feat: add IO Intelligence provider (#12795)
This commit is contained in:
@@ -29,6 +29,7 @@ pub(crate) mod declarative_providers {
|
||||
iflytek,
|
||||
iflytek_astron,
|
||||
inception,
|
||||
ionet,
|
||||
llama_swap,
|
||||
lmstudio,
|
||||
lynkr,
|
||||
|
||||
@@ -0,0 +1,49 @@
|
||||
{
|
||||
"name": "ionet",
|
||||
"engine": "openai",
|
||||
"display_name": "IO Intelligence",
|
||||
"description": "Inference for open-weight models (DeepSeek, Qwen, Llama, GLM, Kimi, gpt-oss and more) through io.net's OpenAI-compatible API",
|
||||
"api_key_env": "IONET_API_KEY",
|
||||
"base_url": "https://api.intelligence.io.solutions/api/v1/chat/completions",
|
||||
"dynamic_models": false,
|
||||
"models": [
|
||||
{
|
||||
"name": "deepseek-ai/DeepSeek-V4.1-Flash",
|
||||
"context_limit": 1048320
|
||||
},
|
||||
{
|
||||
"name": "zai-org/GLM-5.3",
|
||||
"context_limit": 262144
|
||||
},
|
||||
{
|
||||
"name": "moonshotai/Kimi-K3",
|
||||
"context_limit": 1048576
|
||||
},
|
||||
{
|
||||
"name": "Qwen/Qwen3-Next-80B-A3B-Instruct",
|
||||
"context_limit": 262144
|
||||
},
|
||||
{
|
||||
"name": "deepseek-ai/DeepSeek-V3.2",
|
||||
"context_limit": 163840
|
||||
},
|
||||
{
|
||||
"name": "zai-org/GLM-4.6",
|
||||
"context_limit": 131072
|
||||
},
|
||||
{
|
||||
"name": "openai/gpt-oss-120b",
|
||||
"context_limit": 131072
|
||||
},
|
||||
{
|
||||
"name": "meta-llama/Llama-3.3-70B-Instruct",
|
||||
"context_limit": 128000
|
||||
},
|
||||
{
|
||||
"name": "moonshotai/Kimi-K2-Instruct-0905",
|
||||
"context_limit": 262144
|
||||
}
|
||||
],
|
||||
"supports_streaming": true,
|
||||
"model_doc_link": "https://io.net/docs/reference/ai-models/create-chat-completion"
|
||||
}
|
||||
@@ -43,6 +43,7 @@ goose is compatible with a wide range of LLM providers, allowing you to choose a
|
||||
| [Groq](https://groq.com/) | High-performance inference hardware and tools for LLMs. | `GROQ_API_KEY` |
|
||||
| [iFlytek Spark](https://www.xfyun.cn/doc/spark/HTTP%E8%B0%83%E7%94%A8%E6%96%87%E6%A1%A3.html) | iFlytek Spark (讯飞星火) models (4.0Ultra, generalv3.5, max-32k) via the OpenAI-compatible HTTP API. Best for chat: Spark needs `tool_calls_switch=true` (not injectable here) to return OpenAI-style tool calls. | `SPARK_API_PASSWORD` |
|
||||
| [iFlytek Astron MaaS](https://maas.xfyun.cn/) | iFlytek Astron MaaS (讯飞星辰) hosting Spark X2, DeepSeek, GLM, Kimi, MiniMax, Qwen, and Astron coding models via an OpenAI-compatible API. Set `ASTRON_BASE_URL` to switch between the Token Plan and Coding Plan endpoints. | `ASTRON_API_KEY`, `ASTRON_BASE_URL` (optional) |
|
||||
| [IO Intelligence](https://io.net/) | Inference for open-weight models (DeepSeek, Qwen, Llama, GLM, Kimi, gpt-oss and more) through io.net's OpenAI-compatible API. | `IONET_API_KEY` |
|
||||
| [LiteLLM](https://docs.litellm.ai/docs/) | LiteLLM proxy supporting multiple models with automatic prompt caching and unified API access. | `LITELLM_HOST`, `LITELLM_BASE_PATH` (optional), `LITELLM_API_KEY` (optional), `LITELLM_CUSTOM_HEADERS` (optional), `LITELLM_TIMEOUT` (optional) |
|
||||
| [LM Studio](https://lmstudio.ai/) | Run local models with LM Studio's OpenAI-compatible server. **Because this provider runs locally, you must first [download a model](#local-llms).** | None required. Connects to local server at `localhost:1234` by default. |
|
||||
| [Meta](https://dev.meta.ai/) | Meta's Model API, home of the Muse Spark models. | `META_MODEL_API_KEY` |
|
||||
|
||||
Reference in New Issue
Block a user