Catalog / Rota Reasoning
Rota Reasoning
A model for step-by-step analysis, technical reviews and decisions with broad context.
Specifications
- API ID
rota/raciocinio- Context window
- 128k tokens
- Suggested use
- reasoning, code, PT-BR
- Compatibility
- Chat completions, SSE streaming, tool calling
- Cost
- Included in the account's initial free quota
Example
Call Rota Reasoning now.
curl
curl https://rota-nacional.ia.br/v1/chat/completions \
-H "Authorization: Bearer $ROTA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "rota/raciocinio",
"messages": [
{ "role": "user", "content": "Olá, Rota Nacional" }
],
"stream": true
}'OpenAI SDK
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.ROTA_API_KEY,
baseURL: "https://rota-nacional.ia.br/v1"
});
const resposta = await client.chat.completions.create({
model: "rota/raciocinio",
messages: [{ role: "user", content: "ping" }]
});Keep exploring
Other models and integration.
Rota Summary
rota/resumo
A cost-effective model for summaries, classification, triage and focused tasks at scale.
64k tokens
Rota Analysis
rota/analise
A capable model for careful analysis, technical reviews and decisions with broad context.
128k tokens
Rota Code
rota/codigo
A model curated for technical assistance, automation, system reviews and large codebases.
131k tokens
Rota Agents
rota/agentes
A model for assisted automation, tool use, planning and guided execution.
131k tokens
Rota Fast
rota/rapido
A fast model for chat, classification and low-latency tasks.
64k tokens
Rota Instruction
rota/instrucao
A balanced model for assistants, customer support and focused answers.
66k tokens
Rota Long Context
rota/contexto-longo
A model for long documents, contract analysis and synthesizing large datasets.
200k tokens
Rota Local
rota/local
Chat executed by Rota Nacional's private fleet, without the client selecting a machine.
33k tokens
Rota Auto
rota/auto
Automatically selects the most suitable Rota Nacional model using deterministic rules based on content length, keywords and tool use. The effective context window depends on the selected model (up to 200,000 tokens).
200k tokens