Which API should you use with Reasonix?

For Reasonix (DeepSeek-Reasonix), the best API for mixed work is a cost-optimized custom provider: in Reasonix Studio, Settings → Model → Access → Add model service → Custom provider, choose OpenAI-compatible, enter https://api.stdcmpt.com/v1 and the model standardcompute, and Standard Compute's router sends each step to the cheapest model that can do it (Claude Fable 5.1 or GPT-6 Astra only when it counts), on a plan from $19 a month with a $20 compute budget. Reasonix's default is DeepSeek's API billed per token, and its presets cover coding plans such as OpenCode Go, GLM and Kimi. Reasonix itself is free and MIT-licensed.

Light or occasional use

If DeepSeek models handle your tasks, Reasonix's default DeepSeek key billed per token will likely cost the least. A coding plan preset such as OpenCode Go suits steady use of one model family.

Daily use, cost-optimized

When Reasonix runs long planner and subagent sessions and some steps need Claude or GPT, a Standard Compute provider sends each step to the cheapest model that can do it, and for every model we vet providers for price, uptime and speed, with automatic fallback. Opt-in Europe or US Compliance rules apply per key, team or company, and we don't train on your prompts or store them. The bill stays at the monthly plan price: requests stop with HTTP 402 when the compute budget is used, with nothing billed on top.

API and subscription options for Reasonix

Prices and allowances can change. Reasonix's provider fields, custom provider flow and config paths come from its guide and configuration-paths docs, read on October 15, 2026. Reasonix: guide (custom providers) · Reasonix: configuration paths · Reasonix repo. Spot an error? Tell us.

Add Standard Compute as a Reasonix provider

default_model = "standardcompute"

[[providers]]
name        = "standardcompute"
kind        = "openai"
base_url    = "https://api.stdcmpt.com/v1"
model       = "standardcompute"
api_key_env = "STANDARDCOMPUTE_API_KEY"

# ~/.reasonix/.env
# STANDARDCOMPUTE_API_KEY=sc_live_…

Reasonix Studio writes the same entry from Settings → Model → Access → Add model service → Custom provider: protocol OpenAI-compatible, API address https://api.stdcmpt.com/v1 with Full URL off. Switch models with /model.

Reasonix questions

Why does Reasonix ignore the API key I exported in my shell?

Reasonix reads provider keys only from its global .env in Reasonix home (~/.reasonix/.env on macOS and Linux), shared by the CLI and Reasonix Studio. Shell variables, a project .env and the OS keyring are not runtime sources for provider keys. Put STANDARDCOMPUTE_API_KEY=… in ~/.reasonix/.env, or save the key in Studio, which writes it there.

What is Full URL in a Reasonix custom provider?

With Full URL off, Reasonix appends /chat/completions to the API address, so https://api.stdcmpt.com/v1 sends requests to https://api.stdcmpt.com/v1/chat/completions. Turn Full URL on only when a service gives you a complete request URL. It does not switch to the Responses API; Reasonix's custom providers speak OpenAI-compatible Chat Completions or Anthropic-compatible Messages.