AI Deals
Every AI coding subscription, flat-rate API plan, and free harness worth knowing about in 2026. Grouped by how you'd actually use them: is this a flat-rate API key you drop into OpenCode, a consumer subscription that unlocks Claude Code or Codex, an IDE-native agent like Cursor or Copilot, or a free BYOK harness you pair with any provider key?
Subscription value comparison
Price vs estimated monthly requests · hover for models, click to pin
Click a dot above to pin the plan's full details — price, exact usage cap, models with their SWE-bench scores, and harness compatibility.
257 plans with PAYG or unpublished caps not plotted
- MiniMax Token Plan — Starter · $10/mo · Starter tier — fraction of Plus window
- OpenCode Zen · PAYG ~$20 topup · PAYG — provider cost passthrough
- Windsurf Max · $200/mo · Unlisted rolling cap
- Cline · Free (indie) · Unlimited — you pay API
- OpenCode · Free · Unlimited — you pay API
- Continue · Free · Unlimited — you pay API
- GlobalGPT: Access Top AI Coding Models (Claude, GPT, Gemini & More) from $5.8/mo · From $5.8/mo
- Featherless: Flat-Rate Unlimited Tokens for 30,000+ Open LLMs
- Sao10k API: Full Model Pricing – All Token Costs & Context Lengths
- Tngtech R1T Chimera API: Free at $0.00 per 1M Tokens · Free ($0.00/1M tokens)
- AI Coding Plan Comparison: China & Global Subscriptions Side-by-Side · From ¥40/mo / $10/mo
- Trae AI Coding Plan: $1.30 First Month, then $5/mo · $1.30 first month, then $5/mo
- IBM Watsonx.ai: Granite Models from $0.60–$20 per Million Tokens · $0.60–$20/M tokens; $1,500–$5,000/mo minimum
- Prime Intellect INTELLECT-3: API Access from $0.20/1M Tokens · $0.20/1M tokens
- GLM Coding Plan: $18/mo Alternative to Claude Code · $18/mo
- Z.ai GLM Coding Plan: GLM-5.1 API Access for $10/Month · $10/mo
- OpenRouter: Free AI Coding Models incl. NVIDIA Nemotron 3 Super & OpenAI Agentic Model · Free ($0/M tokens)
- OpenRouter: 28 Free AI Models Including Gemma 4, Qwen3, Llama 3.3 & More · Free
- Mistral Codestral API: $0.30/$0.90 per MTok; Le Chat Pro $14.99/mo · $0.30/$0.90 per MTok (API); $14.99/mo (Le Chat Pro)
- Mistral API & Le Chat: Free tier + Pro at $14.99/mo (student $6.99/mo) · Free / $14.99/mo (Pro) / $6.99/mo (student)
- xAI Grok Build: AI Coding Agent Subscription Starting at $300/mo · $300/mo
- OpenRouter: 15+ Free AI Models via API — $0/M Input & Output Tokens · Free
- Arcee AI Trinity Large Preview Free on Krater.ai · Free
- Arcee AI: Trinity Large Thinking Free on OpenRouter (Limited Time) · Free (limited time)
- Qwen Coding Plan: AI Coding Subscription from ~$10/mo on Alibaba Cloud · From ~$10/mo (Lite) / ~$50/mo (Pro)
- ZAI GLM Coding Pro Plan: ~600 prompts/5hrs for $10.80/mo (discounted) · $10.80/mo (Pro, discounted)
- z.ai GLM5 Coding Plan: Usage-Based Tiers at 5h/1week/month
- Z.AI GLM Coding Plan: Subscription for Claude Code, Cline & OpenCode
- Cerebras Code Pro/Max: Fast Qwen3-Coder-480B at $50–$200/mo · $50/mo (Code Pro), $200/mo (Code Max)
- DeepSeek API: DeepSeek-V3 from $0.14/1M input tokens · $0.14/1M tokens
- Groq Cloud Free Tier: Free API Access with Rate-Limited Usage · Free
- Groq: Fast, Low-Cost AI Inference via GroqCloud API
- Fireworks AI FirePass: Unlimited Kimi K2.5 Coding Subscription
- Anthropic Claude API: From $1/M tokens (Haiku) + 50% Batch Discount · From $1/M input tokens; $200/mo (Max 20x)
- 50% Off Claude Code Pro Plan for 3 Months (New Users) · 50% off for 3 months
- OpenCodeGo: Unlimited AI Coding Models (DeepSeek, Kimi K2, Qwen) for $5/mo · $5/mo
- Krater.ai: Access Mancer Weaver (alpha) via Flat Monthly Subscription
- Claude Code 2026: Pro $20/mo, Max 5x $100/mo, Max 20x $200/mo + API Access · $20/mo (Pro), $100/mo (Max 5x), $200/mo (Max 20x), $25/seat/mo (Team)
