Free to start.
Every model in one place.
Two ways to use qlaud. qcode — chat + code with every model on a free or paid plan. Developer API — pay-as-you-go with a flat 7% over upstream prices.
Plans for chat + code
For humans using qcode in the browser or on desktop. Cancel any time.
Up to 7M tokens to try qcode.
Sign up — no card- Up to 7M tokens — cheap-tier models
- DeepSeek, MiniMax, Qwen, Kimi, Llama
- All connectors (Linear, Slack, GitHub, …)
- Web + desktop apps
- Premium models (Opus, GPT-5-pro) on Pro
- ~7M tokens on cheap-tier models
- ~14-20 substantial coding turns
- One-time trial credit (no monthly reset)
Up to 24M tokens every month, any model.
Start Pro- Up to 24M tokens monthly
- Every model: Sonnet, Opus, GPT-5, Gemini, DeepSeek
- Image, audio, video, embeddings — same budget
- Mix and match however you want
- Wallet overflow when the budget runs out
- ~85M tokens on cheap models (MiniMax / DeepSeek / Qwen)
- ~24M tokens on DeepSeek V3
- ~5M tokens on Haiku / GPT-5-mini
- ~1.9M tokens on Sonnet / GPT-5
- ~380K tokens on Opus / GPT-5-pro
Up to 125M tokens every month.
Start Power- Up to 125M tokens monthly
- Same flexibility as Pro, more budget
- All-day Opus or GPT-5 without watching the meter
- Heavy video / audio / image workflows
- Wallet overflow for spike days
- ~430M tokens on cheap models
- ~125M tokens on DeepSeek V3
- ~25M tokens on Haiku / GPT-5-mini
- ~9.5M tokens on Sonnet / GPT-5
- ~1.9M tokens on Opus / GPT-5-pro
Daily limits reset at midnight UTC. Pro & Power overflow into their wallet credit at upstream rates when limits exhaust — no hard stop.
Pay-as-you-go for builders
Mint API keys, point any official SDK at one base URL, top up a prepaid wallet. Flat 7% over what the upstream provider charges. No subscription.
Cents-level negative balance on your final request before lockout — same as OpenAI's prepaid model. Top up to unblock.
Sample model prices
A few entries from our catalog. Live prices live in your dashboard. Prices below are what you pay — upstream cost × 1.07.
| Model | Provider | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
DeepSeek V3 deepseek-v3 | deepseek | 64K | $0.289 | $1.18 |
DeepSeek R1 (reasoning) deepseek-r1 | deepseek | 64K | $0.589 | $2.34 |
Llama 3.3 70B Instruct llama-3.3-70b | groq | 128K | $0.631 | $0.845 |
Qwen3 Coder 480B qwen3-coder-480b | cerebras | 128K | $0.642 | $1.28 |
Claude 3.5 Sonnet (passthrough) claude-3-5-sonnet-20241022 | anthropic | 200K | $3.21 | $16.05 |
What every account gets
- Anthropic
/v1/messages+ OpenAI/v1/chat/completions— point any SDK at one base URL - 12+ providers / 70+ models, growing weekly
- Sequential fallback on 5xx — keeps your agent loop alive
- Real-time wallet balance + per-request usage in your dashboard
- Reasoning streams (DeepSeek-R1, etc.) translated into Anthropic
thinkingblocks - SOC 2-grade tenant isolation — keys, wallets, audit log all per-customer
- End-to-end encrypted, MIT-licensed clients
- All connectors (Linear, Slack, GitHub, Stripe, Resend, …) usable on every plan
Free plan, no credit card required.