Alibaba
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-intl.aliyuncs.com/compatible-mode/v1models.dev, read
- Authentication
- Authorization: Bearer, with the key in
DASHSCOPE_API_KEYmodels.dev, read - Structured output
- Unknown
- Tool calling
- 51 of 56 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-v4-flash-0731 with the model you want.
OpenCode
Put this in opencode.json in your project folder:
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"alibaba": {
"npm": "@ai-sdk/openai-compatible",
"name": "Alibaba",
"options": {
"baseURL": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
"apiKey": "{env:DASHSCOPE_API_KEY}"
},
"models": {
"deepseek-v4-flash-0731": {
"name": "deepseek-v4-flash-0731"
}
}
}
}
}- OpenCode reads any OpenAI-compatible address through the @ai-sdk/openai-compatible package, and an address that speaks the Responses API through @ai-sdk/openai.
From OpenCode documentation, read .
Pi
Put this in ~/.pi/agent/models.json:
{
"providers": {
"alibaba": {
"baseUrl": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
"api": "openai-completions",
"apiKey": "$DASHSCOPE_API_KEY",
"models": [
{
"id": "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 Alibaba 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 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.
| Model | Input | Output | Context | As of |
|---|---|---|---|---|
DeepSeek V4 Flash 0731 deepseek-v4-flash-0731 | 0.200 USD | 0.400 USD | 1,000,000 | older than 30 days |
GLM-5.2 glm-5.2 | 1.40 USD | 4.40 USD | 1,000,000 | older than 30 days |
Kimi K3 kimi-k3 | 3.00 USD | 15.00 USD | 1,048,576 | older than 30 days |
QVQ Max qvq-max | 1.20 USD | 4.80 USD | 131,072 | older than 30 days |
Qwen Flash qwen-flash | 0.050 USD | 0.400 USD | 1,000,000 | older than 30 days |
Qwen Max qwen-max | 1.60 USD | 6.40 USD | 32,768 | older than 30 days |
Qwen-MT Plus qwen-mt-plus | 2.46 USD | 7.37 USD | 16,384 | |
Qwen-MT Turbo qwen-mt-turbo | 0.160 USD | 0.490 USD | 16,384 | |
Qwen-Omni Turbo qwen-omni-turbo | 0.070 USD | 0.270 USD | 32,768 | older than 30 days |
Qwen-Omni Turbo Realtime qwen-omni-turbo-realtime | 0.270 USD | 1.07 USD | 32,768 | older than 30 days |
Qwen Plus qwen-plus | 0.400 USD | 1.20 USD | 1,000,000 | older than 30 days |
Qwen Plus Character (Japanese) qwen-plus-character-ja | 0.500 USD | 1.40 USD | 8,192 | |
Qwen Turbo qwen-turbo | 0.050 USD | 0.200 USD | 1,000,000 | older than 30 days |
Qwen-VL Max qwen-vl-max | 0.800 USD | 3.20 USD | 131,072 | older than 30 days |
Qwen-VL OCR qwen-vl-ocr | 0.720 USD | 0.720 USD | 34,096 | older than 30 days |
Qwen-VL Plus qwen-vl-plus | 0.210 USD | 0.630 USD | 131,072 | older than 30 days |
Qwen2.5 14B Instruct qwen2-5-14b-instruct | 0.350 USD | 1.40 USD | 131,072 | |
Qwen2.5 32B Instruct qwen2-5-32b-instruct | 0.700 USD | 2.80 USD | 131,072 | |
Qwen2.5 72B Instruct qwen2-5-72b-instruct | 1.40 USD | 5.60 USD | 131,072 | |
Qwen2.5 7B Instruct qwen2-5-7b-instruct | 0.175 USD | 0.700 USD | 131,072 | |
Qwen2.5-Omni 7B qwen2-5-omni-7b | 0.100 USD | 0.400 USD | 32,768 | |
Qwen2.5-VL 72B Instruct qwen2-5-vl-72b-instruct | 2.80 USD | 8.40 USD | 131,072 | |