- Kiro AI IDE: Free Tier + Paid Plans from $20/mo (2026 Pricing) · Free / $20/mo / $40/mo / $200/mo
- Tencent Cloud CodeBuddy Pro: 1,000 Credits Add-On for $9.95 · $9.95 (add-on pack, discounted from $19.90)
- Switchpoint API: Compare All Models & Per-Token Costs (2026)
- Nous Portal: Access 300+ AI Models with Exclusive Free Tiers & Discounts
- China AI Coding Plan Starting at 29 RMB/month · 29 RMB/mo
- Meituan API: Full Model & Token Pricing Guide (2026)
- Claude Code on Team Premium: AI Coding CLI at $100/seat/mo · $100/seat/mo (annual)
- Kimi Code: AI Coding CLI on Moderato Plan for $19/mo · $19/mo
- Moonshot AI Kimi K2.6 API: $0.95/$4.00 per MTok (Input/Output) · $0.95/$4.00 per MTok
- StepFun API Plans: Four Tiers from $6.99/mo to $99/mo · $6.99/mo – $99/mo
- BytePlus ModelArk Coding Plan: Multi-Model AI Coding (DeepSeek, Kimi, GPT & More)
- Mistral Devstral Small 2505: Free API Access for AI Coding · Free
- Mistral API & Le Chat: Free tier + Pro at $14.99/mo (student $6.99/mo) · Free / $14.99/mo (student: $6.99/mo)
- Xiaomi MiMo Token Plan: 20% Off Off-Peak AI Coding API Calls
- Kilo Code: Xiaomi MiMo-V2.5, MiMo-V2-Pro & MiMo-V2.5-Pro — Pay-As-You-Go, No Markup · Pay-as-you-go, no markup
- Alibaba Cloud AI Coding Plan: 4 Top Coding Models Under One Subscription
- Z.AI GLM Coding Plan: Cheapest Claude Code Alternative in 2026
- GLM Coding Plan: ~$30/mo for Practically Unlimited GLM 5.1 Access · $90/3 months (~$30/mo)
- DeepSeek API: Frontier Model Performance at 94–97% Less Than Competitors
- Fireworks FirePass: Unlimited Kimi K2 Turbo for $7/week · $7/week
- Google Developer Program: Gemini Code Assist + Cloud Credits for Developers
- OpenAI ChatGPT Pro: 5x More Codex Access for $100/month · $100/mo
- AiZolo All-in-One AI Free Plan: Chat, Audio Transcription & More · Free
- Mancer API: Full Model Lineup with Per-Token Pricing (2026)
- Cohere Free Tier: 1,000 API Calls/Month Across All Models · Free
- Apily: Unlimited Open-Source AI Models at $0.002/Request Flat Rate · $0.002/request
- Apily: Unlimited AI Coding API Access from $0.002/request Flat Rate · From $0.002/request
- NousResearch API: 20 Models from $0.17/M tokens via PricePerToken · From $0.170/M tokens
- Baidu Qianfan AI Coding Plan: New Customers Get First Month for $1.38 · $1.38/first month
- Perplexity API: Free Tier + Pro at $20/mo for AI Search & Coding · Free / $20/mo / $200/mo
- Amazon Q Developer: AI Coding Assistant with Free & Pro Plans on AWS · From $20/user/mo
- StepFun Step Plan: Subscription AI for Coders via Cursor, Claude Code & More
- Stepfun-ai API: Step 3.5 Flash from $0.10/1M Input Tokens · From $0.10/1M tokens
- Atlas Cloud Seedance 2.0 API: Fast Tier from $0.022/sec — 91% Cheaper than Pro · $0.022/sec
- MiniMax Token Plan: Subscription API Access for Text, Speech, Video & More
- MiniMax Coding Plan: Predictable Pricing for AI Coding via Kilo Code
- Xiaomi MiMo v2 Pro API: $1/M input tokens, $3/M output tokens · $1.00/M input, $3.00/M output tokens
- Xiaomi MiMo API: Monthly & Annual Token Subscription Plans Available
- xAI Grok API: Pay-per-token pricing for Grok 4.3 + Batch API at 50% off
- xAI Grok API: Grok 4.1 Fast from $0.20/M input, Grok 4.3 at $1.25/M input · From $0.20/M input tokens
- Arcee AI Trinity Builders Program: Free API Credits for Developers & Researchers · Free (credit grant)
- Arcee AI: Pay-per-token pricing for AI models on Arcee Platform · Per 1M tokens (price varies by model)
- Arcee AI API: Full Model Lineup with Per-Token Pricing (2026)
- Top 6 AI Coding Subscription Plans for 2026: $9–$250/mo Verified · $9–$250/mo
- DeepSeek API: $0.27/M input & $1.10/M output tokens for V4 · $0.27/M input tokens, $1.10/M output tokens
