pjandro/OmniRoute
1
0
Fork 0
mirror of https://github.com/diegosouzapw/OmniRoute.git synced 2026-08-05 14:52:09 +03:00
Code Issues Packages Projects Releases Wiki Activity

feat(provider): add Baidu Qianfan chat provider (#1582)

Browse Source 
Integrated into release/v3.7.0
This commit is contained in:
jimmyzhuu
2026-04-25 18:47:42 +08:00
committed by GitHub
parent e64dc3b431
commit 9eac8c2efe
9 changed files with 130 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/ENVIRONMENT.md
View File

@@ -404,6 +404,7 @@ Recognized pattern: `{PROVIDER_ID}_API_KEY`
| `COHERE_API_KEY` | Cohere |
| `NVIDIA_API_KEY` | NVIDIA NIM |
| `NEBIUS_API_KEY` | Nebius (embeddings) |
| `QIANFAN_API_KEY` | Baidu Qianfan |
> [!TIP]
> Keys set via the Dashboard are stored encrypted in SQLite and take precedence over environment variables.

10
docs/USER_GUIDE.md
View File

@@ -36,6 +36,7 @@ Complete guide for configuring providers, creating combos, integrating CLI tools
| | Cerebras | Pay per use | None | Wafer-scale speed |
| | Cohere | Pay per use | None | Command R+ RAG |
| | NVIDIA NIM | Pay per use | None | Enterprise models |
| | Baidu Qianfan | Pay per use | None | ERNIE models |
| **💰 CHEAP** | GLM-4.7 | $0.6/1M | Daily 10AM | Budget backup |
| | MiniMax M2.1 | $0.2/1M | 5-hour rolling | Cheapest option |
| | Kimi K2 | $9/mo flat | 10M tokens/mo | Predictable cost |
@@ -191,6 +192,13 @@ Models:
**Use:** `kimi/kimi-latest` — **Pro Tip:** Fixed $9/month for 10M tokens = $0.90/1M effective cost!
#### Baidu Qianfan / ERNIE
1. Sign up: [Baidu AI Cloud Qianfan](https://cloud.baidu.com/product/wenxinworkshop)
2. Create a Qianfan API key → Dashboard → Add API Key: Provider: `qianfan`
**Use:** `qianfan/ernie-4.5-turbo-128k`, `qianfan/ernie-x1-turbo-32k`, or another Qianfan OpenAI-compatible model ID.
### 🆓 FREE Providers
#### Qoder (8 FREE models)
@@ -590,6 +598,8 @@ For the full environment variable reference, see the [README](../README.md).
**NVIDIA NIM (`nvidia/`)**: `nvidia/nvidia/llama-3.3-70b-instruct`
**Baidu Qianfan (`qianfan/`)**: `qianfan/ernie-4.5-turbo-128k`, `qianfan/ernie-x1-turbo-32k`
</details>
---