93%, and the gateway API success rate is 99.71% over 90 days. No contractual SLA is stated.

Z.AI GLM Coding Plan

Z.AI

Price

Lite "starting at just 18 USD per month" · Pro and Max prices are not published on the official pages

Our traffic

40 calls in 30 days · 57.5% OK

  • Credits
  • Off-peak discount
  • Tool-only quota
Free tier

No free tier is stated for the Coding Plan. GLM-4.7-Flash and GLM-4.5-Flash are listed as free on the separate pay-as-you-go API pricing page, not as plan credits.

What you get

Credits on three windows.

Speed

No vendor latency figure is published. Off-peak credits are a price mechanism, not a speed guarantee.

Stability

No status page or SLA was found on the fetched official pages. The docs also conflict on the cancellation window: the usage policy says 3 days before the next billing date, the FAQ says 24 hours.

Models, value and full plan details
Models
  • 11 model ids in the live catalog
  • Every plan supports GLM-5.3 and GLM-5.3-Flash; requests for GLM-5.2 and GLM-5.1 are routed to GLM-5.3, and GLM-4.7 is routed to GLM-5.3-Flash
  • Credits only work inside officially supported tools, 20 or more of them, including ZCode, Claude Code, Codex, OpenCode, Cline and OpenClaw
  • Three official endpoints: Anthropic Messages, OpenAI Chat Completions and OpenAI Responses
Value

The quota model is the unusual part: you buy credits with per-model multipliers and get half-rate off-peak, which suits overnight batch work.

What you get

Credits on three windows. Individual plans get 5-hour and weekly credit allowances of 2,000 and 10,000 on Lite, 12,000 and 60,000 on Pro, and 28,000 and 140,000 on Max. Credits are computed from token multipliers: GLM-5.3 uses 6.9 for input, 1.7 for cached input and 24 for output, GLM-5.3-Flash uses 2.3, 0.56 and 8. Off-peak usage is charged at half the standard rate, with peak running Monday to Friday 14:00 to 18:00 Singapore time.

Free tier

No free tier is stated for the Coding Plan. GLM-4.7-Flash and GLM-4.5-Flash are listed as free on the separate pay-as-you-go API pricing page, not as plan credits.

Speed

No vendor latency figure is published. Off-peak credits are a price mechanism, not a speed guarantee.

Stability

No status page or SLA was found on the fetched official pages. The docs also conflict on the cancellation window: the usage policy says 3 days before the next billing date, the FAQ says 24 hours.

Xiaomi MiMo Token Plan

Xiaomi

Price

Lite $6/month (¥39) · Standard $16/month (¥99) · Pro $50/month (¥329) · Max $100/month (¥659). Annual: Lite $63.36, Standard $168.96, Pro $528, Max $1,056

Our traffic

153 calls in 30 days · 90.8% OK

  • Credits
  • Lite $6/mo
  • Speech models
Free tier

No free tier is stated for the Token Plan. The TTS models are free for a limited time and consume no plan credits.

What you get

A monthly credit allowance: 4.1 billion credits on Lite, 11 billion on Standard, 38 billion on Pro and 82 billion on Max.

Speed

No vendor latency figure is published.

Stability

No status page or SLA was found on the fetched official pages. Quota does not roll over, and when the monthly credits run out the service is suspended rather than falling back to a balance.

Models, value and full plan details
Models
  • 6 model ids in the live catalog
  • All plans support mimo-v2.6-pro and mimo-v2.6-flash, plus the ASR and TTS models
  • mimo-v2.5-pro and mimo-v2.5 were retired on 2026-10-21 at 10:00 UTC+8 and their model ids no longer work
  • Speech: mimo-v2.5-asr is billed at 30M credits per hour of input audio
Value

Lite is $6 a month, and it is the only one of these seven that bills speech input by audio hour.

What you get

A monthly credit allowance: 4.1 billion credits on Lite, 11 billion on Standard, 38 billion on Pro and 82 billion on Max. Credits are charged per model: mimo-v2.6-pro takes 300 credits for a cache-miss input token, 2.5 for a cache hit and 600 for an output token; mimo-v2.6-flash takes 100, 2 and 200. The page does not state the credit unit, so "per token" is our reading of it. The first purchase is 12% off for individuals, annual auto-renewal is 12% off, and off-peak usage runs at 0.8x.

Free tier

No free tier is stated for the Token Plan. The TTS models are free for a limited time and consume no plan credits.

Speed

No vendor latency figure is published.

Stability

No status page or SLA was found on the fetched official pages. Quota does not roll over, and when the monthly credits run out the service is suspended rather than falling back to a balance. The FAQ says prices are subject to the landing page, and that page could not be extracted, so the price table we used is the only verified one.

OpenDesign

OpenDesign

Price

Go $10/month ($8 first month, $7/month billed annually at $84) · Plus $20 ($16 first, $14/month annually) · Pro $100 ($70 first, $60/month annually) · Max $200 ($120 first, $98/month annually) · Team $63 per seat per month, minimum 3 seats

Our traffic

25 calls in 30 days · 100% OK

  • Credits
  • Free desktop app
  • Credits not dollars
Free tier

The desktop app is free and open source under Apache-2.0, and running it with your own coding agent or your own API key costs nothing extra from OpenDesign. That free tier supports local CLI and bring-your-own-key only: no recurring model credits, and no trial credit amount is published.

What you get

Model credits, not cash balances.

Speed

No vendor latency figure is published, and no dollar price per model is published either: usage is priced in credit multipliers.

Stability

No status page was reachable: status.open-design.ai returned no response and open-design.ai/status returned 404. No uptime or SLA claim was found.

Models, value and full plan details
Models
  • 13 model ids in the live catalog
  • The pricing page lists Claude Haiku 5.5, GPT-6 Luna, DeepSeek V4.1 Flash, GLM-5.3 Flash-X, MiMo V2.6 Flash and Pro, DeepSeek V4 Flash and Pro, Kimi K2.7 Code and more
  • Plus, Pro and Max list GPT-6 Astra, Claude Fable 5.1 and Claude Opus 5.5, and the first three are marked "Not included" on Plus
  • Per-model prices are published as credit multipliers, not dollars: DeepSeek V4.1 Flash 0.5x, MiMo V2.6 Flash and Pro 1x, GLM-5.3 Flash 1x, Claude Haiku 5.5 2x, GLM-5.3 Flash-X 2x, GPT-6 Luna 4x
Value

The only one of the seven with a free desktop app you can run on your own agent, plus a hosted API on the same credits.

What you get

Model credits, not cash balances. Monthly maximum credits are Go $120, Plus $180, Pro $480 and Max $900, and each plan mixes "Design Plan" credits with plan model credits. Go has no plan model credits at all; Plus adds $20, Pro $120 and Max $300, with limited-time bonuses of 20% on Pro and 50% on Max. Concurrent tasks run from 10 on Go to 30 on Pro and Max.

Free tier

The desktop app is free and open source under Apache-2.0, and running it with your own coding agent or your own API key costs nothing extra from OpenDesign. That free tier supports local CLI and bring-your-own-key only: no recurring model credits, and no trial credit amount is published.

Speed

No vendor latency figure is published, and no dollar price per model is published either: usage is priced in credit multipliers.

Stability

No status page was reachable: status.open-design.ai returned no response and open-design.ai/status returned 404. No uptime or SLA claim was found.

Every model id the seven catalogues listed on 2026-10-30

All 679 model ids the seven catalogues listed on 2026-10-30. This is a snapshot of the catalogues, not a promise about what a plan will let you call. Two cautions: the 439 ClinePass rows are the general Cline API catalogue rather than the ClinePass plan, which serves 15 curated ids in its own namespace; and CommandCode's 107 ids come from the catalogue its CLI cached, not from a model endpoint. Search and the provider filter above narrow both this table and the cards.