- Fireworks Fire Pass: Unlimited Kimi K2.6 Turbo for Agentic Coding — $49/mo · $49/mo
- Fireworks Fire Pass: Unlimited Kimi K2.5 Turbo for $7/week · $7/week (first week free)
- Anthropic Claude API & Claude.ai: Plans from $20/mo or Pay-Per-Token · From $20/mo
- Alibaba Cloud Coding Plan: Multiple Top Models (Qwen3.5-Plus, Kimi K2.5 & more) from $3 · From $3
- Reka API: Pay-As-You-Go Pricing with No Upfront Costs
- SiliconFlow on OpenRouter: DeepSeek V4 Flash Free + V4 Pro from $1.74/M tokens · Free (Flash) / $1.74/M input tokens (Pro)
- Atlas Cloud: Pay-Per-Use AI API Access Across 300+ Models
- Atlas Cloud: 30% Off First Month + Free Tier for 300+ AI Models · Free tier available; 30% off first month
- Atlas Cloud: Pay-As-You-Go API for 300+ AI Models + 20% First Top-Up Bonus · Pay-as-you-go
- DeepInfra: DeepSeek V4 Pro at $1.74/1M input, $3.48/1M output tokens · $1.74/1M input tokens, $3.48/1M output tokens
- GMI Cloud: Zero-Commitment AI Inference from $0.000001–$0.50 per Request · $0.000001–$0.50/request
- Alibaba Cloud: Low-Cost AI Coding Plans with API Access to 4 Models
- Gryphe API: Full Model & Token Pricing Guide (2026)
- Puter Developer API: Free Access to MiMo, Mistral, Qwen, OLMo & More
- Krater.ai: Access 350+ AI Models (ChatGPT, Claude, Gemini & More) in One Platform
- Morph.ai: Pay-As-You-Go AI Coding Starting at $53 · From $53
- Krater AI: Access DeepSeek R1T2 Chimera & More — Plans from $9/mo · From $9/mo
- AI21 Labs: $10 Free Credit for New API Accounts (3-Month Trial) · $10 free credit
- ZeroTwo AI: All-in-One AI Platform Subscription at $29.99/mo · $29.99/mo
- Nous Portal: 300+ Models incl. Hermes Agent in One Subscription
- IBM watsonx Code Assistant: Free Local AI Coding with Granite Models · Free
- Use IBM Granite 4.1 8B on Krater.ai
- Kimi K2 by Moonshot AI: Pricing Plans for Advanced AI Model
- StepFun API: step-3.5-flash-2603 Reasoning Model from $0.02/1M tokens · From $0.02/1M tokens
- StepFun Step 3.5 Flash via OpenRouter: $0.10 input / $0.30 output per 1M tokens · $0.10/1M input, $0.30/1M output
- OpenRouter: 29 Free AI Models Available — No Spend Required · Free
- OpenRouter: 25+ Free Models + Pay-As-You-Go Access to 400+ AI Models · Free tier available; PAYG with 5.5% platform fee
- AionLabs Aion-1.0: API Access at $4/1M Input, $8/1M Output Tokens · $4.00/1M input, $8.00/1M output
- MiniMax Token Plan: 12% OFF – "50x Cheaper Than Claude" for Coding · 12% OFF
- Alibaba Cloud AI Coding Plan: One Sub, One API Key, 4 Powerful Coding Models
- Alibaba Cloud Coding Plan: Unlimited AI Coding API Access (Qwen, Kimi K2.5, GLM & More)
- z.ai GLM Coding Plan: Claude Code, Cline & 10+ Tools from $3/mo · From $3/mo (10% off with code YJTABNTFIP)
- Cerebras AI: Subscribe for Fast AI Training & Inference
- Cerebras Free Tier: 1M Tokens/Day — No Credit Card Required · Free
- DeepSeek API: Free 5M Token Grant + V4 Pro 75% Off Through May 31, 2026 · From $0.14/M tokens; 5M free on signup
- Google AI Studio & Gemini API: Free Tier for Developers · Free
- Google AI Pro/Ultra: Higher AI Studio & Gemini API Limits from $19.99/mo · $19.99/mo (Pro), $249.99/mo (Ultra)
- DeepInfra: NVIDIA Nemotron Models from $0.04/1M tokens · From $0.04/1M input tokens
- DeepInfra: Pay-as-you-go API for Qwen3-Coder, Llama-4, Nemotron & More · From $0.04/M tokens
- DeepInfra: Qwen 2.5 72B API at $0.23/M Tokens — 1/10th the Price of GPT-4o · $0.23/M tokens
- GMI Cloud: Run Claude Code Pay-As-You-Go — No $100–200/mo Subscription · Pay-as-you-go
- io.net Decentralized GPU Cloud: $15/mo in Usage Credits Included · $15/mo in credits
- io.net IO Intelligence: Developer Plan with ~10% Discount vs PAYG
- Chutes AI: Base Plan with $15 Credits for $3/month · $3/mo
