From b78e0edb7d10eb112f7186e19a0d36c4f0d9d3ec Mon Sep 17 00:00:00 2001 From: Alex-wuhu Date: Sun, 22 Mar 2026 19:25:03 +0800 Subject: [PATCH 1/2] feat: add Novita AI as LLM provider --- docs/docs.json | 1 + docs/llm-providers/novita.mdx | 35 +++++++++++++++++++++++++++++++++ docs/llm-providers/overview.mdx | 4 ++++ 3 files changed, 40 insertions(+) create mode 100644 docs/llm-providers/novita.mdx diff --git a/docs/docs.json b/docs/docs.json index 27ee5dc9c..df83365e1 100644 --- a/docs/docs.json +++ b/docs/docs.json @@ -36,6 +36,7 @@ "llm-providers/openai", "llm-providers/anthropic", "llm-providers/openrouter", + "llm-providers/novita", "llm-providers/vertex", "llm-providers/bedrock", "llm-providers/azure", diff --git a/docs/llm-providers/novita.mdx b/docs/llm-providers/novita.mdx new file mode 100644 index 000000000..632391d81 --- /dev/null +++ b/docs/llm-providers/novita.mdx @@ -0,0 +1,35 @@ +--- +title: "Novita AI" +description: "Configure Strix with Novita AI models" +--- + +[Novita AI](https://novita.ai) provides fast, cost-efficient inference for open-source models via an OpenAI-compatible API. + +## Setup + +```bash +export STRIX_LLM="openai/moonshotai/kimi-k2.5" +export LLM_API_KEY="your-novita-api-key" +export LLM_API_BASE="https://api.novita.ai/openai" +``` + +## Available Models + +| Model | Configuration | +|-------|---------------| +| Kimi K2.5 (recommended) | `openai/moonshotai/kimi-k2.5` | +| GLM-5 | `openai/zai-org/glm-5` | +| MiniMax M2.5 | `openai/minimax/minimax-m2.5` | + +## Get API Key + +1. Sign up at [novita.ai](https://novita.ai) +2. Navigate to **API Keys** in your dashboard +3. Create a new key and copy it + +## Benefits + +- **Cost-efficient** — Competitive pricing with per-token billing +- **OpenAI-compatible** — Drop-in replacement using `LLM_API_BASE` +- **Large context** — Models support up to 262k token context windows +- **Function calling** — All listed models support tool/function calling diff --git a/docs/llm-providers/overview.mdx b/docs/llm-providers/overview.mdx index 153ad0ca8..2412be05e 100644 --- a/docs/llm-providers/overview.mdx +++ b/docs/llm-providers/overview.mdx @@ -25,6 +25,7 @@ You can also use any LiteLLM-compatible provider with your own API keys: | GPT-5 | OpenAI | `openai/gpt-5` | | Claude Sonnet 4.6 | Anthropic | `anthropic/claude-sonnet-4-6` | | Gemini 3 Pro | Google Vertex | `vertex_ai/gemini-3-pro-preview` | +| Kimi K2.5 | Novita AI | `openai/moonshotai/kimi-k2.5` | ```bash export STRIX_LLM="openai/gpt-5" @@ -57,6 +58,9 @@ See the [Local Models guide](/llm-providers/local) for setup instructions and re Access 100+ models through a single API. + + Cost-efficient open-source model inference. + Gemini 3 models via Google Cloud. From 0dd0721ce2b72a7f0f2ec4e9c89a161198b895f0 Mon Sep 17 00:00:00 2001 From: Alex-wuhu Date: Sun, 22 Mar 2026 19:34:16 +0800 Subject: [PATCH 2/2] docs: clarify Novita AI requires LLM_API_BASE in overview The overview table lists Novita alongside providers that only need STRIX_LLM + LLM_API_KEY, but Novita also requires LLM_API_BASE to point at api.novita.ai/openai. Without this, users copying the generic code block would hit connection errors against api.openai.com. Add a Note callout directing users to the Novita guide for full setup, and mention Novita in the README supported-providers reference line. --- README.md | 2 +- docs/llm-providers/overview.mdx | 4 ++++ 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 8dbfa9beb..53f0b2619 100644 --- a/README.md +++ b/README.md @@ -233,7 +233,7 @@ export STRIX_REASONING_EFFORT="high" # control thinking effort (default: high, - [Anthropic Claude Sonnet 4.6](https://claude.com/platform/api) — `anthropic/claude-sonnet-4-6` - [Google Gemini 3 Pro Preview](https://cloud.google.com/vertex-ai) — `vertex_ai/gemini-3-pro-preview` -See the [LLM Providers documentation](https://docs.strix.ai/llm-providers/overview) for all supported providers including Vertex AI, Bedrock, Azure, and local models. +See the [LLM Providers documentation](https://docs.strix.ai/llm-providers/overview) for all supported providers including Novita AI, Vertex AI, Bedrock, Azure, and local models. ## Enterprise diff --git a/docs/llm-providers/overview.mdx b/docs/llm-providers/overview.mdx index 2412be05e..3b986ff4c 100644 --- a/docs/llm-providers/overview.mdx +++ b/docs/llm-providers/overview.mdx @@ -32,6 +32,10 @@ export STRIX_LLM="openai/gpt-5" export LLM_API_KEY="your-api-key" ``` + + **Novita AI** requires an additional `LLM_API_BASE` variable pointing to their OpenAI-compatible endpoint. See the [Novita AI guide](/llm-providers/novita) for full setup instructions. + + ## Local Models Run models locally with [Ollama](https://ollama.com), [LM Studio](https://lmstudio.ai), or any OpenAI-compatible server: