Baltor Get started

Endpoints

LLMTR

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://llmtr.com/v1 models.dev, read
Authentication
Authorization: Bearer, with the key in LLMTR_API_KEY models.dev, read
Structured output
Unknown
Tool calling
27 of 32 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 gemma-4 with the model you want.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "llmtr": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "LLMTR",
      "options": {
        "baseURL": "https://llmtr.com/v1",
        "apiKey": "{env:LLMTR_API_KEY}"
      },
      "models": {
        "gemma-4": {
          "name": "gemma-4"
        }
      }
    }
  }
}
  • 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": {
    "llmtr": {
      "baseUrl": "https://llmtr.com/v1",
      "api": "openai-completions",
      "apiKey": "$LLMTR_API_KEY",
      "models": [
        {
          "id": "gemma-4"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and LLMTR 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 LLMTR 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
Gemma 4 gemma-42.00 USD5.00 USD131,072 older than 30 days
Gemini 2.5 Flash-Lite google/gemini-2.5-flash-lite0.100 USD0.100 USD1,048,576 older than 30 days
Magibu 11B v8 magibu-11b-v80.100 USD0.500 USD8,192 older than 30 days
MedGemma 4B medgemma-4b3.00 USD5.00 USD8,192 older than 30 days
Muse Spark 1.2 Contributor meta/muse-spark-1.2-contributor0.100 USD0.200 USD1,048,576 older than 30 days
MiMo-V2.5 mimo/mimo-v2.50.140 USD0.280 USD1,000,000 older than 30 days
MiMo-V2.5-Pro mimo/mimo-v2.5-pro0.435 USD0.870 USD1,000,000 older than 30 days
Voxtral Small (latest) mistral/voxtral-small-latest0.100 USD0.300 USD32,000 older than 30 days
Muse Glimmer 30B (TR) muse-glimmer-30b-tr2.00 USD5.00 USD131,072 older than 30 days
Sonar Deep Research perplexity/sonar-deep-research2.00 USD8.00 USD128,000 older than 30 days
Laguna XS 2.1 poolside/laguna-xs-2.10 USD0 USD262,144 older than 30 days
Apertus 70B Instruct publicai/apertus-70b-instruct0.820 USD2.92 USD65,536 older than 30 days
Apertus 8B Instruct publicai/apertus-8b-instruct0.100 USD0.200 USD65,536 older than 30 days
Qwen Flash qwen/qwen-flash0.050 USD0.400 USD1,000,000 older than 30 days
Qwen Plus qwen/qwen-plus0.400 USD1.20 USD1,000,000 older than 30 days
Qwen3 Coder Flash qwen/qwen3-coder-flash0.300 USD1.50 USD1,000,000 older than 30 days
Qwen3 Coder Plus qwen/qwen3-coder-plus1.00 USD5.00 USD1,000,000 older than 30 days
Qwen3 Max qwen/qwen3-max1.20 USD6.00 USD256,000 older than 30 days
Qwen3-VL Plus qwen/qwen3-vl-plus0.200 USD1.60 USD256,000 older than 30 days
Qwen3.5 397B-A17B qwen/qwen3.5-397b-a17b0.600 USD3.60 USD256,000 older than 30 days
Qwen3.5 Plus qwen/qwen3.5-plus0.400 USD2.40 USD1,000,000 older than 30 days
Qwen3.6 Flash qwen/qwen3.6-flash0.250 USD1.50 USD1,000,000 older than 30 days
Qwen3.6 Plus qwen/qwen3.6-plus0.500 USD3.00 USD1,000,000 older than 30 days
Qwen3.7 Plus qwen/qwen3.7-plus0.400 USD1.60 USD1,000,000 older than 30 days
Qwen3.6 35B-A3B qwen3-6-35b5.00 USD10.00 USD16,384 older than 30 days
Fugu Ultra sakana/fugu-ultra5.00 USD30.00 USD1,000,000 older than 30 days
Inkling thinkingmachines/inkling1.87 USD4.68 USD262,144 older than 30 days
Inkling Small thinkingmachines/inkling-small0.580 USD1.44 USD262,144 older than 30 days
Trendyol Asure 12B trendyol-asure-12b0.100 USD0.500 USD40,960 older than 30 days
Solar Pro 2 upstage/solar-pro20.150 USD0.600 USD65,536 older than 30 days
Solar Pro 3 upstage/solar-pro30.150 USD0.600 USD131,072
Solar Pro 4 upstage/solar-pro40.030 USD0.120 USD524,288 older than 30 days

Sources of this page