Showing 60 of 679 model ids

Model idProviderFamilyNote
beam-free OpenCode Go beam-free free tier
claude-haiku-5-5 OpenCode Go claude-haiku-5-5
deepseek-v4-pro OpenCode Go deepseek-v4-pro
deepseek-v4.1-flash OpenCode Go deepseek-v4.1-flash
gemini-4-argon OpenCode Go gemini-4-argon
glm-5.2 OpenCode Go glm-5.2
glm-5.3 OpenCode Go glm-5.3
glm-5.3-flash OpenCode Go glm-5.3-flash
gpt-5.6-luna OpenCode Go gpt-5.6-luna
gpt-6-luna OpenCode Go gpt-6-luna
grok-4.7 OpenCode Go grok-4.7
hy3 OpenCode Go hy3
hy4-preview OpenCode Go hy4-preview preview
iceman-contributor-free OpenCode Go iceman-contributor-free contributor tier
kimi-k2.7-code OpenCode Go kimi-k2.7-code
kimi-k3 OpenCode Go kimi-k3
kimi-k3.1-pro OpenCode Go kimi-k3.1-pro
longcat-2.0 OpenCode Go longcat-2.0
mimo-v2.6-flash OpenCode Go mimo-v2.6-flash
mimo-v2.6-pro OpenCode Go mimo-v2.6-pro
minimax-m3 OpenCode Go minimax-m3
minimax-m3.1-flash OpenCode Go minimax-m3.1-flash
muse-spark-1.2-contributor OpenCode Go muse-spark-1.2-contributor contributor tier
muse-spark-1.3-contributor OpenCode Go muse-spark-1.3-contributor contributor tier
qwen3.7-plus OpenCode Go qwen3.7-plus
qwen3.8-flash OpenCode Go qwen3.8-flash
qwen3.8-max OpenCode Go qwen3.8-max
step-5-preview OpenCode Go step-5-preview preview
claude-fable-5 CommandCode claude-fable-5
claude-fable-5-1 CommandCode claude-fable-5-1
claude-haiku-4-5-20251001 CommandCode claude-haiku-4-5-20251001
claude-haiku-5-5 CommandCode claude-haiku-5-5
claude-opus-4-7 CommandCode claude-opus-4-7
claude-opus-4-8 CommandCode claude-opus-4-8
claude-opus-5 CommandCode claude-opus-5
claude-opus-5-5 CommandCode claude-opus-5-5
claude-sonnet-4-6 CommandCode claude-sonnet-4-6
claude-sonnet-5 CommandCode claude-sonnet-5
claude-sonnet-5-5 CommandCode claude-sonnet-5-5
deepseek/deepseek-v4-flash CommandCode deepseek deepseek-v4-flash
deepseek/deepseek-v4-flash-fast CommandCode deepseek deepseek-v4-flash-fast
deepseek/deepseek-v4-flash-vision-exp CommandCode deepseek deepseek-v4-flash-vision-exp preview
deepseek/deepseek-v4-pro CommandCode deepseek deepseek-v4-pro
deepseek/deepseek-v4.1-flash CommandCode deepseek deepseek-v4.1-flash
deepseek/deepseek-v4.1-flash-fast CommandCode deepseek deepseek-v4.1-flash-fast
google/gemini-3.1-flash-lite CommandCode Google gemini-3.1-flash-lite
google/gemini-3.5-flash CommandCode Google gemini-3.5-flash
google/gemini-3.5-flash-lite CommandCode Google gemini-3.5-flash-lite
google/gemini-3.6-flash CommandCode Google gemini-3.6-flash
google/gemini-3.7-flash CommandCode Google gemini-3.7-flash
google/gemini-3.8-flash CommandCode Google gemini-3.8-flash
google/gemini-4-argon CommandCode Google gemini-4-argon
gpt-5.3-codex CommandCode gpt-5.3-codex
gpt-5.4 CommandCode gpt-5.4
gpt-5.4-mini CommandCode gpt-5.4-mini
gpt-5.5 CommandCode gpt-5.5
gpt-5.6-luna CommandCode gpt-5.6-luna
gpt-5.6-sol CommandCode gpt-5.6-sol
gpt-5.6-terra CommandCode gpt-5.6-terra
gpt-6-astra CommandCode gpt-6-astra
gpt-6-luna CommandCode gpt-6-luna
gpt-6-sol CommandCode gpt-6-sol
gpt-6.1-sol CommandCode gpt-6.1-sol
gpt-6.1-terra CommandCode gpt-6.1-terra
inclusionai/ling-3.1-flash CommandCode InclusionAI ling-3.1-flash
inclusionai/ling-3.1-flash-1019:free CommandCode InclusionAI ling-3.1-flash-1019 free tier
inclusionai/ling-3.1-flash:free CommandCode InclusionAI ling-3.1-flash free tier
meituan/LongCat-2.0 CommandCode Meituan LongCat-2.0
meituan/LongCat-2.0:free CommandCode Meituan LongCat-2.0 free tier
meta/muse-spark-1.1 CommandCode Meta muse-spark-1.1
meta/muse-spark-1.2 CommandCode Meta muse-spark-1.2
meta/muse-spark-1.2-contributor CommandCode Meta muse-spark-1.2-contributor contributor tier
meta/muse-spark-1.3 CommandCode Meta muse-spark-1.3
meta/muse-spark-1.3-contributor CommandCode Meta muse-spark-1.3-contributor contributor tier
meta/muse-spark-open CommandCode Meta muse-spark-open
meta/muse-wonder-1.0 CommandCode Meta muse-wonder-1.0
minimax/minimax-m2.7-free CommandCode minimax minimax-m2.7-free free tier
minimax/minimax-m3-free CommandCode minimax minimax-m3-free free tier
minimax/minimax-m3.1-flash CommandCode minimax minimax-m3.1-flash
minimax/minimax-m3.1-flash:free CommandCode minimax minimax-m3.1-flash free tier
MiniMaxAI/MiniMax-M2.5 CommandCode MiniMax MiniMax-M2.5
MiniMaxAI/MiniMax-M2.7 CommandCode MiniMax MiniMax-M2.7
MiniMaxAI/MiniMax-M3 CommandCode MiniMax MiniMax-M3
MiniMaxAI/MiniMax-M3-Free CommandCode MiniMax MiniMax-M3-Free free tier
mistral/mistral-large-4 CommandCode mistral mistral-large-4
moonshotai/Kimi-K2.5 CommandCode Moonshot Kimi-K2.5
moonshotai/Kimi-K2.6 CommandCode Moonshot Kimi-K2.6
moonshotai/Kimi-K2.7-Code CommandCode Moonshot Kimi-K2.7-Code
moonshotai/Kimi-K2.7-Code-Highspeed CommandCode Moonshot Kimi-K2.7-Code-Highspeed
moonshotai/Kimi-K3 CommandCode Moonshot Kimi-K3
moonshotai/Kimi-K3.1-Pro CommandCode Moonshot Kimi-K3.1-Pro
nvidia/nemotron-3-ultra-550b-a55b CommandCode NVIDIA nemotron-3-ultra-550b-a55b
nvidia/nemotron-3.5-super-vl CommandCode NVIDIA nemotron-3.5-super-vl
ornith/ornith-1.5-122b CommandCode ornith ornith-1.5-122b
ornith/ornith-1.5-122b:free CommandCode ornith ornith-1.5-122b free tier
poolside/laguna-s-2.1-free CommandCode Poolside laguna-s-2.1-free free tier
Qwen/Qwen3.6-Max-Preview CommandCode Qwen Qwen3.6-Max-Preview
Qwen/Qwen3.6-Plus CommandCode Qwen Qwen3.6-Plus
Qwen/Qwen3.7-Flash CommandCode Qwen Qwen3.7-Flash
Qwen/Qwen3.7-Max CommandCode Qwen Qwen3.7-Max
Qwen/Qwen3.7-Plus CommandCode Qwen Qwen3.7-Plus
Qwen/Qwen3.8-27B CommandCode Qwen Qwen3.8-27B
Qwen/Qwen3.8-Flash CommandCode Qwen Qwen3.8-Flash
Qwen/Qwen3.8-Max CommandCode Qwen Qwen3.8-Max
Qwen/Qwen3.8-Max-0902 CommandCode Qwen Qwen3.8-Max-0902
Qwen/Qwen3.8-Max-Prime CommandCode Qwen Qwen3.8-Max-Prime
Qwen/Qwen3.8-Omni-Flash CommandCode Qwen Qwen3.8-Omni-Flash
reflection/beam:free CommandCode Reflection beam free tier
sakana/fugu-ultra CommandCode sakana fugu-ultra
stealth/glyph-cluster:free CommandCode Stealth glyph-cluster free tier
stealth/pixel-canary CommandCode Stealth pixel-canary
stealth/space-bunny-alpha CommandCode Stealth space-bunny-alpha
stepfun/Step-3.5-Flash CommandCode StepFun Step-3.5-Flash
stepfun/Step-3.7-Flash CommandCode StepFun Step-3.7-Flash
stepfun/Step-5-Preview CommandCode StepFun Step-5-Preview
tencent/Hy3 CommandCode Tencent Hy3
tencent/hy3-paid CommandCode Tencent hy3-paid
tencent/hy4-preview CommandCode Tencent hy4-preview preview
