Unlimited tokens.
Literally.
TerminalCursorQualquer client OpenAI
Terminal, Cursor, any OpenAI client. Same API key. No fine print.
8+Modelos
10.9BTokens/mês
100%Uptime
// curated models
The best open source models for coding.
—
modelcoding score
mimo-v2.5TOP
42
1M~78Xiaomiminimax-m2.7
42
197k~68MiniMax@preset/glm4-7-flash
—
202koss@preset/qwen-3-6-35b
—
262kossstepfun-ai/step-3.7-flash
—
262kossdeepseek-v4-flash
—
1Moss@preset/qwen3-6-27b
—
262kossz-ai/glm-5.1
—
131kossUnlimited tokens
Subscribe and use the CLI with unlimited tokens — like Claude Pro, but no rate limit and zero data going to any external API. 3 days free, no credit card.
JuniorGet started
R$ 60
/moUnlimited tokens
✓API access (OpenAI-compatible)↻30 req/min
@preset/glm4-7-flash, @preset/qwen-3-6-35b,
No free trial
ProGet started
R$ 120
/moUnlimited tokens
✓API access (OpenAI-compatible)↻30 req/min
deepseek-v4-flash, mimo-v2.5,
1 day free
Em breve
EnterpriseDedicated instance
100% dedicated GPU clusterCustom throughput · no rate limitsmTLS + customer-managed keysPrivacy guaranteed in contract
Talk to salesOpenAI-compat · configurable rate limit
API access
Unlimited tokens via OpenAI-compatible HTTP endpoint. Plug into your chat, agent, IDE, pipeline — whatever you want. RPM/TPM rate limit agreed by contract.
GrowthR$ 600/mês
@preset/qwen3-6-27b
100 req/min
✓OpenAI-compatible endpoint
✓Unlimited tokens in contract
✓Configurable RPM/TPM rate limit
✓BYO tooling · chat, agents, IDE
✓Per-request logs and audit
✓Optional mTLS · zero training
$ verboo --help
Frequently asked questions.
You subscribe to a plan, install the CLI with one command, and start. Unlimited tokens from the very first request — no queue, no quota, no rate limit. The 3-day trial is free, no credit card.
3 days free. No credit card. No catch.
Truly unlimited tokens, open source model running on our GPU. Install, test, then decide.