Baltor Get started

Endpoints

Synthetic

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.synthetic.new/openai/v1 models.dev, read
Authentication
Authorization: Bearer, with the key in SYNTHETIC_API_KEY models.dev, read
Structured output
Unknown
Tool calling
10 of 10 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 hf:MiniMaxAI/MiniMax-M3 with the model you want.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "synthetic": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Synthetic",
      "options": {
        "baseURL": "https://api.synthetic.new/openai/v1",
        "apiKey": "{env:SYNTHETIC_API_KEY}"
      },
      "models": {
        "hf:MiniMaxAI/MiniMax-M3": {
          "name": "hf:MiniMaxAI/MiniMax-M3"
        }
      }
    }
  }
}
  • 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": {
    "synthetic": {
      "baseUrl": "https://api.synthetic.new/openai/v1",
      "api": "openai-completions",
      "apiKey": "$SYNTHETIC_API_KEY",
      "models": [
        {
          "id": "hf:MiniMaxAI/MiniMax-M3"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and Synthetic 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 Synthetic 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
MiniMax-M3 hf:MiniMaxAI/MiniMax-M30.600 USD1.20 USD524,288 older than 30 days
Qwen3.6 27B hf:Qwen/Qwen3.6-27B0.450 USD3.60 USD262,144 older than 30 days
DeepSeek V4.1 Flash hf:deepseek-ai/DeepSeek-V4.1-Flash0.600 USD1.20 USD524,288
Kimi K2.7 Code hf:moonshotai/Kimi-K2.7-Code0.950 USD4.00 USD262,144 older than 30 days
Kimi K3 hf:moonshotai/Kimi-K33.00 USD15.00 USD524,288 older than 30 days
Nemotron 3 Super 120B A12B hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP40.300 USD1.00 USD262,144 older than 30 days
GPT OSS 120B hf:openai/gpt-oss-120b0.100 USD0.100 USD131,072 older than 30 days
GLM-4.7-Flash hf:zai-org/GLM-4.7-Flash0.100 USD0.500 USD196,608 older than 30 days
GLM-5.2 hf:zai-org/GLM-5.21.40 USD4.40 USD524,288 older than 30 days
GLM-5.3-Flash hf:zai-org/GLM-5.3-Flash0.150 USD0.500 USD524,288

Sources of this page