A plug-and-play model gateway
MyTabulon Coding Plans
MyTabulon Coding Plans give every workspace direct, OpenAI-compatible access to leading coding models from the agents, IDE extensions, and SDKs developers already use. Free starts with limited Maximo Atlas 1.2 access and no card. Paid tiers add more models, larger usage pools, and higher concurrency. Your prompts and tools reach the selected model without an appended system prompt or injected tools.
maximo-atlas-1.2maximo-atlas-previewmaximo-pandora-3.8maximo-pandora-3.8-nanogoogle/gemini-3.5-flash-litemuse-spark-1.1muse-spark-1.2deepseek/deepseek-v4-flash-0731deepseek/deepseek-v4-pro-0813openai/gpt-5.6-lunamaximo-pandora-3.8-prox-ai/grok-4.6google/gemini-3.6-flashmoonshotai/kimi-k3openai/gpt-5.6-terraanthropic/claude-opus-5google/gemini-3.1-proopenai/gpt-5.6-sol- Free includes limited Maximo Atlas 1.2 access (with Atlas Preview retiring on August 15, 2026) and 2 concurrent requests. Plus is $3/week or ₦3,000/week for 11 models and 10 concurrent requests. Pro is $9/week or ₦9,000/week for 19 models and 25 concurrent requests. Max is $15/week or ₦15,000/week for all 21 models and 50 concurrent requests.
- Paid Coding Plan model access follows the matching MyTabulon workspace tier. Plus includes Maximo Atlas 1.2, Maximo Pandora 3.8 Preview, Maximo Pandora 3.8 Nano, DeepSeek V4 Flash (0731), DeepSeek V4 Pro (0813), GPT-5.6 Luna, Gemini 3.5 Flash-Lite, Meta Muse Spark 1.1, and Meta Muse Spark 1.2. Pro adds models such as Maximo Pandora 3.8 Pro Preview, Grok 4.6, Kimi K3, Gemini 3.6 Flash, Claude Opus 5, and GPT-5.6 Terra. Max adds Gemini 3.1 Pro and GPT-5.6 Sol.
- Model context is not reduced by the Coding Plan. Requests can use each selected model's native supported context window.
- Maximo Atlas 1.2 costs $0.55/M cache-miss input, $0.05/M cached input, and $1.50/M output. Maximo Pandora 3.8 Preview starts on Plus and costs $1.50/M cache-miss input, $0.085/M cached input, and $4.20/M output. Maximo Pandora 3.8 Nano is now generally available: it costs $0.15/M input, $0.015/M cached input, and $0.55/M output through 226K input tokens, then $0.25/M input, $0.025/M cached input, and $0.95/M output above 226K. The provider's full input count selects the Nano tier, and that tier applies to the full request. DeepSeek V4 Flash 0731 and V4 Pro 0813 use the rates published for their current revisions: from 16:00 UTC on August 16, 2026, off-peak is Flash $0.007/$0.22/$0.66 and Pro $0.022/$0.66/$1.98 for cache-hit input/cache-miss input/output, while peak is Flash $0.014/$0.44/$1.32 and Pro $0.044/$1.32/$3.96. Peak is 01:00–04:00 and 06:00–10:00 UTC; all other hours are off-peak. Coding Plan usage pools are shared across every model available on the plan.
- Both OpenAI Chat Completions and Responses APIs are supported, including tool calling, streaming, image and file inputs, structured output, and standard parameters at POST https://api.mytabulon.com/v1/chat/completions and POST https://api.mytabulon.com/v1/responses.
- Usage draws from tier-sized pools with two limits, shown only as percentages on the dashboard and via GET /v1/coding-plan/usage. Plus keeps the same usage pools as the original Coding Plan.
- Every user has a Coding Plan developer link. The invited developer gets 50% more five-hour and weekly usage for the first paid week; after their first successful API request, the referrer can claim a seven-day 50% Usage Boost or a seven-day Coding Plus pass when referring from Free.
- Creators and developer community leaders can apply for MyTabulon Developer Partners. Approved partners earn 25% of net Coding Plan revenue for the first 12 successful weekly payments per referral, with a 30-day protection period and monthly payouts.
- Fixed 5-hour window: your first API request opens a 5-hour window; usage fully resets when the window ends (it is not a rolling average).
- Weekly limit: a 7-day cap anchored to your billing date and re-anchored on each renewal. When either limit is reached the API returns 429 with both reset times.
- For the fastest start, install the Maximo Syntax CLI (npm install -g @maximoai/maximo-syntax-cli), run maximo, and sign in with MyTabulon — your Coding Plan links automatically with no key. Or create a live platform API key (mtb_live_) with the ai.coding scope and follow the ready-to-copy Codex, Kilo Code, or OpenClaw guide on the developer platform.
- The model comparison shows published benchmark signals, context, pricing, and source links beside a transparent value recommendation. It never presents missing or incomparable benchmark results as a made-up composite score.