- AkashML: Managed AI Inference on Decentralized GPUs — 70-85% Cost Savings
- Inflection API: Inflection 3 Pi & Productivity at $2.50/1M Input Tokens · $2.50/1M input tokens, $10.00/1M output tokens
- Claude Code: Plans from $20/mo Pro to $200/mo Max + API Pay-per-Token · From $20/mo (Pro); $100–$200/mo (Max); pay-per-token (API)
- Claude Code: Free tier + plans from $20/mo up to $200/mo for heavy devs · Free / $20/mo / $100–$200/mo
- Krater.ai: TNG DeepSeek R1T Chimera Available Free · Free
- GLM AI Coding Plans: From 7.9 RMB/mo for 10M daily tokens (Qwen3, DeepSeek, Kimi) · From 7.9 RMB/mo (intro) / 39 RMB/mo (regular)
- Tencent Cloud Coding Plan – Subscription for AI Coding Services
- ByteDance Doubao-Seed-Code: AI Coding Agent for ~$1.30/mo (Promo) · ~$1.30/mo (promo); ~$5.50/mo standard
- AiZolo: Multi-Model AI Workspace with Free Tier & Plans from $9.90/mo · Free / $9.90/mo
- INTELLECT-3: API Access from $0.20/M input & $1.10/M output tokens · $0.20/M input, $1.10/M output tokens
- Kimi Code: Moonshot AI Coding API at $0.60/$2.50 per MTok + $19/mo Membership · $0.60/$2.50 per MTok + ~$19/mo
- Claude Code Free Forever via OpenRouter's Free Tier · Free
- OpenRouter: Access 100s of AI Models with Pay-As-You-Go Pricing · From $0.05/sec (video); $0.25–$0.30/image
- Krater.ai: Use Aion-2.0 via Flat Monthly Subscription — No Per-Token Billing
- Krater.ai: Use Inception Mercury Coder via Flat Monthly Subscription
- Inception API: Full Model & Token Pricing Guide (2026)
- Bytedance Seed 2.0 Lite API: $0.25/1M input tokens, $2.00/1M output tokens · $0.25/1M input, $2.00/1M output
- Mistral AI Studio: Free Tier + Scale Plan for API Access · Free (Experiment) / Paid (Scale)
- MiniMax M2.7 API: $0.30/M input, $1.20/M output tokens · $0.30/M input, $1.20/M output
- TokenMonopoly: Best AI Coding Subscription Plans Roundup for 2026 · Free – $50/mo
- Xiaomi API: MiMo-V2-Flash from $0.09/1M Input Tokens · From $0.09/1M input tokens
- Hermes Guide AI Coding Bundles: Stacked Plans from $30/mo · From $30
- Alibaba Cloud Qwen Coding Plan: Up to 90K AI Coding Requests from ~$10/mo · From ~$10/mo (Lite) / ~$50/mo (Pro)
- codingplan.org: Compare Claude Code, GLM, MiniMax, Kimi & Qwen Coding Plans · Free (GLM tier); $20/mo (Claude Code Pro)
- zAI GLM Coding Plans: Frontier AI Coding with Cline from just $3/mo · $3/mo (Lite) · $15/mo (Pro)
- Z.ai: Unlimited AI Coding with GLM-5.1 & GLM-5-Turbo for Agents & IDEs
- DeepSeek API: V3.2 at $0.28/M input & $0.42/M output tokens · $0.28/M input, $0.42/M output tokens
- Groq: Free API Key + Low-Cost Fast Inference via GroqCloud · Free (paid tiers available)
- Groq API Free Tier: Llama 3.3, Llama 4 Scout & More at No Cost · Free
- Fireworks FirePass: Unlimited Kimi K2.5 Turbo for $7/week · $7/week (first week free)
- Google AI Pro & Ultra: Gemini API access in AI Studio included
- Google AI Studio Included in AI Pro & Ultra Plans at No Extra Cost · Included with AI Pro/Ultra
- Google AI Pro/Ultra: Increased AI Studio Usage Limits for Subscribers
- Awesome Free LLM APIs: Curated List of Free-Tier AI Coding APIs · Free
- GitHub Copilot Free Tier: 2,000 Code Completions + 50 Premium Requests/mo · Free
- Chutes on OpenRouter: Pay-per-token access to Kimi K2, DeepSeek-V3.2 & more
- Chutes: Deploy & Run AI Models with Serverless API Access · Free
- AkashML: Pay-as-You-Go Decentralized AI Inference API
- AkashML on OpenRouter: Pay-per-token AI API Access
- Krater.ai: 20% Off AI Coding Subscription (Venice Alternative) · 20% Off
- Venice AI: Paid Plan from $12.41/mo + Free Tier Available · From $12.41/mo
- Venice AI: OpenAI-Compatible API Starting at 10 Credits per 1M Tokens · From free (Pro) with credit-based tiers
