Baltor Get started

Endpoints

Alibaba (China)

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://dashscope.aliyuncs.com/compatible-mode/v1 models.dev, read
Authentication
Authorization: Bearer, with the key in DASHSCOPE_API_KEY models.dev, read
Structured output
Unknown
Tool calling
85 of 90 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 MiniMax-M2.5 with the model you want.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "alibaba-cn": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Alibaba (China)",
      "options": {
        "baseURL": "https://dashscope.aliyuncs.com/compatible-mode/v1",
        "apiKey": "{env:DASHSCOPE_API_KEY}"
      },
      "models": {
        "MiniMax-M2.5": {
          "name": "MiniMax-M2.5"
        }
      }
    }
  }
}
  • 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": {
    "alibaba-cn": {
      "baseUrl": "https://dashscope.aliyuncs.com/compatible-mode/v1",
      "api": "openai-completions",
      "apiKey": "$DASHSCOPE_API_KEY",
      "models": [
        {
          "id": "MiniMax-M2.5"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and Alibaba (China) 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 Alibaba (China) 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-M2.5 MiniMax-M2.50.300 USD1.20 USD204,800 older than 30 days
MiniMax-M2.7 MiniMax/MiniMax-M2.70.300 USD1.20 USD204,800 older than 30 days
DeepSeek R1 deepseek-r10.574 USD2.29 USD131,072 older than 30 days
DeepSeek R1 0528 deepseek-r1-05280.574 USD2.29 USD131,072 older than 30 days
DeepSeek R1 Distill Llama 70B deepseek-r1-distill-llama-70b0.287 USD0.861 USD32,768 older than 30 days
DeepSeek R1 Distill Llama 8B deepseek-r1-distill-llama-8b0 USD0 USD32,768 older than 30 days
DeepSeek R1 Distill Qwen 1.5B deepseek-r1-distill-qwen-1-5b0 USD0 USD32,768 older than 30 days
DeepSeek R1 Distill Qwen 14B deepseek-r1-distill-qwen-14b0.144 USD0.431 USD32,768 older than 30 days
DeepSeek R1 Distill Qwen 32B deepseek-r1-distill-qwen-32b0.287 USD0.861 USD32,768 older than 30 days
DeepSeek R1 Distill Qwen 7B deepseek-r1-distill-qwen-7b0.072 USD0.144 USD32,768 older than 30 days
DeepSeek V3 deepseek-v30.287 USD1.15 USD65,536 older than 30 days
DeepSeek V3.1 deepseek-v3-10.574 USD1.72 USD131,072 older than 30 days
DeepSeek V3.2 Exp deepseek-v3-2-exp0.287 USD0.431 USD131,072 older than 30 days
DeepSeek V4 Flash deepseek-v4-flash0.140 USD0.280 USD1,000,000 older than 30 days
DeepSeek V4 Pro deepseek-v4-pro0.435 USD0.870 USD1,000,000 older than 30 days
DeepSeek V4.1 Flash deepseek-v4.1-flash0.298 USD1.19 USD1,000,000
GLM-5 glm-50.573 USD2.58 USD202,752 older than 30 days
GLM-5.1 glm-5.10.825 USD3.30 USD202,752 older than 30 days
GLM-5.2 glm-5.21.10 USD3.85 USD1,000,000 older than 30 days
GLM-5.3 glm-5.31.10 USD3.85 USD1,000,000 older than 30 days
Moonshot Kimi K2 Thinking kimi-k2-thinking0.574 USD2.29 USD262,144 older than 30 days
Moonshot Kimi K2.5 kimi-k2.50.574 USD2.41 USD262,144 older than 30 days
Moonshot Kimi K2.6 kimi-k2.60.929 USD3.86 USD262,144 older than 30 days
Kimi K3 kimi-k32.83 USD14.13 USD1,048,576 older than 30 days
kimi/kimi-k2.5 kimi/kimi-k2.50.600 USD3.00 USD262,144 older than 30 days
Moonshot Kimi K2 Instruct moonshot-kimi-k2-instruct0.574 USD2.29 USD131,072 older than 30 days
QVQ Max qvq-max1.15 USD4.59 USD131,072 older than 30 days
Qwen Deep Research qwen-deep-research7.74 USD23.37 USD1,000,000
Qwen Doc Turbo qwen-doc-turbo0.087 USD0.144 USD131,072
Qwen Flash qwen-flash0.022 USD0.216 USD1,000,000 older than 30 days
Qwen Long qwen-long0.072 USD0.287 USD10,000,000 older than 30 days
Qwen Math Plus qwen-math-plus0.574 USD1.72 USD4,096 older than 30 days
Qwen Math Turbo qwen-math-turbo0.287 USD0.861 USD4,096 older than 30 days
Qwen Max qwen-max0.345 USD1.38 USD131,072 older than 30 days
Qwen-MT Plus qwen-mt-plus0.259 USD0.775 USD16,384
