Baltor Get started

Endpoints

Together AI

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

Authentication
Authorization: Bearer, with the key in TOGETHER_API_KEY provider documentation, read
Structured output
provider documentation, read
Tool calling
provider documentation, read
Rate limits
Read the page provider documentation, read
Prices
Read the page provider documentation, read
Data retention
Together documents what it stores from inputs and outputs, and offers zero data retention. Read the page provider documentation, read
Documentation
Unknown
Output limits Baltor recorded
Unknown

Harness setup

Replace LiquidAI/LFM2-24B-A2B with the model you want.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "together": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Together AI",
      "options": {
        "baseURL": "https://api.together.ai/v1",
        "apiKey": "{env:TOGETHER_API_KEY}"
      },
      "models": {
        "LiquidAI/LFM2-24B-A2B": {
          "name": "LiquidAI/LFM2-24B-A2B"
        }
      }
    }
  }
}
  • 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": {
    "together": {
      "baseUrl": "https://api.together.ai/v1",
      "api": "openai-completions",
      "apiKey": "$TOGETHER_API_KEY",
      "models": [
        {
          "id": "LiquidAI/LFM2-24B-A2B"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and Together AI 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 Together AI 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
LFM2-24B-A2B LiquidAI/LFM2-24B-A2B0.030 USD0.120 USD32,768 older than 30 days
MiniMax-M2.5 MiniMaxAI/MiniMax-M2.50.300 USD1.20 USD204,800 older than 30 days
MiniMax-M2.7 MiniMaxAI/MiniMax-M2.70.300 USD1.20 USD196,608 older than 30 days
MiniMax-M3 MiniMaxAI/MiniMax-M30.300 USD1.20 USD524,288 older than 30 days
Qwen 2.5 7B Instruct Turbo Qwen/Qwen2.5-7B-Instruct-Turbo0.300 USD0.300 USD32,768 older than 30 days
Qwen3 235B A22B Instruct 2507 FP8 Qwen/Qwen3-235B-A22B-Instruct-2507-tput0.200 USD0.600 USD262,144 older than 30 days
Qwen3 Coder 480B A35B Instruct Qwen/Qwen3-Coder-480B-A35B-Instruct-FP82.00 USD2.00 USD262,144 older than 30 days
Qwen3 Coder Next FP8 Qwen/Qwen3-Coder-Next-FP80.500 USD1.20 USD262,144 older than 30 days
Qwen3.5 397B A17B Qwen/Qwen3.5-397B-A17B0.600 USD3.60 USD262,144 older than 30 days
Qwen3.5 9B Qwen/Qwen3.5-9B0.170 USD0.250 USD262,144 older than 30 days
Qwen3.6 Plus Qwen/Qwen3.6-Plus0.500 USD3.00 USD1,000,000 older than 30 days
Qwen3.7 Max Qwen/Qwen3.7-Max1.25 USD3.75 USD1,000,000 older than 30 days
Cogito v2.1 671B deepcogito/cogito-v2-1-671b1.25 USD1.25 USD163,840 older than 30 days
DeepSeek-R1 deepseek-ai/DeepSeek-R13.00 USD7.00 USD163,839 older than 30 days
DeepSeek-V3 deepseek-ai/DeepSeek-V31.25 USD1.25 USD131,072 older than 30 days
DeepSeek V3.1 deepseek-ai/DeepSeek-V3-10.600 USD1.70 USD131,072 older than 30 days
DeepSeek V4 Flash 0731 deepseek-ai/DeepSeek-V4-Flash-07310.140 USD0.280 USD1,048,576 older than 30 days
DeepSeek V4 Pro deepseek-ai/DeepSeek-V4-Pro1.74 USD3.48 USD512,000 older than 30 days
DeepSeek V4 Pro 0813 deepseek-ai/DeepSeek-V4-Pro-08131.32 USD3.96 USD1,048,576 older than 30 days
DeepSeek V4.1 Flash deepseek-ai/DeepSeek-V4.1-Flash0.300 USD1.20 USD1,048,576
Rnj-1 Instruct essentialai/Rnj-1-Instruct0.150 USD0.150 USD32,768 older than 30 days
Gemma 3N E4B Instruct google/gemma-3n-E4B-it0.060 USD0.120 USD32,768 older than 30 days
Gemma 4 31B Instruct google/gemma-4-31B-it0.390 USD0.970 USD262,144 older than 30 days
Llama 3.3 70B meta-llama/Llama-3.3-70B-Instruct-Turbo1.04 USD1.04 USD131,072 older than 30 days
Meta Llama 3 8B Instruct Lite meta-llama/Meta-Llama-3-8B-Instruct-Lite0.140 USD0.140 USD8,192 older than 30 days
Kimi K2.5 moonshotai/Kimi-K2.50.500 USD2.80 USD262,144 older than 30 days
Kimi K2.6 moonshotai/Kimi-K2.61.20 USD4.50 USD262,144 older than 30 days
Kimi K2.7 Code moonshotai/Kimi-K2.7-Code0.950 USD4.00 USD262,144 older than 30 days
Kimi K3 moonshotai/Kimi-K33.00 USD15.00 USD1,048,576 older than 30 days
Nemotron 3 Ultra 550B A55B nvidia/nemotron-3-ultra-550b-a55b0.600 USD3.60 USD512,300 older than 30 days
GPT OSS 120B openai/gpt-oss-120b0.150 USD0.600 USD131,072 older than 30 days
GPT OSS 20B openai/gpt-oss-20b0.050 USD0.200 USD131,072 older than 30 days
Pearl AI Gemma 4 31B Instruct pearl-ai/gemma-4-31b-it0.280 USD0.860 USD32,000 older than 30 days
Inkling thinkingmachines/Inkling1.00 USD4.05 USD524,288 older than 30 days
GLM-5 zai-org/GLM-51.00 USD3.20 USD202,752 older than 30 days
GLM-5.1 zai-org/GLM-5.11.40 USD4.40 USD202,752 older than 30 days
GLM-5.2 zai-org/GLM-5.21.40 USD4.40 USD1,048,575 older than 30 days
GLM-5.3 zai-org/GLM-5.31.40 USD4.40 USD1,048,576 older than 30 days
GLM-5.3-Flash zai-org/GLM-5.3-Flash0.150 USD0.500 USD1,048,575