thinkingmachines/inkling CommandCode thinkingmachines inkling
thinkingmachines/inkling-small CommandCode thinkingmachines inkling-small
xai/grok-4.5 CommandCode xAI grok-4.5
xai/grok-4.6 CommandCode xAI grok-4.6
xai/grok-4.7 CommandCode xAI grok-4.7
xiaomi/mimo-v2.5 CommandCode xiaomi mimo-v2.5
xiaomi/mimo-v2.5-pro CommandCode xiaomi mimo-v2.5-pro
xiaomi/mimo-v2.6-flash CommandCode xiaomi mimo-v2.6-flash
xiaomi/mimo-v2.6-pro CommandCode xiaomi mimo-v2.6-pro
xiaomi/mimo-v2.6-pro-ultraspeed CommandCode xiaomi mimo-v2.6-pro-ultraspeed
z-ai/glm-5.3-flash CommandCode Z.AI glm-5.3-flash
z-ai/glm-5.3-flashx CommandCode Z.AI glm-5.3-flashx
zai-org/GLM-5 CommandCode Z.AI GLM-5
zai-org/GLM-5.1 CommandCode Z.AI GLM-5.1
zai-org/GLM-5.2 CommandCode Z.AI GLM-5.2
zai-org/GLM-5.2-Fast CommandCode Z.AI GLM-5.2-Fast
zai-org/GLM-5.3 CommandCode Z.AI GLM-5.3
@preset/cline-mistral-k5-20261023-large4-zdr-r1 ClinePass @preset cline-mistral-k5-20261023-large4-zdr-r1
@preset/cline-new27-20261022-gpt61sol-azure-r1 ClinePass @preset cline-new27-20261022-gpt61sol-azure-r1
@preset/cline-new27-20261022-nemotron35vl-coreweave-r1 ClinePass @preset cline-new27-20261022-nemotron35vl-coreweave-r1
@preset/cline-new27-20261022-opus55-vertex-global-r1 ClinePass @preset cline-new27-20261022-opus55-vertex-global-r1
@preset/cline-new27-20261022-sonnet55-vertex-global-r1 ClinePass @preset cline-new27-20261022-sonnet55-vertex-global-r1
aion-labs/aion-2.0 ClinePass aion-labs aion-2.0
aion-labs/aion-3.0 ClinePass aion-labs aion-3.0
aion-labs/aion-3.0-mini ClinePass aion-labs aion-3.0-mini
aion-labs/aion-3.5 ClinePass aion-labs aion-3.5
aion-labs/aion-3.5-mini ClinePass aion-labs aion-3.5-mini
aion-labs/aion-rp-llama-3.1-8b ClinePass aion-labs aion-rp-llama-3.1-8b
amazon/nova-2-lite-v1 ClinePass Amazon nova-2-lite-v1
amazon/nova-lite-v1 ClinePass Amazon nova-lite-v1
amazon/nova-micro-v1 ClinePass Amazon nova-micro-v1
amazon/nova-premier-v1 ClinePass Amazon nova-premier-v1
amazon/nova-pro-v1 ClinePass Amazon nova-pro-v1
anthracite-org/magnum-v4-72b ClinePass anthracite-org magnum-v4-72b
anthropic/claude-fable-5 ClinePass Anthropic claude-fable-5
anthropic/claude-fable-5.1 ClinePass Anthropic claude-fable-5.1
anthropic/claude-fable-5.1:batch ClinePass Anthropic claude-fable-5.1
anthropic/claude-fable-5:batch ClinePass Anthropic claude-fable-5
anthropic/claude-haiku-4.5 ClinePass Anthropic claude-haiku-4.5
anthropic/claude-haiku-4.5:batch ClinePass Anthropic claude-haiku-4.5
anthropic/claude-haiku-5.5 ClinePass Anthropic claude-haiku-5.5
anthropic/claude-haiku-5.5:batch ClinePass Anthropic claude-haiku-5.5
anthropic/claude-opus-4.1 ClinePass Anthropic claude-opus-4.1
anthropic/claude-opus-4.1:batch ClinePass Anthropic claude-opus-4.1
anthropic/claude-opus-4.5 ClinePass Anthropic claude-opus-4.5
anthropic/claude-opus-4.5:batch ClinePass Anthropic claude-opus-4.5
anthropic/claude-opus-4.6 ClinePass Anthropic claude-opus-4.6
anthropic/claude-opus-4.6:batch ClinePass Anthropic claude-opus-4.6
anthropic/claude-opus-4.7 ClinePass Anthropic claude-opus-4.7
anthropic/claude-opus-4.7:batch ClinePass Anthropic claude-opus-4.7
anthropic/claude-opus-4.8 ClinePass Anthropic claude-opus-4.8
anthropic/claude-opus-4.8:batch ClinePass Anthropic claude-opus-4.8
anthropic/claude-opus-5 ClinePass Anthropic claude-opus-5
anthropic/claude-opus-5.5 ClinePass Anthropic claude-opus-5.5
anthropic/claude-opus-5.5:batch ClinePass Anthropic claude-opus-5.5
anthropic/claude-opus-5:batch ClinePass Anthropic claude-opus-5
anthropic/claude-sonnet-4.5 ClinePass Anthropic claude-sonnet-4.5
anthropic/claude-sonnet-4.5:batch ClinePass Anthropic claude-sonnet-4.5
anthropic/claude-sonnet-4.6 ClinePass Anthropic claude-sonnet-4.6
anthropic/claude-sonnet-4.6:batch ClinePass Anthropic claude-sonnet-4.6
anthropic/claude-sonnet-5 ClinePass Anthropic claude-sonnet-5
anthropic/claude-sonnet-5.5 ClinePass Anthropic claude-sonnet-5.5
anthropic/claude-sonnet-5.5:batch ClinePass Anthropic claude-sonnet-5.5
anthropic/claude-sonnet-5:batch ClinePass Anthropic claude-sonnet-5
bytedance-seed/seed-1.6 ClinePass bytedance-seed seed-1.6
bytedance-seed/seed-1.6-flash ClinePass bytedance-seed seed-1.6-flash
bytedance-seed/seed-2-1-turbo ClinePass bytedance-seed seed-2-1-turbo
bytedance-seed/seed-2.0-code ClinePass bytedance-seed seed-2.0-code
bytedance-seed/seed-2.0-lite ClinePass bytedance-seed seed-2.0-lite
bytedance-seed/seed-2.0-mini ClinePass bytedance-seed seed-2.0-mini
bytedance/ui-tars-1.5-7b ClinePass bytedance ui-tars-1.5-7b
cognitivecomputations/dolphin-mistral-24b-venice-edition ClinePass cognitivecomputations dolphin-mistral-24b-venice-edition
cohere/command-a ClinePass cohere command-a
cohere/command-a-plus ClinePass cohere command-a-plus
cohere/command-r-08-2024 ClinePass cohere command-r-08-2024
cohere/command-r-plus-08-2024 ClinePass cohere command-r-plus-08-2024
cohere/command-r7b-12-2024 ClinePass cohere command-r7b-12-2024
cohere/north-mini-code:free ClinePass cohere north-mini-code free tier
deepseek/deepseek-chat ClinePass deepseek deepseek-chat
deepseek/deepseek-chat-v3-0324 ClinePass deepseek deepseek-chat-v3-0324
deepseek/deepseek-chat-v3.1 ClinePass deepseek deepseek-chat-v3.1
deepseek/deepseek-r1-0528 ClinePass deepseek deepseek-r1-0528
deepseek/deepseek-v3.1-terminus ClinePass deepseek deepseek-v3.1-terminus
deepseek/deepseek-v3.2 ClinePass deepseek deepseek-v3.2
deepseek/deepseek-v3.2-exp ClinePass deepseek deepseek-v3.2-exp preview
deepseek/deepseek-v4-flash ClinePass deepseek deepseek-v4-flash
deepseek/deepseek-v4-flash-0731 ClinePass deepseek deepseek-v4-flash-0731
deepseek/deepseek-v4-flash-vision-exp ClinePass deepseek deepseek-v4-flash-vision-exp preview
deepseek/deepseek-v4-pro ClinePass deepseek deepseek-v4-pro
deepseek/deepseek-v4-pro-0813 ClinePass deepseek deepseek-v4-pro-0813
deepseek/deepseek-v4.1-flash ClinePass deepseek deepseek-v4.1-flash
deepseek/deepseek-v4.1-flash-1017 ClinePass deepseek deepseek-v4.1-flash-1017
deepseek/deepseek-v4.1-flash:batch ClinePass deepseek deepseek-v4.1-flash
dots-studio/dots-3-note-preview:free ClinePass dots-studio dots-3-note-preview free tier
elorian/glimpse ClinePass elorian glimpse
fireworks/ember-1 ClinePass fireworks ember-1
google/gemini-2.5-flash ClinePass Google gemini-2.5-flash
google/gemini-2.5-flash-image ClinePass Google gemini-2.5-flash-image
google/gemini-2.5-flash-lite ClinePass Google gemini-2.5-flash-lite
