Auto Mode: How Smart Routing Stretches Your Token Budget
Auto mode picks the cheapest capable model per task. Manual selection gives you control with transparent cost multipliers.
Every message you send doesn't need GPT-5.6. File reads, shell commands, and simple edits run perfectly on cheaper models. Auto mode routes each task to the most cost-effective model — your pool lasts the full month without sacrificing quality where it matters.
How Auto Mode Works
Auto classifies each message into a task type: tool operations (file reads, shell commands), code generation, reasoning, or premium (complex architecture). It then picks the cheapest model that handles that task well. Tool ops go to DeepSeek Flash. Code gen goes to GLM-5.2. Complex reasoning goes to Gemini 3.1 Pro or GPT-5.6. You pay 1.0x — one token from your pool per token used.
Manual Selection: You Choose, You Pay
Want a specific model? Go for it. Each model has a transparent multiplier that adjusts how fast your pool drains. DeepSeek Flash at 0.10x stretches your pool 10x. GLM-5.2 at 1.18x drains slightly faster. GPT-5.6 at 3.90x drains nearly 4x faster. The multiplier is shown in the model dropdown so you always know the cost before sending.
What You Get Per Plan
Free: 1M tokens (auto only). Lite: 30M tokens. Starter: 70M tokens. Pro: 190M tokens. Elite: 390M tokens. On Auto, these are face-value. On manual selection, the effective amount depends on the model — cheaper models stretch further, premium models use more. The dropdown shows your effective balance for each model in real time.
Why This Beats Fixed Model Pricing
Other platforms charge per-request or give you a fixed number of "premium" and "fast" requests. With Multos, you have one pool and full flexibility. Use Auto for maximum efficiency, or manually pick models when you need specific capabilities. No separate buckets, no wasted fast credits, no surprise overages.
Ready to Get Started?
Start with 1M free tokens — Auto mode picks the best model for every task.
Start Building FreeRelated Articles
GPT-5.6 Luna Price Cut 80% — Now Available on Free & Lite
OpenAI slashed GPT-5.6 Luna by 80% overnight — from $1/$6 to $0.20/$1.20 per million tokens. We're passing it straight through: Luna is now available on every plan including Free and Lite.
Read more →Claude Opus 5 & Sonnet 5 Now Available: Near-Frontier Intelligence at Every Tier
Anthropic's Claude Opus 5 and Claude Sonnet 5 are now live on Multos. Opus 5 delivers near-Fable-5 intelligence at half the price with 79.2% on SWE-bench Pro, while Sonnet 5 brings Opus-class agentic capabilities to Starter-tier users at $3/$15 per million tokens.
Read more →Kimi K3 Now Available: The World's Largest Open-Weight Model on Multos
Moonshot AI's 2.8-trillion-parameter Kimi K3 is now live on Multos. A frontier-class open model with a 1M token context window, ranked #1 on Frontend Code Arena and #4 overall on Artificial Analysis Intelligence Index.
Read more →