Qwen-MT Turbo qwen-mt-turbo0.101 USD0.280 USD16,384
Qwen-Omni Turbo qwen-omni-turbo0.058 USD0.230 USD32,768 older than 30 days
Qwen-Omni Turbo Realtime qwen-omni-turbo-realtime0.230 USD0.918 USD32,768 older than 30 days
Qwen Plus qwen-plus0.115 USD0.287 USD1,000,000 older than 30 days
Qwen Plus Character qwen-plus-character0.115 USD0.287 USD32,768
Qwen Turbo qwen-turbo0.044 USD0.087 USD1,000,000 older than 30 days
Qwen-VL Max qwen-vl-max0.230 USD0.574 USD131,072 older than 30 days
Qwen-VL OCR qwen-vl-ocr0.043 USD0.072 USD34,096
Qwen-VL Plus qwen-vl-plus0.115 USD0.287 USD131,072 older than 30 days
Qwen2.5 14B Instruct qwen2-5-14b-instruct0.144 USD0.431 USD131,072
Qwen2.5 32B Instruct qwen2-5-32b-instruct0.287 USD0.861 USD131,072
Qwen2.5 72B Instruct qwen2-5-72b-instruct0.574 USD1.72 USD131,072
Qwen2.5 7B Instruct qwen2-5-7b-instruct0.072 USD0.144 USD131,072
Qwen2.5-Coder 32B Instruct qwen2-5-coder-32b-instruct0.287 USD0.861 USD131,072
Qwen2.5-Coder 7B Instruct qwen2-5-coder-7b-instruct0.144 USD0.287 USD131,072
Qwen2.5-Math 72B Instruct qwen2-5-math-72b-instruct0.574 USD1.72 USD4,096
Qwen2.5-Math 7B Instruct qwen2-5-math-7b-instruct0.144 USD0.287 USD4,096
Qwen2.5-Omni 7B qwen2-5-omni-7b0.087 USD0.345 USD32,768
Qwen2.5-VL 72B Instruct qwen2-5-vl-72b-instruct2.29 USD6.88 USD131,072
Qwen2.5-VL 7B Instruct qwen2-5-vl-7b-instruct0.287 USD0.717 USD131,072
Qwen3 14B qwen3-14b0.144 USD0.574 USD131,072
Qwen3 235B-A22B qwen3-235b-a22b0.287 USD1.15 USD131,072
Qwen3 32B qwen3-32b0.287 USD1.15 USD131,072
Qwen3 8B qwen3-8b0.072 USD0.287 USD131,072
Qwen3-ASR Flash qwen3-asr-flash0.032 USD0.032 USD53,248 older than 30 days
Qwen3-Coder 30B-A3B Instruct qwen3-coder-30b-a3b-instruct0.216 USD0.861 USD262,144
Qwen3-Coder 480B-A35B Instruct qwen3-coder-480b-a35b-instruct0.861 USD3.44 USD262,144
Qwen3 Coder Flash qwen3-coder-flash0.144 USD0.574 USD1,000,000 older than 30 days
Qwen3 Coder Plus qwen3-coder-plus0.574 USD2.30 USD1,048,576
Qwen3 Max qwen3-max0.359 USD1.43 USD262,144
Qwen3-Next 80B-A3B Instruct qwen3-next-80b-a3b-instruct0.144 USD0.574 USD131,072
Qwen3-Next 80B-A3B (Thinking) qwen3-next-80b-a3b-thinking0.144 USD1.43 USD131,072
Qwen3-Omni Flash qwen3-omni-flash0.058 USD0.230 USD65,536 older than 30 days
Qwen3-Omni Flash Realtime qwen3-omni-flash-realtime0.230 USD0.918 USD65,536 older than 30 days
Qwen3-VL 235B-A22B qwen3-vl-235b-a22b0.287 USD1.15 USD131,072
Qwen3-VL 30B-A3B qwen3-vl-30b-a3b0.108 USD0.431 USD131,072
Qwen3-VL Plus qwen3-vl-plus0.143 USD1.43 USD262,144 older than 30 days
Qwen3.5 397B-A17B qwen3.5-397b-a17b0.172 USD1.03 USD262,144 older than 30 days
Qwen3.5 Flash qwen3.5-flash0.029 USD0.287 USD1,000,000
Qwen3.5 Plus qwen3.5-plus0.115 USD0.688 USD1,000,000
Qwen3.6 Flash qwen3.6-flash0.188 USD1.12 USD1,000,000 older than 30 days
Qwen3.6 Max Preview qwen3.6-max-preview1.32 USD7.90 USD245,800 older than 30 days
Qwen3.6 Plus qwen3.6-plus0.500 USD3.00 USD1,000,000 older than 30 days
Qwen3.7 Flash qwen3.7-flash0.030 USD0.118 USD1,000,000 older than 30 days
Qwen3.7 Max qwen3.7-max2.50 USD7.50 USD1,000,000 older than 30 days
Qwen3.7 Plus qwen3.7-plus0.500 USD3.00 USD1,000,000 older than 30 days
Qwen3.8 Flash qwen3.8-flash0.119 USD0.401 USD1,000,000
Qwen3.8 Max qwen3.8-max1.78 USD5.33 USD1,000,000 older than 30 days
QwQ 32B qwq-32b0.287 USD0.861 USD131,072
QwQ Plus qwq-plus0.230 USD0.574 USD131,072 older than 30 days
siliconflow/deepseek-r1-0528 siliconflow/deepseek-r1-05280.500 USD2.18 USD163,840 older than 30 days
siliconflow/deepseek-v3-0324 siliconflow/deepseek-v3-03240.250 USD1.00 USD163,840 older than 30 days
siliconflow/deepseek-v3.1-terminus siliconflow/deepseek-v3.1-terminus0.270 USD1.00 USD163,840 older than 30 days
siliconflow/deepseek-v3.2 siliconflow/deepseek-v3.20.270 USD0.420 USD163,840 older than 30 days
Tongyi Intent Detect V3 tongyi-intent-detect-v30.058 USD0.144 USD8,192

Sources of this page