google/gemini-2.5-pro ClinePass Google gemini-2.5-pro
google/gemini-2.5-pro-preview ClinePass Google gemini-2.5-pro-preview preview
google/gemini-3-flash-preview ClinePass Google gemini-3-flash-preview preview
google/gemini-3-flash-preview:batch ClinePass Google gemini-3-flash-preview preview
google/gemini-3-pro-image ClinePass Google gemini-3-pro-image
google/gemini-3-pro-image-preview ClinePass Google gemini-3-pro-image-preview preview
google/gemini-3.1-flash-image ClinePass Google gemini-3.1-flash-image
google/gemini-3.1-flash-image-preview ClinePass Google gemini-3.1-flash-image-preview preview
google/gemini-3.1-flash-lite ClinePass Google gemini-3.1-flash-lite
google/gemini-3.1-flash-lite-image ClinePass Google gemini-3.1-flash-lite-image
google/gemini-3.1-flash-lite-preview ClinePass Google gemini-3.1-flash-lite-preview preview
google/gemini-3.1-flash-lite:batch ClinePass Google gemini-3.1-flash-lite
google/gemini-3.1-pro-preview ClinePass Google gemini-3.1-pro-preview preview
google/gemini-3.1-pro-preview-customtools ClinePass Google gemini-3.1-pro-preview-customtools preview
google/gemini-3.1-pro-preview:batch ClinePass Google gemini-3.1-pro-preview preview
google/gemini-3.5-flash ClinePass Google gemini-3.5-flash
google/gemini-3.5-flash-lite ClinePass Google gemini-3.5-flash-lite
google/gemini-3.5-flash-lite:batch ClinePass Google gemini-3.5-flash-lite
google/gemini-3.5-flash:batch ClinePass Google gemini-3.5-flash
google/gemini-3.6-flash ClinePass Google gemini-3.6-flash
google/gemini-3.6-flash:batch ClinePass Google gemini-3.6-flash
google/gemini-3.7-flash ClinePass Google gemini-3.7-flash
google/gemini-3.7-flash:batch ClinePass Google gemini-3.7-flash
google/gemini-3.8-flash ClinePass Google gemini-3.8-flash
google/gemini-3.8-flash:batch ClinePass Google gemini-3.8-flash
google/gemini-4-argon ClinePass Google gemini-4-argon
google/gemini-4-argon:batch ClinePass Google gemini-4-argon
google/gemini-nano-banana-2.1 ClinePass Google gemini-nano-banana-2.1
google/gemma-2-27b-it ClinePass Google gemma-2-27b-it
google/gemma-3-12b-it ClinePass Google gemma-3-12b-it
google/gemma-3-27b-it ClinePass Google gemma-3-27b-it
google/gemma-3-4b-it ClinePass Google gemma-3-4b-it
google/gemma-4-26b-a4b-it ClinePass Google gemma-4-26b-a4b-it
google/gemma-4-26b-a4b-it:free ClinePass Google gemma-4-26b-a4b-it free tier
google/gemma-4-31b-it ClinePass Google gemma-4-31b-it
google/gemma-4-31b-it:free ClinePass Google gemma-4-31b-it free tier
google/lyria-3-clip-preview ClinePass Google lyria-3-clip-preview preview
google/lyria-3-pro-preview ClinePass Google lyria-3-pro-preview preview
gryphe/mythomax-l2-13b ClinePass gryphe mythomax-l2-13b
ibm-granite/granite-4.2-8b ClinePass ibm-granite granite-4.2-8b
inception/mercury-2 ClinePass inception mercury-2
inception/mercury-2.5 ClinePass inception mercury-2.5
inception/mercury-3 ClinePass inception mercury-3
inclusionai/ling-3.0-flash ClinePass InclusionAI ling-3.0-flash
inclusionai/ling-3.0-flash-vl ClinePass InclusionAI ling-3.0-flash-vl
inclusionai/ling-3.1-flash ClinePass InclusionAI ling-3.1-flash
inference-net/schematron-v2-small ClinePass inference-net schematron-v2-small
inference-net/schematron-v2-turbo ClinePass inference-net schematron-v2-turbo
liquid/lfm-2.5-2.6b ClinePass liquid lfm-2.5-2.6b
liquid/lfm-2.5-2.6b:free ClinePass liquid lfm-2.5-2.6b free tier
liquid/lfm-2.5-24b-a2b ClinePass liquid lfm-2.5-24b-a2b
mancer/weaver ClinePass mancer weaver
meituan/longcat-2.0 ClinePass Meituan longcat-2.0
meta-llama/llama-3.1-70b-instruct ClinePass meta-llama llama-3.1-70b-instruct
meta-llama/llama-3.1-8b-instruct ClinePass meta-llama llama-3.1-8b-instruct
meta-llama/llama-3.2-1b-instruct ClinePass meta-llama llama-3.2-1b-instruct
meta-llama/llama-3.2-3b-instruct ClinePass meta-llama llama-3.2-3b-instruct
meta-llama/llama-3.3-70b-instruct ClinePass meta-llama llama-3.3-70b-instruct
meta-llama/llama-4-maverick ClinePass meta-llama llama-4-maverick
meta-llama/llama-4-scout ClinePass meta-llama llama-4-scout
meta-llama/llama-guard-4-12b ClinePass meta-llama llama-guard-4-12b
meta/muse-glimmer-30b ClinePass Meta muse-glimmer-30b
meta/muse-spark-1.1 ClinePass Meta muse-spark-1.1
meta/muse-spark-1.2 ClinePass Meta muse-spark-1.2
meta/muse-spark-1.2-contributor ClinePass Meta muse-spark-1.2-contributor contributor tier
meta/muse-spark-1.3 ClinePass Meta muse-spark-1.3
meta/muse-spark-1.3-contributor ClinePass Meta muse-spark-1.3-contributor contributor tier
meta/muse-spark-open ClinePass Meta muse-spark-open
meta/muse-wonder ClinePass Meta muse-wonder
microsoft/phi-4 ClinePass Microsoft phi-4
minimax/minimax-01 ClinePass minimax minimax-01
minimax/minimax-m1 ClinePass minimax minimax-m1
minimax/minimax-m2 ClinePass minimax minimax-m2
minimax/minimax-m2-her ClinePass minimax minimax-m2-her
minimax/minimax-m2.1 ClinePass minimax minimax-m2.1
minimax/minimax-m2.5 ClinePass minimax minimax-m2.5
minimax/minimax-m2.7 ClinePass minimax minimax-m2.7
minimax/minimax-m3 ClinePass minimax minimax-m3
minimax/minimax-m3.1-flash ClinePass minimax minimax-m3.1-flash
mistralai/codestral-2508 ClinePass Mistral codestral-2508
mistralai/devstral-2512 ClinePass Mistral devstral-2512
mistralai/ministral-14b-2512 ClinePass Mistral ministral-14b-2512
mistralai/ministral-3b-2512 ClinePass Mistral ministral-3b-2512
mistralai/ministral-8b-2512 ClinePass Mistral ministral-8b-2512
mistralai/mistral-large ClinePass Mistral mistral-large
mistralai/mistral-large-2407 ClinePass Mistral mistral-large-2407
mistralai/mistral-large-2512 ClinePass Mistral mistral-large-2512
mistralai/mistral-large-4-0 ClinePass Mistral mistral-large-4-0
mistralai/mistral-medium-3 ClinePass Mistral mistral-medium-3
mistralai/mistral-medium-3-5 ClinePass Mistral mistral-medium-3-5
mistralai/mistral-medium-3-5:batch ClinePass Mistral mistral-medium-3-5
mistralai/mistral-medium-3.1 ClinePass Mistral mistral-medium-3.1
mistralai/mistral-nemo ClinePass Mistral mistral-nemo
mistralai/mistral-saba ClinePass Mistral mistral-saba
mistralai/mistral-small-24b-instruct-2501 ClinePass Mistral mistral-small-24b-instruct-2501
mistralai/mistral-small-2603 ClinePass Mistral mistral-small-2603
mistralai/mistral-small-3.1-24b-instruct ClinePass Mistral mistral-small-3.1-24b-instruct
mistralai/mistral-small-3.2-24b-instruct ClinePass Mistral mistral-small-3.2-24b-instruct
