Baltor Get started

Endpoints

Scaleway

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.scaleway.ai/v1 models.dev, read
Authentication
Authorization: Bearer, with the key in SCALEWAY_API_KEY models.dev, read
Structured output
Unknown
Tool calling
12 of 15 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 bge-multilingual-gemma2 with the model you want.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "scaleway": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Scaleway",
      "options": {
        "baseURL": "https://api.scaleway.ai/v1",
        "apiKey": "{env:SCALEWAY_API_KEY}"
      },
      "models": {
        "bge-multilingual-gemma2": {
          "name": "bge-multilingual-gemma2"
        }
      }
    }
  }
}
  • 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": {
    "scaleway": {
      "baseUrl": "https://api.scaleway.ai/v1",
      "api": "openai-completions",
      "apiKey": "$SCALEWAY_API_KEY",
      "models": [
        {
          "id": "bge-multilingual-gemma2"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and Scaleway 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 Scaleway 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
BGE Multilingual Gemma2 bge-multilingual-gemma20.100 USD0 USD8,191 older than 30 days
DeepSeek V4 Flash 0731 deepseek-v4-flash-07310.468 USD0.936 USD256,000 older than 30 days
Gemma 4 26B A4B IT gemma-4-26b-a4b-it0.250 USD0.500 USD256,000 older than 30 days
GLM-5.2 glm-5.21.80 USD5.50 USD256,000 older than 30 days
GPT-OSS 120B gpt-oss-120b0.150 USD0.600 USD128,000 older than 30 days
Llama-3.3-70B-Instruct llama-3.3-70b-instruct0.900 USD0.900 USD100,000 older than 30 days
Mistral Medium 3.5 128B mistral-medium-3.5-128b1.50 USD7.50 USD256,000 older than 30 days
Mistral Small 3.2 24B Instruct (2506) mistral-small-3.2-24b-instruct-25060.150 USD0.350 USD128,000 older than 30 days
Pixtral 12B 2409 pixtral-12b-24090.200 USD0.200 USD128,000 older than 30 days
Qwen3 235B A22B Instruct 2507 qwen3-235b-a22b-instruct-25070.750 USD2.25 USD260,000 older than 30 days
Qwen3-Coder 30B-A3B Instruct qwen3-coder-30b-a3b-instruct0.200 USD0.800 USD128,000 older than 30 days
Qwen3 Embedding 8B qwen3-embedding-8b0.100 USD0 USD32,768 older than 30 days
Qwen3.5 397B A17B qwen3.5-397b-a17b0.600 USD3.60 USD256,000 older than 30 days
Qwen3.6 35B A3B qwen3.6-35b-a3b0.250 USD1.50 USD128,000 older than 30 days
Whisper Large v3 whisper-large-v30.0030 USD0 USDUnknown older than 30 days

Sources of this page