Skip to content

docs: add Opper provider guide #1606

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Felixkw12 wants to merge 1 commit into
base: main
Choose a base branch
from
+55 −0
Open

docs: add Opper provider guide #1606

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions docs/docs.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,7 @@
"llm-providers/bedrock",
"llm-providers/azure",
"llm-providers/novita",
"llm-providers/opper",
"llm-providers/local"
]
},
Expand Down
54 changes: 54 additions & 0 deletions docs/llm-providers/opper.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,54 @@
---
title: "Opper"
description: "Configure Strix with models through Opper"
---

[Opper](https://opper.ai) is an EU-hosted AI gateway with 700+ models from 50+ providers behind one OpenAI-compatible API.

## Setup

```bash
export STRIX_LLM="openai/glm-5.3"
export LLM_API_KEY="your-opper-api-key"
export LLM_API_BASE="https://api.opper.ai/v3/compat"
```

The `openai/` prefix sends requests to the OpenAI-compatible endpoint set in `LLM_API_BASE`. The remaining value is an Opper model name.

## Available Models

Model names are bare pool names, and Opper picks the route per request:

| Model | Configuration |
|-------|---------------|
| GLM-5.3 (recommended) | `openai/glm-5.3` |
| GPT-6.1 Sol | `openai/gpt-6.1-sol` |
| GPT-6 Astra | `openai/gpt-6-astra` |
| Claude Opus 5.5 | `openai/claude-opus-5-5` |
| Claude Sonnet 5.5 | `openai/claude-sonnet-5-5` |
| Gemini 4 Argon | `openai/gemini-4-argon` |
| Gemini 3.8 Flash | `openai/gemini-3.8-flash` |
| DeepSeek V4.1 Flash | `openai/deepseek-v4.1-flash` |
| DeepSeek V4 Pro | `openai/deepseek-v4-pro` |
| Kimi K3.1 Pro | `openai/kimi-k3.1-pro` |
| GLM-5.3 Flash | `openai/glm-5.3-flash` |

A `provider/model` name such as `openai/anthropic/claude-sonnet-5-5` pins one route. OpenAI, Anthropic and Gemini models keep their provider safeguards through Opper. Security testing with them needs [Daybreak](https://openai.com/daybreak/), [CVP](https://support.claude.com/en/articles/14604842-cyber-verification-program) or [Fairwind](https://deepmind.google/fairwind-program/) access.

The full list is in Opper's public model catalog:

```text
https://api.opper.ai/v3/models
```

## Get API Key

1. Go to [platform.opper.ai](https://platform.opper.ai)
2. Sign in and create an API key
3. Set the key as `LLM_API_KEY`

## Benefits

- **EU-hosted**: Opper runs in the EU, and requests can be pinned to EU-hosted regions
- **Single API**: 700+ models from 50+ providers with one key
- **Provider rates**: no markup on provider token rates