mistralai/mixtral-8x22b-instruct ClinePass Mistral mixtral-8x22b-instruct
mistralai/voxtral-small-24b-2507 ClinePass Mistral voxtral-small-24b-2507
moondream/moondream3-preview ClinePass moondream moondream3-preview preview
moondream/moondream3.1-9b-a2b ClinePass moondream moondream3.1-9b-a2b
moonshotai/kimi-k2 ClinePass Moonshot kimi-k2
moonshotai/kimi-k2-0905 ClinePass Moonshot kimi-k2-0905
moonshotai/kimi-k2-thinking ClinePass Moonshot kimi-k2-thinking
moonshotai/kimi-k2.5 ClinePass Moonshot kimi-k2.5
moonshotai/kimi-k2.6 ClinePass Moonshot kimi-k2.6
moonshotai/kimi-k2.7-code ClinePass Moonshot kimi-k2.7-code
moonshotai/kimi-k3 ClinePass Moonshot kimi-k3
moonshotai/kimi-k3.1-pro ClinePass Moonshot kimi-k3.1-pro
moonshotai/kimi-k3:batch ClinePass Moonshot kimi-k3
morph/morph-v3-fast ClinePass morph morph-v3-fast
morph/morph-v3-large ClinePass morph morph-v3-large
nex-agi/nex-n2.5-mini ClinePass nex-agi nex-n2.5-mini
nex-agi/nex-n2.5-pro ClinePass nex-agi nex-n2.5-pro
nousresearch/hermes-3-llama-3.1-405b ClinePass nousresearch hermes-3-llama-3.1-405b
nousresearch/hermes-3-llama-3.1-70b ClinePass nousresearch hermes-3-llama-3.1-70b
nousresearch/hermes-4-405b ClinePass nousresearch hermes-4-405b
nvidia/nemotron-3-nano-30b-a3b ClinePass NVIDIA nemotron-3-nano-30b-a3b
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free ClinePass NVIDIA nemotron-3-nano-omni-30b-a3b-reasoning free tier
nvidia/nemotron-3-super-120b-a12b ClinePass NVIDIA nemotron-3-super-120b-a12b
nvidia/nemotron-3-ultra-550b-a55b ClinePass NVIDIA nemotron-3-ultra-550b-a55b
nvidia/nemotron-3-ultra-550b-a55b:free ClinePass NVIDIA nemotron-3-ultra-550b-a55b free tier
nvidia/nemotron-3.5-content-safety ClinePass NVIDIA nemotron-3.5-content-safety
nvidia/nemotron-3.5-content-safety:free ClinePass NVIDIA nemotron-3.5-content-safety free tier
nvidia/nemotron-3.5-lightning ClinePass NVIDIA nemotron-3.5-lightning
nvidia/nemotron-3.5-lightning:free ClinePass NVIDIA nemotron-3.5-lightning free tier
nvidia/nemotron-3.5-super-vl ClinePass NVIDIA nemotron-3.5-super-vl
nvidia/nemotron-3.5-super-vl:free ClinePass NVIDIA nemotron-3.5-super-vl free tier
nvidia/switchyard ClinePass NVIDIA switchyard
openai/gpt-3.5-turbo-0613 ClinePass OpenAI gpt-3.5-turbo-0613
openai/gpt-3.5-turbo-16k ClinePass OpenAI gpt-3.5-turbo-16k
openai/gpt-4 ClinePass OpenAI gpt-4
openai/gpt-4.1 ClinePass OpenAI gpt-4.1
openai/gpt-4.1-mini ClinePass OpenAI gpt-4.1-mini
openai/gpt-4.1-nano ClinePass OpenAI gpt-4.1-nano
openai/gpt-4o ClinePass OpenAI gpt-4o
openai/gpt-4o-2024-05-13 ClinePass OpenAI gpt-4o-2024-05-13
openai/gpt-4o-2024-08-06 ClinePass OpenAI gpt-4o-2024-08-06
openai/gpt-4o-2024-11-20 ClinePass OpenAI gpt-4o-2024-11-20
openai/gpt-4o-mini ClinePass OpenAI gpt-4o-mini
openai/gpt-4o-mini-2024-07-18 ClinePass OpenAI gpt-4o-mini-2024-07-18
openai/gpt-5 ClinePass OpenAI gpt-5
openai/gpt-5-image ClinePass OpenAI gpt-5-image
openai/gpt-5-image-mini ClinePass OpenAI gpt-5-image-mini
openai/gpt-5-mini ClinePass OpenAI gpt-5-mini
openai/gpt-5-nano ClinePass OpenAI gpt-5-nano
openai/gpt-5-nano:batch ClinePass OpenAI gpt-5-nano
openai/gpt-5-pro ClinePass OpenAI gpt-5-pro
openai/gpt-5.1 ClinePass OpenAI gpt-5.1
openai/gpt-5.1-codex ClinePass OpenAI gpt-5.1-codex
openai/gpt-5.1-codex-max ClinePass OpenAI gpt-5.1-codex-max
openai/gpt-5.1-codex-mini ClinePass OpenAI gpt-5.1-codex-mini
openai/gpt-5.2 ClinePass OpenAI gpt-5.2
openai/gpt-5.2-codex ClinePass OpenAI gpt-5.2-codex
openai/gpt-5.2-pro ClinePass OpenAI gpt-5.2-pro
openai/gpt-5.3-codex ClinePass OpenAI gpt-5.3-codex
openai/gpt-5.4 ClinePass OpenAI gpt-5.4
openai/gpt-5.4-image-2 ClinePass OpenAI gpt-5.4-image-2
openai/gpt-5.4-mini ClinePass OpenAI gpt-5.4-mini
openai/gpt-5.4-nano ClinePass OpenAI gpt-5.4-nano
openai/gpt-5.4-pro ClinePass OpenAI gpt-5.4-pro
openai/gpt-5.5 ClinePass OpenAI gpt-5.5
openai/gpt-5.5-pro ClinePass OpenAI gpt-5.5-pro
openai/gpt-5.6-luna ClinePass OpenAI gpt-5.6-luna
openai/gpt-5.6-luna-pro ClinePass OpenAI gpt-5.6-luna-pro
openai/gpt-5.6-luna-pro:batch ClinePass OpenAI gpt-5.6-luna-pro
openai/gpt-5.6-luna:batch ClinePass OpenAI gpt-5.6-luna
openai/gpt-5.6-sol ClinePass OpenAI gpt-5.6-sol
openai/gpt-5.6-sol-pro ClinePass OpenAI gpt-5.6-sol-pro
openai/gpt-5.6-sol-pro:batch ClinePass OpenAI gpt-5.6-sol-pro
openai/gpt-5.6-sol:batch ClinePass OpenAI gpt-5.6-sol
openai/gpt-5.6-terra ClinePass OpenAI gpt-5.6-terra
openai/gpt-5.6-terra-pro ClinePass OpenAI gpt-5.6-terra-pro
openai/gpt-5.6-terra-pro:batch ClinePass OpenAI gpt-5.6-terra-pro
openai/gpt-5.6-terra:batch ClinePass OpenAI gpt-5.6-terra
openai/gpt-6-astra ClinePass OpenAI gpt-6-astra
openai/gpt-6-astra-pro ClinePass OpenAI gpt-6-astra-pro
openai/gpt-6-astra-pro:batch ClinePass OpenAI gpt-6-astra-pro
openai/gpt-6-astra:batch ClinePass OpenAI gpt-6-astra
openai/gpt-6-luna ClinePass OpenAI gpt-6-luna
openai/gpt-6-luna-pro ClinePass OpenAI gpt-6-luna-pro
openai/gpt-6-luna-pro:batch ClinePass OpenAI gpt-6-luna-pro
openai/gpt-6-luna:batch ClinePass OpenAI gpt-6-luna
openai/gpt-6-sol ClinePass OpenAI gpt-6-sol
openai/gpt-6-sol-pro ClinePass OpenAI gpt-6-sol-pro
openai/gpt-6-sol-pro:batch ClinePass OpenAI gpt-6-sol-pro
openai/gpt-6-sol:batch ClinePass OpenAI gpt-6-sol
openai/gpt-6.1-sol ClinePass OpenAI gpt-6.1-sol
openai/gpt-6.1-sol-pro ClinePass OpenAI gpt-6.1-sol-pro
openai/gpt-6.1-sol-pro:batch ClinePass OpenAI gpt-6.1-sol-pro
openai/gpt-6.1-sol:batch ClinePass OpenAI gpt-6.1-sol
openai/gpt-6.1-terra ClinePass OpenAI gpt-6.1-terra
openai/gpt-6.1-terra-pro ClinePass OpenAI gpt-6.1-terra-pro
openai/gpt-6.1-terra-pro:batch ClinePass OpenAI gpt-6.1-terra-pro
openai/gpt-6.1-terra:batch ClinePass OpenAI gpt-6.1-terra
openai/gpt-audio ClinePass OpenAI gpt-audio
openai/gpt-audio-mini ClinePass OpenAI gpt-audio-mini
openai/gpt-chat-latest ClinePass OpenAI gpt-chat-latest
openai/gpt-oss-120b ClinePass OpenAI gpt-oss-120b
openai/gpt-oss-120b:batch ClinePass OpenAI gpt-oss-120b
openai/gpt-oss-20b ClinePass OpenAI gpt-oss-20b
openai/gpt-oss-20b:batch ClinePass OpenAI gpt-oss-20b
openai/gpt-oss-safeguard-20b ClinePass OpenAI gpt-oss-safeguard-20b
openai/o3 ClinePass OpenAI o3
openai/o3-pro ClinePass OpenAI o3-pro
openrouter/auto ClinePass openrouter auto
openrouter/auto-beta ClinePass openrouter auto-beta
openrouter/bodybuilder ClinePass openrouter bodybuilder
openrouter/free ClinePass openrouter free free tier
openrouter/fusion ClinePass openrouter fusion