- Venice AI: Free Forever Plan + Pro at $18/mo · Free / $18/mo
- Novita AI: Coding Packages Live — Lower Cost, More Tokens
- Novita AI Coding Plan: 150M Tokens/Month for $50/mo · $50/mo
- Novita AI Coding Plan: 7 Top Models via Unified API, Low-Cost Token Bundles
- Parasail: Pay-Per-Token AI Inference — No Limits, No Contracts · Pay-per-token
- Alibaba AI Coding Pro Plan: API Access to 4 Models from $5.50/mo · $5.50/first mo, then $29/mo
- Alibaba Cloud Multi-Model AI Coding Subscription from $1/mo · From $1/mo
- Alibaba Cloud Coding Plan: Flat-Rate AI Coding Models for $50/mo · $50/mo
- Mancer: Pay-as-you-go AI Coding Models with Credit-Based Pricing
- Mancer: Pay-as-You-Go API Credits for LLMs (Free Models Available)
- Cohere Trial API: 1,000 Free API Calls/Month Across All Models · Free (1,000 calls/mo) / $2.50 per 1M input tokens
- Cohere API Pricing: All Models & Token Costs (2026)
- EleutherAI API: Full Model & Token Pricing Guide (2026)
- Morph: Free Tier + Pro Plan for AI Code Editing & Search API · Free (200 req/mo); Pro pricing not stated
- Alibaba Coding Plan: Switch Freely Between 4 Chinese Open-Source Models
- Tencent CodeBuddy: AI Code Editor Pro Plan + 1,000 Credits Add-on for $9.95/mo · $9.95/mo (1,000 Credits add-on)
- Tencent Cloud CodeBuddy Pro: AI Coding Assistant at $9.95/month (50% Off) · $9.95/month (orig. $19.90/month) or $119.40/year
- Tencent Cloud Coding Plan: Hunyuan 3 Access for ¥9.9 First Month · ¥9.9/first month
- BytePlus ModelArk Coding Plan: AI Coding Subscription with Bytedance-Seed-Code · $10/mo (Lite plan)
- ByteDance Volcano Engine: Doubao-Seed-Code Coding Agent for $1.30/first month · $1.30/first month
- China's Top 7 AI Coding Subscriptions Compared: Plans from ~7.9 CNY/mo · From 7.9 CNY/first month; up to 200 CNY/mo
- Trae AI Coding Plan: $1.30 First Month, then $5/mo · $1.30 first month, then $5/mo
- Nous Portal: Credits for Hermes Agent & Hundreds of AI Models
- Krater.ai: Access AI Models Including LongCat Flash Chat from $9/mo · From $9/mo
- Prompts.ai: Free Plan with 30 Credits & Access to GPT-5 Mini, Grok-3 Mini, Claude 3.5 · Free ($0/mo)
- Thedrummer API Pricing: Per-Token Costs for All Models (2026)
- $3/mo AI Coding Plan: Flat Rate for Qwen, Kimi & More · $3/mo
- Baidu Qianfan Coding Plan: Subscription-Free AI Coding with GLM & DeepSeek · Free (Subscription-Free)
- Zhipu AI GLM Coding Plan: Paid Subscription for AI Programming
- Alibaba Cloud Coding Plan: Subscription for AI Coding Models incl. Qwen3-Coder
- Baidu Qianfan AI Coding Plan: First Month for $1.38 for New Users · $1.38/first month
- IBM Granite API: Full 2026 Per-Token Pricing for All Models
- Perplexity Sonar API: From $5/1K requests for AI-powered search · From $5/1K requests
- Prime Intellect Hosted Training: Pay-as-you-go for Open-Weights Models
- Prime Intellect API: Full Model Lineup with Per-Token Pricing (2026)
- Amazon Q Developer: Free Tier + Pro Plan for AI Coding Assistant · Free / Pro (price not stated)
- Puter.js: Free Nex AGI API Access — No Backend or API Keys Needed · Free
- OpenRouter: Nex AGI DeepSeek V3.1 Nex N1 Free Tier via API · Free
- Relace Apply 3 API: $0.85/1M input tokens, $1.25/1M output tokens · $0.85/1M input, $1.25/1M output
- Relace AI: Token-Based Pricing for Code Generation & Embeddings
- Relace API: Full Model & Token Pricing Guide (2026)
- Upstage Solar Pro 3 Free on Krater.ai · Free
- StepFun Step Plan: Predictable AI Agent API Pricing for Developers
- StepFun Step-3.5-Flash: AI Coding Subscription Starting at $6.99/mo · $6.99/mo
- OpenRouter: Unified LLM API — Pay-Per-Use, No Subscription Required
- OpenRouter: Pay-Per-Token Access to 323+ AI Models, No Monthly Fees · Pay-per-token; free tier available
