Baltor Get started

Endpoints

Regolo AI

A hosted service with its own key and prices. This page lists the addresses it answers, the facts its documentation states, and the setup of each harness.

Addresses and facts

  • OpenAI Chat Completions: https://api.regolo.ai/v1 models.dev, read
Authentication
Authorization: Bearer, with the key in REGOLO_API_KEY models.dev, read
Structured output
Unknown
Tool calling
13 of 18 listed models The share of this provider's models that models.dev records with tool calling. models.dev, read
Rate limits
Unknown
Prices
Unknown
Data retention
Unknown
Documentation
Read the page models.dev, read
Output limits Baltor recorded
Unknown

Harness setup

Replace apertus-70b with the model you want.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "regolo-ai": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Regolo AI",
      "options": {
        "baseURL": "https://api.regolo.ai/v1",
        "apiKey": "{env:REGOLO_API_KEY}"
      },
      "models": {
        "apertus-70b": {
          "name": "apertus-70b"
        }
      }
    }
  }
}
  • OpenCode reads any OpenAI-compatible address through the @ai-sdk/openai-compatible package, and an address that speaks the Responses API through @ai-sdk/openai.

From OpenCode documentation, read .

Pi

Put this in ~/.pi/agent/models.json:

{
  "providers": {
    "regolo-ai": {
      "baseUrl": "https://api.regolo.ai/v1",
      "api": "openai-completions",
      "apiKey": "$REGOLO_API_KEY",
      "models": [
        {
          "id": "apertus-70b"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and Regolo AI documents no Responses address. A gateway that offers one can sit in between.

  • Codex speaks the Responses API only: responses is the one supported wire API of a custom provider. Ollama and LM Studio are built in and start with --oss.

From Codex documentation, read .

Claude Code

Claude Code sends Anthropic Messages requests, and Regolo AI documents no such address. A gateway that translates to that API can sit in between.

  • Claude Code sends Anthropic Messages requests to ANTHROPIC_BASE_URL. Anthropic says it does not support routing Claude Code to models other than Claude through any gateway, so some features may not work with another model.

From Claude Code documentation, read .

Models it lists

Prices in US dollars per million tokens, input and output, as models.dev, read records them.

ModelInputOutputContextAs of
Apertus 70B apertus-70b0.460 USD2.42 USD30,000 older than 30 days
Brick Complexity Pro brick-complexity-pro0.120 USD0.460 USD100,000 older than 30 days
Brick v1 Beta brick-v1-beta0 USD0 USD100,000 older than 30 days
DeepSeek OCR 2 deepseek-ocr-20 USD0 USD4,000 older than 30 days
Faster Whisper Large v3 faster-whisper-large-v30 USD0 USD448 older than 30 days
Gemma 4 31B IT gemma4-31b0.460 USD2.42 USD100,000 older than 30 days
GLM-5.2 glm5.22.31 USD6.00 USD96,000 older than 30 days
GPT-OSS-120B gpt-oss-120b1.00 USD4.20 USD128,000 older than 30 days
GPT-OSS-20B gpt-oss-20b0.400 USD1.80 USD128,000 older than 30 days
Llama 3.3 70B Instruct llama-3.3-70b-instruct0.600 USD2.70 USD128,000 older than 30 days
Mistral Small 4 119B mistral-small-4-119b0.750 USD3.00 USD256,000 older than 30 days
Qwen-Image qwen-image0.500 USD2.00 USD8,192 older than 30 days
Qwen3-Coder-Next qwen3-coder-next0.300 USD1.20 USD262,144 older than 30 days
Qwen3-Embedding-8B qwen3-embedding-8b0.100 USD0.100 USD32,768 older than 30 days
Qwen3-Reranker-4B qwen3-reranker-4b0.120 USD0.120 USD32,768 older than 30 days
Qwen3.5-122B qwen3.5-122b0.900 USD3.60 USD262,144 older than 30 days
Qwen3.5-9B qwen3.5-9b0.150 USD0.600 USD262,144 older than 30 days
Qwen3.8 27B qwen3.8-27b0.580 USD2.42 USD120,000 older than 30 days

Sources of this page