AI API for Brazilian developers, paid in reais by Pix
Works in Cursor and Cline. One key opens several model routes, with personal data handled before inference.
Learn how it worksPlatform usage
Last 30 days- Requests
- 5.3k
- Tokens
- 5.2M
- Providers in use
- 4
- Active routes
- 19
- Median response time
- 3.1 sec
Requests by provider
DeepSeek4,28980.6%
Google Gemini4929.2%
Anthropic2775.2%
OpenAI2244.2%- Others370.7%
Requests by route
- Rota Analysis4,21979.1%
- Rota Fast290.5%
- Rota Long Context200.4%
- Rota Agents40.1%
- Others1,06419.9%
Models and prices
Prices per million tokensOpenAI4
| Model | Input | Output | Context |
|---|---|---|---|
GPT-6 Lunarota/gpt-6-luna | R$0.72 | R$3.58 | 272k |
GPT-6.1 Terrarota/gpt-6-1-terra | R$7.15 | R$35.75 | 272k |
GPT-6.1 Solrota/gpt-6-1-sol | R$14.30 | R$71.50 | 272k |
GPT-6 Astrarota/gpt-6-astra | R$71.50 | R$357.50 | 272k |
Anthropic4
| Model | Input | Output | Context |
|---|---|---|---|
Claude Haiku 5.5rota/claude-haiku-5-5 | R$0.72 | R$3.58 | 100k |
Claude Sonnet 5.5rota/claude-sonnet-5-5 | R$14.30 | R$71.50 | 1M |
Claude Opus 5.5rota/claude-opus-5-5 | R$28.60 | R$143.00 | 1M |
Claude Fable 5.1rota/claude-fable-5-1 | R$71.50 | R$357.50 | 1M |
Google Gemini3
| Model | Input | Output | Context |
|---|---|---|---|
Gemini 3.5 Flash-Literota/gemini-3-5-flash-lite | R$2.15 | R$17.88 | 1M |
Gemini 3.8 Flashrota/gemini-3-8-flash | R$10.73 | R$53.63 | 1M |
Gemini 4 Argonrota/gemini-4-argon | R$28.60 | R$143.00 | 1M |
Routes by task8
| Model | Input | Output | Context |
|---|---|---|---|
Rota Summaryrota/resumo | R$2.15 | R$8.58 | 64k |
| A cost-effective model for summaries, classification, triage and focused tasks at scale. | |||
Rota Analysisrota/analise | R$2.15 | R$8.58 | 128k |
| A capable model for careful analysis, technical reviews and decisions with broad context. | |||
Rota Coderota/codigo | R$2.15 | R$8.58 | 131k |
| A model curated for technical assistance, automation, system reviews and large codebases. | |||
Rota Agentsrota/agentes | R$2.15 | R$8.58 | 131k |
| A model for assisted automation, tool use, planning and guided execution. | |||
| Model | Input | Output | Context |
|---|---|---|---|
Rota Fastrota/rapido | R$2.15 | R$8.58 | 64k |
| A fast model for chat, classification and low-latency tasks. | |||
Rota Reasoningrota/raciocinio | R$2.15 | R$8.58 | 128k |
| A model for step-by-step analysis, technical reviews and decisions with broad context. | |||
Rota Instructionrota/instrucao | R$2.15 | R$8.58 | 66k |
| A balanced model for assistants, customer support and focused answers. | |||
Rota Long Contextrota/contexto-longo | R$2.15 | R$8.58 | 200k |
| A model for long documents, contract analysis and synthesizing large datasets. | |||
Free test and credits
R$0.00
Free test
- 100k tokens on Rota Fast for 7 days, once per person
- Up to $1.00 a day on each provider, subject to the shared daily allowance
- No card: verified email or Google, with human verification on first use
Pix, from R$10.00. Agents without an account pay each call by x402, with USDC on Base, from $0.001. See API prices
Inference optimization
We choose the model and setup that meet your latency and cost target, on your own GPU or a rented one. We show the savings against a closed API.