Baltor Get started

Endpoints

IteraCompute

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.iteracompute.com/v1 models.dev, read
Authentication
Authorization: Bearer, with the key in ITERACOMPUTE_API_KEY models.dev, read
Structured output
Unknown
Tool calling
9 of 9 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 deepseek/deepseek-v4-flash-0731 with the model you want.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "iteracompute": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "IteraCompute",
      "options": {
        "baseURL": "https://api.iteracompute.com/v1",
        "apiKey": "{env:ITERACOMPUTE_API_KEY}"
      },
      "models": {
        "deepseek/deepseek-v4-flash-0731": {
          "name": "deepseek/deepseek-v4-flash-0731"
        }
      }
    }
  }
}
  • 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": {
    "iteracompute": {
      "baseUrl": "https://api.iteracompute.com/v1",
      "api": "openai-completions",
      "apiKey": "$ITERACOMPUTE_API_KEY",
      "models": [
        {
          "id": "deepseek/deepseek-v4-flash-0731"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and IteraCompute 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 IteraCompute 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
DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-07310.340 USD1.05 USD970,000 older than 30 days
DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-08131.10 USD3.30 USD1,048,576 older than 30 days
MiniMax-M3 minimax/minimax-m30.290 USD1.20 USD1,048,576 older than 30 days
Kimi K3 moonshotai/kimi-k33.00 USD14.90 USD1,048,576 older than 30 days
Ornith 1.5 35B A3B ornith-ai/ornith-1.5-35b-a3b0.300 USD3.00 USD327,680 older than 30 days
Qwen3.8 2.4T A95B qwen/qwen3.8-2.4t-a95b1.95 USD5.95 USD970,000 older than 30 days
Qwen3.8 27B qwen/qwen3.8-27b0.300 USD2.50 USD327,680 older than 30 days
GLM-5.3 z-ai/glm-5.31.20 USD3.50 USD1,048,576 older than 30 days
GLM-5.3-Flash z-ai/glm-5.3-flash0.140 USD0.490 USD1,048,576

Sources of this page