- ZenMux Free Tier: Access 25+ AI Models Across 4 Providers at No Cost · Free
- ZeroTwo: Unlimited Access to 60+ AI Models (incl. OpenRouter) for $29.99/mo · $29.99/mo
- AIonX 5-AI Bundle: ChatGPT, Claude, Gemini, Grok & SeeDream for $30/mo · $30/mo
- Aion 2.0 API: From $0.80/M input & $1.60/M output tokens · $0.80/M input, $1.60/M output tokens
- Volcano Engine Doubao-Seed-Code: Coding Agent Promo at $1.3 for First Month · $1.3 (first month promo)
- Bytedance-seed API: Seed 1.6 Flash from $0.075/1M input tokens · From $0.075/1M input tokens
- Mistral AI API: Free tier + Pro from $14.99/mo (incl. Codestral) · Free / $14.99/mo / $24.99/mo
- Mistral AI: Free Experiment Tier + Up to $30K in Startup API Credits · Free / Up to $30K credits
- Mistral AI Free Tier: All Models (incl. Codestral) — 1B Tokens/Month Free · Free
- MiniMax M2.7 Coding Powerhouse API: $1/hour Token Plan · $1/hour
- MiniMax M2.5: AI Coding API from $0.15/M tokens — 20× cheaper than Claude Opus · $0.15/M tokens
- Xiaomi MiMo API: AI Coding-Capable Model API with Public Beta Access
- OpenRouter: Xiaomi MiMo-V2-Pro – API Access with 256K Context
- Xiaomi Coding Plan: Unlimited Token-Based Access for $6 · $6
- Kwaipilot API: Full Model & Token Pricing Guide (2026)
- xAI Grok API: From $0.20/M Tokens + $175/Month Free Credits · From $0.20/M tokens; $175/mo free credits
- Alibaba Cloud AI Coding Plan: Qwen3-Coder + Claude Code API Access
- Alibaba Cloud "Ultimate Coding Plan": API Access to 8 Top Models incl. Qwen3.5, Kimi K2.5
- Alibaba Qwen Code: New Coding Plan Pro Subscription at $50/mo · $50/mo
- Qwen Coding Plan: Lite $10/mo or Pro $50/mo for AI Coding API · $10/mo (Lite), $50/mo (Pro)
- Z.ai GLM Coding Plan: AI Coding Subscription Powered by GLM-5.1 & GLM-5-Turbo
- Cerebras Inference API: Developer Free Tier + Pro at $50/mo · Free / $50/mo
- Cerebras Code Pro: High-Speed AI Code Generation API at $50/month · $50/mo
- Cerebras Code Pro/Max: Unlimited Qwen3-Coder at 2,000 tok/s from $50/mo · $50/mo (Pro), $200/mo (Max)
- DeepSeek API: deepseek-v4-pro at 75% Discount Until May 31, 2026 · 75% off
- DeepSeek API: 5M Free Tokens for New Users + Competitive Paid Rates · Free (5M tokens)
- Groq Free Tier: Access All Models on Ultra-Fast LPU Hardware — No Credit Card · Free
- Fireworks AI: Serverless API Pricing — Models from $0.50/M tokens · From $0.50/M tokens
- Fireworks AI Quietly Launches a Coding Subscription for Developers
- Fireworks AI: $1 Free Starter Credits Across 50+ Models · $1 free credits
- Google AI Studio: Free API Access to Gemini, Imagen, Veo & More · Free
- Google AI Studio: Free Browser-Based Access to Gemini Models for Developers · Free
- Google AI Studio: Free Tier + Pay-As-You-Go API for AI Coding · Free / Pay-as-you-go
- OpenAI ChatGPT Pro Tier: 5x Codex Usage Limits for $100/mo · $100/mo
- OpenAI ChatGPT Pro: 5x Codex Usage for $100/mo vs $20 Plus Plan · $20/mo (Plus) or $100/mo (Pro)
- OpenAI ChatGPT $100/mo Tier: 5x–10x More Codex Usage Than Plus · $100/mo
- Claude Code: Pro $20/mo, Max $100–$200/mo, or Pay-as-You-Go API · $20/mo (Pro), $100–$200/mo (Max), pay-per-token (API)
- 50% Off Claude Code Pro Plan for 3 Months (New Users) · 50% off for 3 months
- Augment Code: AI Coding Plans for Individuals, Teams & Enterprise
- Alibaba Cloud AI Coding Plan: 18K Requests/Month from $3 First Month · $3/mo (intro), then $10/mo
- Pi AI Coding Harness: Free & Open Source – Bring Your Own API Keys · Free
- 2026 Free AI API Credits: $200+ Across 15+ Providers, No Card Needed · Free
All subscription deals
Hand-curated catalog of every subscription, flat-rate, and free-harness plan worth knowing about for coding use in 2026. Grouped by how they connect to harnesses.
