Baltor Get started

Endpoints

evroc

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://models.think.evroc.com/v1 models.dev, read
Authentication
Authorization: Bearer, with the key in EVROC_API_KEY models.dev, read
Structured output
Unknown
Tool calling
9 of 16 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 KBLab/kb-whisper-large with the model you want.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "evroc": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "evroc",
      "options": {
        "baseURL": "https://models.think.evroc.com/v1",
        "apiKey": "{env:EVROC_API_KEY}"
      },
      "models": {
        "KBLab/kb-whisper-large": {
          "name": "KBLab/kb-whisper-large"
        }
      }
    }
  }
}
  • 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": {
    "evroc": {
      "baseUrl": "https://models.think.evroc.com/v1",
      "api": "openai-completions",
      "apiKey": "$EVROC_API_KEY",
      "models": [
        {
          "id": "KBLab/kb-whisper-large"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and evroc 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 evroc 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
KB Whisper KBLab/kb-whisper-large0.0023 USD0.0023 USD448 older than 30 days
Qwen3 Embedding 8B Qwen/Qwen3-Embedding-8B0.115 USD0.115 USD40,960 older than 30 days
Qwen3 Reranker 4B Qwen/Qwen3-Reranker-4B0.058 USD0 USD32,000 older than 30 days
Qwen3.6 35B-A3B Qwen/Qwen3.6-35B-A3B0.345 USD1.38 USD262,144 older than 30 days
Qwen3.8-27B Qwen/Qwen3.8-27B0.870 USD3.50 USD262,144 older than 30 days
roc evroc/roc2.88 USD11.52 USD262,144 older than 30 days
Gemma 4 26B A4B IT google/gemma-4-26B-A4B-it0.144 USD0.575 USD262,144 older than 30 days
E5 Multi-Lingual Large Embeddings 0.6B intfloat/multilingual-e5-large-instruct0.114 USD0.114 USD512 older than 30 days
Mistral Medium 3.5 mistralai/Mistral-Medium-3.5-128B1.73 USD6.90 USD262,144 older than 30 days
Voxtral Small 24B mistralai/Voxtral-Small-24B-25070.0023 USD0.0023 USD32,000 older than 30 days
Kimi K2.6 moonshotai/Kimi-K2.61.44 USD5.75 USD262,144 older than 30 days
Llama-3.3-70B-Instruct nvidia/Llama-3.3-70B-Instruct-FP81.15 USD1.15 USD128,000 older than 30 days
GPT OSS 120B openai/gpt-oss-120b0.230 USD0.920 USD65,536 older than 30 days
Whisper 3 Large openai/whisper-large-v30.0023 USD0.0023 USD448 older than 30 days
Whisper Large v3 Turbo openai/whisper-large-v3-turbo0.0023 USD0.0023 USD448 older than 30 days
GLM-5.2 zai-org/GLM-5.21.44 USD5.75 USD524,288 older than 30 days

Sources of this page