AMD
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://developer.amd.com.cn/radeon/api/v1models.dev, read
- Authentication
- Authorization: Bearer, with the key in
AMD_API_KEYmodels.dev, read - Structured output
- Unknown
- Tool calling
- 6 of 6 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 with the model you want.
OpenCode
Put this in opencode.json in your project folder:
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"amd": {
"npm": "@ai-sdk/openai-compatible",
"name": "AMD",
"options": {
"baseURL": "https://developer.amd.com.cn/radeon/api/v1",
"apiKey": "{env:AMD_API_KEY}"
},
"models": {
"DeepSeek-V4-Flash": {
"name": "DeepSeek-V4-Flash"
}
}
}
}
}- OpenCode reads any OpenAI-compatible address through the @ai-sdk/openai-compatible package, and an address that speaks the Responses API through @ai-sdk/openai.
From OpenCode documentation, read .
Pi
Put this in ~/.pi/agent/models.json:
{
"providers": {
"amd": {
"baseUrl": "https://developer.amd.com.cn/radeon/api/v1",
"api": "openai-completions",
"apiKey": "$AMD_API_KEY",
"models": [
{
"id": "DeepSeek-V4-Flash"
}
]
}
}
}- The apiKey field can name an environment variable as $NAME.
From Pi documentation, read .
Codex
Codex speaks only the Responses API, and AMD 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 AMD 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 | 0.140 USD | 0.280 USD | 1,048,576 | older than 30 days |
DeepSeek V4 Flash Vision Exp DeepSeek-V4-Flash-Vision-Exp | 0.140 USD | 0.280 USD | 1,000,000 | |
DeepSeek V4.1 Flash DeepSeek-V4.1-Flash | 0.140 USD | 0.280 USD | 1,048,576 | |
MiniCPM5-2B MiniCPM5-2B | 0.124 USD | 0.743 USD | 131,072 | |
Qwen3.8 27B Qwen3.8-27B | 0 USD | 0 USD | 131,072 | older than 30 days |
Qwen3.8 Flash Next Qwen3.8-Flash-Next | 0.150 USD | 0.470 USD | 262,144 |
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.