Flat-rate API subscriptions
API key from a monthly subscription. Best value for power users of external harnesses — no per-token metering.
Flat weekly rate for high-volume Kimi K2.5 Turbo access. API key works in any OpenAI-compatible harness.
- Models
- Kimi K2.5 Turbo
- Limit
- Unlimited tokens (RPM throttled)
- Harness
- OpenCode, Cline, Roo, any OpenAI-compat
Flat monthly rate giving API access to Claude-class frontier models. Drop the key into any agent framework.
- Models
- Claude-class frontier
- Limit
- Unlimited tokens, 135 concurrent requests
- Harness
- Cline, Roo, OpenCode, any framework
Entry tier of MiniMax's flat-rate API bundle. Uses standard API keys so any harness works.
- Models
- MiniMax M2.7
- Limit
- Starter tier — fraction of Plus window
- Harness
- OpenCode Zen, Cline, Roo, OpenClaw
Mid-tier MiniMax subscription with 4,500 requests per 5-hour window. Best price/volume ratio in the flat-rate bucket.
- Models
- MiniMax M2.7 + speech/image
- Limit
- 4,500 req / 5hr
- Harness
- OpenCode Zen, Cline, Roo, OpenClaw
Top MiniMax tier, 15,000 requests per 5-hour window plus all modalities. For continuous agent workflows.
- Models
- MiniMax M2.7 + all modalities
- Limit
- 15,000 req / 5hr
- Harness
- OpenCode Zen, Cline, Roo, OpenClaw
Pay-as-you-go gateway to multiple frontier models at zero markup. No monthly fee — just top up and use.
- Models
- Kimi K2.5, GPT-5-Codex, Gemini, Claude
- Limit
- PAYG — provider cost passthrough
- Harness
- OpenCode native, any via key
Consumer subscriptions (harness-compatible)
Standard chatbot plans that can be unlocked for harness use via subscription auth plugins. You keep the chat app, you also get the CLI.
Standard Claude chat subscription. Claude Code subscription auth is reusable by OpenCode, Cline, and other harnesses. Some third-party restrictions apply on Max tokens.
- Models
- Claude Sonnet 4.6
- Limit
- ~45 Sonnet msgs / 5hr
- Harness
- Claude Code, OpenCode, Cline (sub auth)
- Own agent
- Claude Code
~225 Sonnet messages per 5-hour window (5× Claude Pro). Claude Code subscription auth reusable by OpenCode, Cline, and other harnesses — though Anthropic restricts some third-party consumers of Max tokens.
- Models
- Claude Sonnet 4.6, Opus 4.6
- Limit
- ~225 Sonnet msgs / 5hr
- Harness
- Claude Code, OpenCode, Cline (sub auth)
- Own agent
- Claude Code
~900 Sonnet messages per 5-hour window (20× Claude Pro). Heaviest Claude Code tier for full-day Opus runs. Subscription auth reusable by OpenCode / Cline with some third-party restrictions.
- Models
- Claude Sonnet 4.6, Opus 4.6
- Limit
- ~900 Sonnet msgs / 5hr
- Harness
- Claude Code, OpenCode, Cline (sub auth)
- Own agent
- Claude Code
Baseline Codex tier. Token-based 5-hour windows (since Apr 2 2026). Codex OAuth works in OpenCode, ForgeCode, Cline and other OpenAI-compatible harnesses.
- Models
- GPT-5, o3, o4-mini, GPT-5 Codex
- Limit
- 600–3,000 Codex local msgs / 5hr
- Harness
- Codex CLI, OpenCode, ForgeCode, Cline (Codex OAuth)
- Own agent
- Codex CLI
New $100 Pro tier (Apr 9 2026). 5× Codex of Plus — built for heavy agentic coding sessions. Same model access as $200 Pro. 10× boost through May 31 promo.
- Models
- GPT-5, o3, o4-mini, GPT-5 Codex
- Limit
- 3,000–15,000 Codex local msgs / 5hr (5× Plus)
- Harness
- Codex CLI, OpenCode, ForgeCode, Cline (Codex OAuth)
- Own agent
- Codex CLI
Maximum Codex throughput — 20× Plus limits. Unlimited GPT-5 Instant/Thinking, 250 Deep Research runs/mo. Same harness OAuth as other tiers.
- Models
- GPT-5, o3, o4-mini, GPT-5 Codex
- Limit
- 12,000–60,000 Codex local msgs / 5hr (20× Plus)
- Harness
- Codex CLI, OpenCode, ForgeCode, Cline (Codex OAuth)
- Own agent
- Codex CLI
Gemini 2.5 Pro consumer tier. Jules and Code Assist ship native; OpenCode authenticates via the gemini-auth plugin for harness use.