openrouter/pareto-code ClinePass openrouter pareto-code
particle-ai/particle-1 ClinePass particle-ai particle-1
perceptron/perceptron-mk1 ClinePass perceptron perceptron-mk1
perceptron/perceptron-mk1.5 ClinePass perceptron perceptron-mk1.5
perplexity/sonar ClinePass perplexity sonar
perplexity/sonar-deep-research ClinePass perplexity sonar-deep-research
perplexity/sonar-pro ClinePass perplexity sonar-pro
perplexity/sonar-pro-search ClinePass perplexity sonar-pro-search
perplexity/sonar-reasoning-pro ClinePass perplexity sonar-reasoning-pro
poolside/laguna-s-2.1 ClinePass Poolside laguna-s-2.1
poolside/laguna-s-2.1:free ClinePass Poolside laguna-s-2.1 free tier
poolside/laguna-xs-2.1 ClinePass Poolside laguna-xs-2.1
poolside/laguna-xs-2.1:free ClinePass Poolside laguna-xs-2.1 free tier
prism-ml/ternary-bonsai-2-27b ClinePass prism-ml ternary-bonsai-2-27b
prism-ml/ternary-bonsai-2-9b ClinePass prism-ml ternary-bonsai-2-9b
qwen/qwen-2.5-72b-instruct ClinePass qwen qwen-2.5-72b-instruct
qwen/qwen-2.5-7b-instruct ClinePass qwen qwen-2.5-7b-instruct
qwen/qwen-2.5-coder-32b-instruct ClinePass qwen qwen-2.5-coder-32b-instruct
qwen/qwen-plus ClinePass qwen qwen-plus
qwen/qwen2.5-vl-72b-instruct ClinePass qwen qwen2.5-vl-72b-instruct
qwen/qwen3-14b ClinePass qwen qwen3-14b
qwen/qwen3-235b-a22b-2507 ClinePass qwen qwen3-235b-a22b-2507
qwen/qwen3-235b-a22b-thinking-2507 ClinePass qwen qwen3-235b-a22b-thinking-2507
qwen/qwen3-30b-a3b ClinePass qwen qwen3-30b-a3b
qwen/qwen3-30b-a3b-instruct-2507 ClinePass qwen qwen3-30b-a3b-instruct-2507
qwen/qwen3-32b ClinePass qwen qwen3-32b
qwen/qwen3-coder ClinePass qwen qwen3-coder
qwen/qwen3-coder-30b-a3b-instruct ClinePass qwen qwen3-coder-30b-a3b-instruct
qwen/qwen3-coder-flash ClinePass qwen qwen3-coder-flash
qwen/qwen3-coder-next ClinePass qwen qwen3-coder-next
qwen/qwen3-next-80b-a3b-instruct ClinePass qwen qwen3-next-80b-a3b-instruct
qwen/qwen3-vl-235b-a22b-instruct ClinePass qwen qwen3-vl-235b-a22b-instruct
qwen/qwen3-vl-30b-a3b-instruct ClinePass qwen qwen3-vl-30b-a3b-instruct
qwen/qwen3-vl-30b-a3b-thinking ClinePass qwen qwen3-vl-30b-a3b-thinking
qwen/qwen3-vl-8b-instruct ClinePass qwen qwen3-vl-8b-instruct
qwen/qwen3.5-122b-a10b ClinePass qwen qwen3.5-122b-a10b
qwen/qwen3.5-27b ClinePass qwen qwen3.5-27b
qwen/qwen3.5-35b-a3b ClinePass qwen qwen3.5-35b-a3b
qwen/qwen3.5-397b-a17b ClinePass qwen qwen3.5-397b-a17b
qwen/qwen3.5-9b ClinePass qwen qwen3.5-9b
qwen/qwen3.5-flash-02-23 ClinePass qwen qwen3.5-flash-02-23
qwen/qwen3.5-plus-02-15 ClinePass qwen qwen3.5-plus-02-15
qwen/qwen3.5-plus-20260420 ClinePass qwen qwen3.5-plus-20260420
qwen/qwen3.6-27b ClinePass qwen qwen3.6-27b
qwen/qwen3.6-35b-a3b ClinePass qwen qwen3.6-35b-a3b
qwen/qwen3.6-flash ClinePass qwen qwen3.6-flash
qwen/qwen3.6-plus ClinePass qwen qwen3.6-plus
qwen/qwen3.7-flash ClinePass qwen qwen3.7-flash
qwen/qwen3.7-max ClinePass qwen qwen3.7-max
qwen/qwen3.7-plus ClinePass qwen qwen3.7-plus
qwen/qwen3.7-plus:batch ClinePass qwen qwen3.7-plus
qwen/qwen3.8-2.4t-a95b ClinePass qwen qwen3.8-2.4t-a95b
qwen/qwen3.8-27b ClinePass qwen qwen3.8-27b
qwen/qwen3.8-flash ClinePass qwen qwen3.8-flash
qwen/qwen3.8-max-0902 ClinePass qwen qwen3.8-max-0902
qwen/qwen3.8-max-prime ClinePass qwen qwen3.8-max-prime
qwen/qwen3.8-omni-flash ClinePass qwen qwen3.8-omni-flash
recursive/flint-v1.0:free ClinePass recursive flint-v1.0 free tier
reflection/beam-1.0-501b-a23b ClinePass Reflection beam-1.0-501b-a23b
rekaai/reka-edge ClinePass rekaai reka-edge
rekaai/reka-flash-3 ClinePass rekaai reka-flash-3
relace/relace-apply-3 ClinePass relace relace-apply-3
relace/relace-search ClinePass relace relace-search
sakana/fugu-max ClinePass sakana fugu-max
sakana/fugu-ultra ClinePass sakana fugu-ultra
sakana/fugu-ultra-v2 ClinePass sakana fugu-ultra-v2
sakana/sakana-namazu ClinePass sakana sakana-namazu
sao10k/l3-lunaris-8b ClinePass sao10k l3-lunaris-8b
sao10k/l3.1-euryale-70b ClinePass sao10k l3.1-euryale-70b
scaledown/extract ClinePass scaledown extract
scaledown/summarize ClinePass scaledown summarize
stepfun/step-3.5-flash ClinePass StepFun step-3.5-flash
stepfun/step-3.7-flash ClinePass StepFun step-3.7-flash
stepfun/step-5-preview ClinePass StepFun step-5-preview preview
tencent/hunyuan-a13b-instruct ClinePass Tencent hunyuan-a13b-instruct
tencent/hy-mt2-1.8b ClinePass Tencent hy-mt2-1.8b
tencent/hy-mt2-30b-a3b ClinePass Tencent hy-mt2-30b-a3b
tencent/hy-mt2-7b ClinePass Tencent hy-mt2-7b
tencent/hy3 ClinePass Tencent hy3
tencent/hy3-preview ClinePass Tencent hy3-preview preview
tencent/hy4-preview ClinePass Tencent hy4-preview preview
thedrummer/cydonia-24b-v4.1 ClinePass thedrummer cydonia-24b-v4.1
thedrummer/skyfall-36b-v2 ClinePass thedrummer skyfall-36b-v2
thedrummer/unslopnemo-12b ClinePass thedrummer unslopnemo-12b
thinkingmachines/inkling ClinePass thinkingmachines inkling
thinkingmachines/inkling-small ClinePass thinkingmachines inkling-small
thinkingmachines/inkling-small:free ClinePass thinkingmachines inkling-small free tier
thinkingmachines/inkling:free ClinePass thinkingmachines inkling free tier
typesafe/jev-router ClinePass typesafe jev-router
unbiased/pareto-26.10 ClinePass unbiased pareto-26.10
unbiased/pareto-26.9 ClinePass unbiased pareto-26.9
undi95/remm-slerp-l2-13b ClinePass undi95 remm-slerp-l2-13b
upstage/solar-mini4 ClinePass upstage solar-mini4
upstage/solar-pro4 ClinePass upstage solar-pro4
writer/palmyra-x5 ClinePass writer palmyra-x5
x-ai/grok-4.20 ClinePass x-ai grok-4.20
x-ai/grok-4.20-multi-agent ClinePass x-ai grok-4.20-multi-agent
x-ai/grok-4.3 ClinePass x-ai grok-4.3
x-ai/grok-4.3:batch ClinePass x-ai grok-4.3
x-ai/grok-4.5 ClinePass x-ai grok-4.5
x-ai/grok-4.6 ClinePass x-ai grok-4.6
x-ai/grok-4.7 ClinePass x-ai grok-4.7
x-ai/grok-build-0.1 ClinePass x-ai grok-build-0.1
xiaomi/mimo-v2.5 ClinePass xiaomi mimo-v2.5
xiaomi/mimo-v2.5-pro ClinePass xiaomi mimo-v2.5-pro
xiaomi/mimo-v2.6-flash ClinePass xiaomi mimo-v2.6-flash
xiaomi/mimo-v2.6-pro ClinePass xiaomi mimo-v2.6-pro
xiaomi/mimo-v2.6-pro-ultraspeed ClinePass xiaomi mimo-v2.6-pro-ultraspeed
xingchen-agi/xing4.0-29b-a4b:free ClinePass xingchen-agi xing4.0-29b-a4b free tier
z-ai/glm-4.5 ClinePass Z.AI glm-4.5
z-ai/glm-4.5-air ClinePass Z.AI glm-4.5-air
z-ai/glm-4.5v ClinePass Z.AI glm-4.5v
z-ai/glm-4.6 ClinePass Z.AI glm-4.6
z-ai/glm-4.6v ClinePass Z.AI glm-4.6v
z-ai/glm-4.7 ClinePass Z.AI glm-4.7