Qwen2.5-VL 7B Instruct qwen2-5-vl-7b-instruct | 0.350 USD | 1.05 USD | 131,072 | |
Qwen3 14B qwen3-14b | 0.350 USD | 1.40 USD | 131,072 | |
Qwen3 235B-A22B qwen3-235b-a22b | 0.700 USD | 2.80 USD | 131,072 | |
Qwen3 32B qwen3-32b | 0.700 USD | 2.80 USD | 131,072 | |
Qwen3 8B qwen3-8b | 0.180 USD | 0.700 USD | 131,072 | |
Qwen3-ASR Flash qwen3-asr-flash | 0.035 USD | 0.035 USD | 53,248 | older than 30 days |
Qwen3-Coder 30B-A3B Instruct qwen3-coder-30b-a3b-instruct | 0.450 USD | 2.25 USD | 262,144 | |
Qwen3-Coder 480B-A35B Instruct qwen3-coder-480b-a35b-instruct | 1.50 USD | 7.50 USD | 262,144 | |
Qwen3 Coder Flash qwen3-coder-flash | 0.300 USD | 1.50 USD | 1,000,000 | older than 30 days |
Qwen3 Coder Plus qwen3-coder-plus | 1.00 USD | 5.00 USD | 1,048,576 | older than 30 days |
Qwen3-LiveTranslate Flash Realtime qwen3-livetranslate-flash-realtime | 10.00 USD | 10.00 USD | 53,248 | older than 30 days |
Qwen3 Max qwen3-max | 1.20 USD | 6.00 USD | 262,144 | older than 30 days |
Qwen3-Next 80B-A3B Instruct qwen3-next-80b-a3b-instruct | 0.500 USD | 2.00 USD | 131,072 | |
Qwen3-Next 80B-A3B (Thinking) qwen3-next-80b-a3b-thinking | 0.500 USD | 6.00 USD | 131,072 | |
Qwen3-Omni Flash qwen3-omni-flash | 0.430 USD | 1.66 USD | 65,536 | older than 30 days |
Qwen3-Omni Flash Realtime qwen3-omni-flash-realtime | 0.520 USD | 1.99 USD | 65,536 | older than 30 days |
Qwen3-VL 235B-A22B qwen3-vl-235b-a22b | 0.700 USD | 2.80 USD | 131,072 | |
Qwen3-VL 30B-A3B qwen3-vl-30b-a3b | 0.200 USD | 0.800 USD | 131,072 | |
Qwen3-VL Plus qwen3-vl-plus | 0.200 USD | 1.60 USD | 262,144 | older than 30 days |
Qwen3.5 122B-A10B qwen3.5-122b-a10b | 0.400 USD | 3.20 USD | 262,144 | older than 30 days |
Qwen3.5 27B qwen3.5-27b | 0.300 USD | 2.40 USD | 262,144 | older than 30 days |
Qwen3.5 35B-A3B qwen3.5-35b-a3b | 0.250 USD | 2.00 USD | 262,144 | older than 30 days |
Qwen3.5 397B-A17B qwen3.5-397b-a17b | 0.600 USD | 3.60 USD | 262,144 | older than 30 days |
Qwen3.5 Plus qwen3.5-plus | 0.400 USD | 2.40 USD | 1,000,000 | older than 30 days |
Qwen3.6 27B qwen3.6-27b | 0.600 USD | 3.60 USD | 262,144 | older than 30 days |
Qwen3.6 35B-A3B qwen3.6-35b-a3b | 0.248 USD | 1.49 USD | 262,144 | older than 30 days |
Qwen3.6 Flash qwen3.6-flash | 0.188 USD | 1.12 USD | 1,000,000 | older than 30 days |
Qwen3.6 Max Preview qwen3.6-max-preview | 1.30 USD | 7.80 USD | 262,144 | older than 30 days |
Qwen3.6 Plus qwen3.6-plus | 0.500 USD | 3.00 USD | 1,000,000 | older than 30 days |
Qwen3.7 Max qwen3.7-max | 2.50 USD | 7.50 USD | 1,000,000 | older than 30 days |
Qwen3.7 Plus qwen3.7-plus | 0.500 USD | 3.00 USD | 1,000,000 | older than 30 days |
Qwen3.8 Flash qwen3.8-flash | 0.150 USD | 0.470 USD | 1,000,000 | |
Qwen3.8 Max qwen3.8-max | 2.00 USD | 6.00 USD | 1,000,000 | older than 30 days |
QwQ Plus qwq-plus | 0.800 USD | 2.40 USD | 131,072 | older than 30 days |
Sources of this page
- models.dev/api.json, read
Paid links
No link in this directory is a paid link or an ad, and no listing is paid for. The order and the contents of every list come from the sources named on this page.