- Models
- Gemini 2.5 Pro
- Limit
- 100 Gemini 2.5 Pro msgs / day
- Harness
- Jules, Code Assist, OpenCode (gemini-auth)
- Own agent
- Jules, Code Assist
Formerly ChatGPT Team. Per-seat pricing with admin console, SOC 2, SAML SSO. Standard seats include full Codex access with token-based credits.
- Models
- GPT-5, o3, o4-mini, GPT-5 Codex
- Limit
- ~600 Codex msgs / 5hr (per seat)
- Harness
- Codex CLI, OpenCode, ForgeCode, Cline (Codex OAuth)
- Own agent
- Codex CLI
IDE / terminal native agents
Ship their own harness in-editor. Most also allow BYOK so you can drive external tools with the same plan.
Intent agent for VS Code / JetBrains / CLI. 40k credits/mo, uses Augment's own models — no BYOK.
- Models
- Augment proprietary
- Limit
- 40,000 credits / mo
- Harness
- Intent CLI (internal)
- Own agent
- Intent
Team tier: 130k credits/mo, up to 20 users. Same locked-in Augment models.
- Models
- Augment proprietary
- Limit
- 130,000 credits / mo
- Harness
- Intent CLI (internal)
- Own agent
- Intent
Heavy-use tier: 450k credits/mo. Still locked to Augment's models.
- Models
- Augment proprietary
- Limit
- 450,000 credits / mo
- Harness
- Intent CLI (internal)
- Own agent
- Intent
Terminal AI agent with BYOK unlocked. 1,500 credits/mo.
- Models
- Multi (BYOK)
- Limit
- 1,500 credits / mo
- Harness
- Warp Agent + BYOK
- Own agent
- Warp Agent
10,000 credits/mo for Warp's terminal agent, with BYOK support.
- Models
- Multi (BYOK)
- Limit
- 10,000 credits / mo
- Harness
- Warp Agent + BYOK
- Own agent
- Warp Agent
Top Warp tier at 18,000 credits/mo. BYOK available.
- Models
- Multi (BYOK)
- Limit
- 18,000 credits / mo
- Harness
- Warp Agent + BYOK
- Own agent
- Warp Agent
Cursor IDE with Claude + GPT agent mode. BYOK supported for external API use.
- Models
- Claude + GPT (multi)
- Limit
- 500 premium req / mo
- Harness
- Cursor IDE + BYOK
- Own agent
- Cursor Agent
10,000 premium requests per month across all frontier models. Top tier for Cursor heavy users.
- Models
- All frontier (multi)
- Limit
- 10,000 premium req / mo
- Harness
- Cursor IDE + BYOK
- Own agent
- Cursor Agent
Windsurf IDE agent with 500 credits/mo and BYOK support.
- Models
- Multi (BYOK)
- Limit
- 500 credits / mo
- Harness
- Windsurf IDE + BYOK
- Own agent
- Windsurf Agent
Rolling-window power user tier for Windsurf. BYOK available.
- Models
- Multi (BYOK)
- Limit
- Unlisted rolling cap
- Harness
- Windsurf IDE + BYOK
- Own agent
- Windsurf Agent
Copilot with agent mode in VS Code + JetBrains. 300 advanced requests, MCP-compatible, BYOK supported.
- Models
- Multi (BYOK)
- Limit
- 300 advanced req / mo
- Harness
- VS Code + JetBrains + MCP + BYOK
- Own agent
- Copilot Agent
Higher Copilot tier with access to all frontier models and higher request limits.
- Models
- All frontier (multi)
- Limit
- 1,500 premium req / mo
- Harness
- VS Code + JetBrains + MCP + BYOK
- Own agent
- Copilot Agent
BYOK harnesses (free platform)
Free (or near-free) harness platforms. Pair these with any API key from the sections above.
Open-source VS Code + CLI agent. Free for individuals, $20/mo for teams. Drop in any provider key.
- Models
- Any (BYOK)
- Limit
- Unlimited — you pay API
- Harness
- VS Code + CLI, any provider key
- Own agent
- Cline Agent
Free terminal TUI agent. Plug in any provider or use Zen as an optional gateway.
- Models
- Any (BYOK)
- Limit
- Unlimited — you pay API
- Harness
- Any provider key, Zen optional
- Own agent
- OpenCode Agent
Free VS Code / JetBrains plugin. Works with any OpenAI-compatible provider.
- Models
- Any (OpenAI-compat)
- Limit
- Unlimited — you pay API
- Harness
- VS Code + JetBrains, any OpenAI-compat key
- Own agent
- Continue Agent
What "BYOH" means on these cards
BYOH = Bring Your Own Harness. A deal is marked BYOH when the API key or subscription auth it provides can be plugged into an external coding agent like OpenCode, Cline, ForgeCode, Roo, or any OpenAI-compatible tool. The opposite is "Locked in", meaning the plan only works inside the vendor's own agent. For most harness users, BYOH plans are strictly more flexible.