z-ai/glm-4.7-flash ClinePass Z.AI glm-4.7-flash
z-ai/glm-5 ClinePass Z.AI glm-5
z-ai/glm-5-turbo ClinePass Z.AI glm-5-turbo
z-ai/glm-5.1 ClinePass Z.AI glm-5.1
z-ai/glm-5.2 ClinePass Z.AI glm-5.2
z-ai/glm-5.3 ClinePass Z.AI glm-5.3
z-ai/glm-5.3-flash ClinePass Z.AI glm-5.3-flash
z-ai/glm-5.3-flash:batch ClinePass Z.AI glm-5.3-flash
z-ai/glm-5.3-flashx ClinePass Z.AI glm-5.3-flashx
z-ai/glm-5.3-prime ClinePass Z.AI glm-5.3-prime
z-ai/glm-5.3:batch ClinePass Z.AI glm-5.3
z-ai/glm-5v-turbo ClinePass Z.AI glm-5v-turbo
~anthropic/claude-fable-latest ClinePass ~anthropic claude-fable-latest
~anthropic/claude-haiku-latest ClinePass ~anthropic claude-haiku-latest
~anthropic/claude-opus-latest ClinePass ~anthropic claude-opus-latest
~anthropic/claude-sonnet-latest ClinePass ~anthropic claude-sonnet-latest
~deepseek/deepseek-flash-latest ClinePass ~deepseek deepseek-flash-latest
~deepseek/deepseek-pro-latest ClinePass ~deepseek deepseek-pro-latest
~deepseek/deepseek-v4-flash-latest ClinePass ~deepseek deepseek-v4-flash-latest
~google/gemini-flash-latest ClinePass ~google gemini-flash-latest
~google/gemini-pro-latest ClinePass ~google gemini-pro-latest
~moonshotai/kimi-latest ClinePass ~moonshotai kimi-latest
~openai/gpt-astra-latest ClinePass ~openai gpt-astra-latest
~openai/gpt-luna-latest ClinePass ~openai gpt-luna-latest
~openai/gpt-mini-latest ClinePass ~openai gpt-mini-latest
~openai/gpt-sol-latest ClinePass ~openai gpt-sol-latest
~openai/gpt-terra-latest ClinePass ~openai gpt-terra-latest
~unbiased/pareto-latest ClinePass ~unbiased pareto-latest
~x-ai/grok-latest ClinePass ~x-ai grok-latest
~z-ai/glm-flash-latest ClinePass ~z-ai glm-flash-latest
~z-ai/glm-latest ClinePass ~z-ai glm-latest
claude-fable-5 Token Harbor claude-fable-5
claude-fable-5.1 Token Harbor claude-fable-5.1
claude-haiku-5.5 Token Harbor claude-haiku-5.5
claude-opus-4.8 Token Harbor claude-opus-4.8
claude-opus-5 Token Harbor claude-opus-5
claude-opus-5-fast Token Harbor claude-opus-5-fast
claude-opus-5.5 Token Harbor claude-opus-5.5
claude-opus-5.5-fast Token Harbor claude-opus-5.5-fast
claude-sonnet-4.6 Token Harbor claude-sonnet-4.6
claude-sonnet-5 Token Harbor claude-sonnet-5
claude-sonnet-5.5 Token Harbor claude-sonnet-5.5
deepseek-r1-0528 Token Harbor deepseek-r1-0528
deepseek-v3.2 Token Harbor deepseek-v3.2
deepseek-v4-flash Token Harbor deepseek-v4-flash
deepseek-v4-flash:free Token Harbor deepseek-v4-flash free tier
deepseek-v4-pro Token Harbor deepseek-v4-pro
deepseek-v4.1-flash Token Harbor deepseek-v4.1-flash
deepseek-v4.1-flash-1017 Token Harbor deepseek-v4.1-flash-1017
deepseek-v4.1-flash-1017-fast Token Harbor deepseek-v4.1-flash-1017-fast
deepseek-v4.1-flash:free Token Harbor deepseek-v4.1-flash free tier
gemini-3.6-flash Token Harbor gemini-3.6-flash
gemini-3.7-flash Token Harbor gemini-3.7-flash
gemini-3.8-flash Token Harbor gemini-3.8-flash
gemini-4-argon Token Harbor gemini-4-argon
glm-5.1 Token Harbor glm-5.1
glm-5.2 Token Harbor glm-5.2
glm-5.3 Token Harbor glm-5.3
glm-5.3-fast Token Harbor glm-5.3-fast
glm-5.3-flash Token Harbor glm-5.3-flash
glm-5.3-flashx Token Harbor glm-5.3-flashx
gpt-5.6-luna Token Harbor gpt-5.6-luna
gpt-5.6-luna-fast Token Harbor gpt-5.6-luna-fast
gpt-5.6-sol Token Harbor gpt-5.6-sol
gpt-5.6-sol-fast Token Harbor gpt-5.6-sol-fast
gpt-5.6-terra Token Harbor gpt-5.6-terra
gpt-5.6-terra-fast Token Harbor gpt-5.6-terra-fast
gpt-6-astra Token Harbor gpt-6-astra
gpt-6-astra-fast Token Harbor gpt-6-astra-fast
gpt-6-luna Token Harbor gpt-6-luna
gpt-6-luna-fast Token Harbor gpt-6-luna-fast
gpt-6-sol Token Harbor gpt-6-sol
gpt-6-sol-fast Token Harbor gpt-6-sol-fast
gpt-6.1-sol Token Harbor gpt-6.1-sol
gpt-6.1-sol-fast Token Harbor gpt-6.1-sol-fast
gpt-6.1-terra Token Harbor gpt-6.1-terra
gpt-6.1-terra-fast Token Harbor gpt-6.1-terra-fast
grok-4.5 Token Harbor grok-4.5
grok-4.6 Token Harbor grok-4.6
grok-4.7 Token Harbor grok-4.7
kimi-k2.6 Token Harbor kimi-k2.6
kimi-k3 Token Harbor kimi-k3
kimi-k3-fast Token Harbor kimi-k3-fast
kimi-k3.1-pro Token Harbor kimi-k3.1-pro
ling-3.1-flash Token Harbor ling-3.1-flash
mimo-v2.5 Token Harbor mimo-v2.5
mimo-v2.5-pro Token Harbor mimo-v2.5-pro
mimo-v2.5:free Token Harbor mimo-v2.5 free tier
mimo-v2.6-flash Token Harbor mimo-v2.6-flash
mimo-v2.6-flash:free Token Harbor mimo-v2.6-flash free tier
mimo-v2.6-pro Token Harbor mimo-v2.6-pro
minimax-m3.1-flash Token Harbor minimax-m3.1-flash
mistral-large-2512 Token Harbor mistral-large-2512
mistral-large-4 Token Harbor mistral-large-4
muse-spark-1-3 Token Harbor muse-spark-1-3
muse-spark-1.1 Token Harbor muse-spark-1.1
muse-spark-1.2 Token Harbor muse-spark-1.2
muse-wonder-1.0 Token Harbor muse-wonder-1.0
qwen3.5-27b Token Harbor qwen3.5-27b
qwen3.6-27b Token Harbor qwen3.6-27b
qwen3.6-flash Token Harbor qwen3.6-flash
qwen3.7-flash Token Harbor qwen3.7-flash
qwen3.7-max Token Harbor qwen3.7-max
qwen3.8-27b Token Harbor qwen3.8-27b
qwen3.8-flash Token Harbor qwen3.8-flash
qwen3.8-max Token Harbor qwen3.8-max
glm-4.5 Z.AI GLM Coding Plan glm-4.5
glm-4.5-air Z.AI GLM Coding Plan glm-4.5-air
glm-4.6 Z.AI GLM Coding Plan glm-4.6
glm-4.7 Z.AI GLM Coding Plan glm-4.7
glm-5 Z.AI GLM Coding Plan glm-5
glm-5-turbo Z.AI GLM Coding Plan glm-5-turbo
glm-5.1 Z.AI GLM Coding Plan glm-5.1
glm-5.2 Z.AI GLM Coding Plan glm-5.2
glm-5.3 Z.AI GLM Coding Plan glm-5.3
glm-5.3-flash Z.AI GLM Coding Plan glm-5.3-flash
glm-5.3-flashx Z.AI GLM Coding Plan glm-5.3-flashx
mimo-v2.5-asr Xiaomi MiMo Token Plan mimo-v2.5-asr
mimo-v2.5-tts Xiaomi MiMo Token Plan mimo-v2.5-tts
mimo-v2.5-tts-voiceclone Xiaomi MiMo Token Plan mimo-v2.5-tts-voiceclone
mimo-v2.5-tts-voicedesign Xiaomi MiMo Token Plan mimo-v2.5-tts-voicedesign
mimo-v2.6-flash Xiaomi MiMo Token Plan mimo-v2.6-flash
mimo-v2.6-pro Xiaomi MiMo Token Plan mimo-v2.6-pro
claude-haiku-5.5 OpenDesign claude-haiku-5.5
deepseek-v4-flash OpenDesign deepseek-v4-flash
deepseek-v4-flash-vision-exp OpenDesign deepseek-v4-flash-vision-exp preview
deepseek-v4-pro OpenDesign deepseek-v4-pro
deepseek-v4.1-flash OpenDesign deepseek-v4.1-flash
glm-5.3-flash OpenDesign glm-5.3-flash
glm-5.3-flashx OpenDesign glm-5.3-flashx
gpt-6-luna OpenDesign gpt-6-luna
hy4-preview OpenDesign hy4-preview preview
kimi-k2.7-code OpenDesign kimi-k2.7-code
mimo-v2.6-flash OpenDesign mimo-v2.6-flash
mimo-v2.6-pro OpenDesign mimo-v2.6-pro
minimax-m3.1-flash OpenDesign minimax-m3.1-flash
label: internal · API access only

