Baltor Get started

Endpoints

Standard Compute

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.stdcmpt.com/v1 models.dev, read
Authentication
Authorization: Bearer, with the key in STANDARDCOMPUTE_API_KEY models.dev, read
Structured output
Unknown
Tool calling
40 of 40 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 anthropic/claude-fable-5 with the model you want.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "standardcompute": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Standard Compute",
      "options": {
        "baseURL": "https://api.stdcmpt.com/v1",
        "apiKey": "{env:STANDARDCOMPUTE_API_KEY}"
      },
      "models": {
        "anthropic/claude-fable-5": {
          "name": "anthropic/claude-fable-5"
        }
      }
    }
  }
}
  • 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": {
    "standardcompute": {
      "baseUrl": "https://api.stdcmpt.com/v1",
      "api": "openai-completions",
      "apiKey": "$STANDARDCOMPUTE_API_KEY",
      "models": [
        {
          "id": "anthropic/claude-fable-5"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and Standard Compute 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 Standard Compute 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
Claude Fable 5 anthropic/claude-fable-510.00 USD50.00 USD1,000,000 older than 30 days
Claude Fable 5.1 anthropic/claude-fable-5.110.00 USD50.00 USD1,000,000 older than 30 days
Claude Haiku 5.5 anthropic/claude-haiku-5.50.100 USD0.500 USD1,000,000
Claude Opus 5 anthropic/claude-opus-55.00 USD25.00 USD1,000,000 older than 30 days
Claude Opus 5.5 anthropic/claude-opus-5.54.00 USD20.00 USD1,000,000
Claude Sonnet 5 anthropic/claude-sonnet-52.00 USD10.00 USD1,000,000 older than 30 days
Claude Sonnet 5.5 anthropic/claude-sonnet-5.52.00 USD10.00 USD1,000,000
DeepSeek V4 Flash deepseek/deepseek-v4-flash0.083 USD0.165 USD1,000,000 older than 30 days
DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-07310.440 USD1.32 USD1,000,000 older than 30 days
DeepSeek V4 Pro deepseek/deepseek-v4-pro1.04 USD2.09 USD1,000,000 older than 30 days
DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-08131.12 USD3.37 USD1,000,000 older than 30 days
DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash0.140 USD0.420 USD1,000,000 older than 30 days
Gemini 2.5 Flash google/gemini-2.5-flash0.300 USD2.50 USD1,048,576 older than 30 days
Gemini 2.5 Pro google/gemini-2.5-pro1.25 USD10.00 USD1,048,576 older than 30 days
Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview2.00 USD12.00 USD1,048,576 older than 30 days
Gemini 3.5 Flash Lite google/gemini-3.5-flash-lite0.300 USD2.50 USD1,048,576 older than 30 days
Gemini 3.8 Flash google/gemini-3.8-flash0.750 USD3.75 USD1,048,576 older than 30 days
MiniMax-M3 minimax/minimax-m30.300 USD1.20 USD1,048,576 older than 30 days
Mistral Large 4 mistralai/mistral-large-4-00.680 USD2.09 USD1,048,576
Kimi K3 moonshotai/kimi-k33.00 USD15.00 USD1,048,576 older than 30 days
GPT-5.6 Luna openai/gpt-5.6-luna0.200 USD1.20 USD1,050,000 older than 30 days
GPT-5.6 Sol openai/gpt-5.6-sol4.00 USD20.00 USD1,050,000 older than 30 days
GPT-5.6 Terra openai/gpt-5.6-terra2.00 USD12.00 USD1,050,000 older than 30 days
GPT-6 Astra openai/gpt-6-astra10.00 USD50.00 USD1,050,000 older than 30 days
GPT-6 Luna openai/gpt-6-luna0.100 USD0.500 USD1,050,000
Qwen3.7 Flash qwen/qwen3.7-flash0.030 USD0.130 USD1,000,000 older than 30 days
Qwen3.7 Max qwen/qwen3.7-max1.48 USD4.42 USD1,000,000 older than 30 days
Qwen3.7 Plus qwen/qwen3.7-plus0.320 USD1.28 USD1,000,000 older than 30 days
Qwen3.8 27B qwen/qwen3.8-27b0.425 USD2.55 USD262,144 older than 30 days
Qwen3.8 Flash qwen/qwen3.8-flash0.150 USD0.470 USD1,000,000 older than 30 days
Qwen3.8 Max 0902 qwen/qwen3.8-max-09022.00 USD6.00 USD1,000,000 older than 30 days
Standard Compute standardcomputeUnknownUnknown1,000,000
Grok 4.3 x-ai/grok-4.31.25 USD2.50 USD1,000,000 older than 30 days
MiMo-V2.5 xiaomi/mimo-v2.50.140 USD0.280 USD1,048,576 older than 30 days
MiMo-V2.5-Pro xiaomi/mimo-v2.5-pro0.435 USD0.870 USD1,048,576 older than 30 days
MiMo-V2.6-Flash xiaomi/mimo-v2.6-flash0.140 USD0.280 USD1,048,576
MiMo-V2.6-Pro xiaomi/mimo-v2.6-pro0.430 USD0.870 USD1,048,576
GLM-5.2 z-ai/glm-5.20.562 USD1.80 USD1,000,000 older than 30 days
GLM-5.3 z-ai/glm-5.31.40 USD4.40 USD1,000,000 older than 30 days
GLM-5.3-Flash z-ai/glm-5.3-flash0.080 USD0.500 USD1,000,000 older than 30 days

Sources of this page