Our internal routing data: API access only, NOT about the consumer plans above

These are measurements of our own API routes, summarised from our internal provider call log over the arena window shown below. They describe the routes we call, not Claude Code, GitHub Copilot, Cursor or any other plan on this page. This window is older than the 30-day traffic figures on the API cards above, so the two sets of numbers are not comparable.

Period: 2026-10-09 to 2026-10-28. Latency medians are per model: a median for one model says nothing about the same route on another model. Figures with fewer than 100 calls are small samples.

opencode-go 2198 calls · 93.1% OK median 8.7s (claude-haiku-5-5) / 15.2s (minimax-m3.1-flash) / 167s (mimo-v2.6-flash)
commandcode 1073 calls · 95.2% OK median 9.7s (claude-haiku-5-5) / 139s (mimo-v2.6-flash)
cline-pass 620 calls · 95.3% OK median 10.8s (glm-5.3) / 130s (mimo-v2.6-flash)
tokenharbor 515 calls · 93.4% OK median 9.5s (claude-haiku-5-5) / 160s (mimo-v2.6-flash)
claude-cli 445 calls · 99.6% OK median 10.7s (claude-haiku-5-5) · $0 marginal (OAuth)
antseed 90 calls · 94.4% OK no median shown · small sample
zai 32 calls · 46.9% OK no median shown · small sample
kilo 30 calls · 86.7% OK no median shown · small sample

Stability and incidents: what the status pages show

Claude

No reported incidents on Oct 16, 17, 18 and 19. Oct 21: investigating elevated errors on requests to Claude Fable 5, 20:29 UTC, resolved. The history page shows 25 incidents for the August to October window.

status.claude.com/history

GitHub Copilot

On Sep 28, Copilot Code Review was unable to complete reviews, and about 70% of requested reviews did not complete between 19:23 and 22:08 UTC. Oct 30 shows two incidents and one under investigation.

githubstatus.com/history

Cursor

Not verified. The status link resolves to an xAI status page, so we do not claim a Cursor uptime figure.

Windsurf, Cline, Zed, Kilo Code, Antigravity

no status data from the vendor page

Speed is not independently benchmarked for any consumer plan on this page. The status facts above are the only stability measures we have, and they are not a speed measure.

How we built this, and what we did not verify

  • Every price, tier name, model list and platform line comes from the vendor pages below, fetched on 2026-10-30. Most were read with HTTP 200; the openai.com plan pages return 403 to a plain fetch and were read through a text extractor instead, and status.open-design.ai returned no response at all.
  • Where a vendor page did not show a price, the card says "price not verified". Google AI Pro and AI Ultra prices are not verified. The OpenAI plan prices were read from the Codex pricing page at developers.openai.com. The openai.com plan pages are client-rendered and return 403 to a plain fetch: openai.com/codex did show Plus, Pro and Business amounts once its page text was extracted, and the $8 Go price appears only on the Codex pricing page, so the card says so.
  • Platform labels appear only where a vendor page names that surface. Cursor, Windsurf and Zed do not state a platform on their vendor pages, so their cards show "Not stated on the vendor page" instead.
  • We did not verify any speed benchmark for a consumer plan. Speed is not benchmarked for any of these plans. The status-page facts appear in the stability notes instead.
  • The internal routing numbers describe our own API routes, not these consumer plans.
  • Gemini CLI and the Gemini Code Assist IDE extensions are no longer current products. Antigravity replaced them for unpaid-tier and Google One users on June 18, 2026.
  • The API plans section adds seven API-first plans. Prices, quotas and limits come from each vendor's own pages, fetched 2026-10-30; model ids come from each provider's live model endpoint the same day. CommandCode has no model-list endpoint, so its 107 ids come from the catalogue its CLI cached that day.
  • A model id in a provider's catalogue does not mean the plan can call it. ClinePass lists 439 ids, but the plan serves a curated set of 15 in its own cline-pass/ namespace, and none of the 15 appear in the catalogue.
  • No vendor publishes a latency percentile except Token Harbor, whose status page gives a 90-day p95. ClinePass quotes one health-check reading of about 51ms, which is a single dashboard value rather than a percentile, and the other five say their vendor publishes none. Our own call counts are labelled as our traffic.
  • Where two official pages disagree the page says so instead of picking one: CommandCode's Max request counts, ClinePass's two model lists and Z.AI's cancellation windows are flagged.

Sources:

Sources for the API plans section: