nezumi/9router
1
0
Fork 0
mirror of https://github.com/Nezumi-2711/9router.git synced 2026-09-22 13:38:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(nvidia): add new models and capabilities for NVIDIA provider

Browse Source 
- Updated capabilities for NVIDIA models to enforce OpenAI-compatible reasoning formats.
- Added new models: MiniMax M3, GLM 5.2, DeepSeek V4 Pro, DeepSeek V4 Flash, Kimi K2.6, and Nemotron 3 Ultra to the NVIDIA registry.

This enhances the provider's functionality and aligns with OpenAI standards.
This commit is contained in:
decolua
2026-07-03 12:15:58 +07:00
parent cb0135b695
commit ced51ed62f
4 changed files with 74 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
open-sse/providers/capabilities.js
+9
View File
@@ -102,6 +102,15 @@ export const MODEL_CAPABILITIES = {
* Provider-specific capability overrides. Keyed by provider alias/id.
*/
export const PROVIDER_CAPABILITIES = {
// NVIDIA NIM is OpenAI-compatible → rejects MiniMax/GLM native `thinking` field.
// Force openai reasoning_effort format for its reasoning models. #issue
"nvidia": {
"minimaxai/minimax-m2.7": { reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 131072 },
"minimaxai/minimax-m3": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 512000, maxOutput: 131072 },
"z-ai/glm-5.2": { reasoning: true, thinkingFormat: "openai", contextWindow: 200000, maxOutput: 128000 },
"deepseek-ai/deepseek-v4-pro": { reasoning: true, thinkingFormat: "openai", contextWindow: 1000000, maxOutput: 65536 },
"deepseek-ai/deepseek-v4-flash": { reasoning: true, thinkingFormat: "openai", contextWindow: 1000000, maxOutput: 65536 },
},
// CodeBuddy.cn — authoritative per-model metadata from the gateway's model
// config (contextWindow=maxInputTokens, maxOutput=maxOutputTokens, vision=
// supportsImages). Every model reasons via OpenAI-style reasoning_effort
open-sse/providers/registry/nvidia.js
+7 -2
View File
@@ -20,8 +20,13 @@ export default {
validateUrl: "https://integrate.api.nvidia.com/v1/models",
},
models: [
{ id: "minimaxai/minimax-m2.7", name: "Minimax M2.7" },
{ id: "z-ai/glm4.7", name: "GLM 4.7" },
{ id: "minimaxai/minimax-m2.7", name: "MiniMax M2.7" },
{ id: "minimaxai/minimax-m3", name: "MiniMax M3" },
{ id: "z-ai/glm-5.2", name: "GLM 5.2" },
{ id: "deepseek-ai/deepseek-v4-pro", name: "DeepSeek V4 Pro" },
{ id: "deepseek-ai/deepseek-v4-flash", name: "DeepSeek V4 Flash" },
{ id: "moonshotai/kimi-k2.6", name: "Kimi K2.6" },
{ id: "nvidia/nemotron-3-ultra-550b-a55b", name: "Nemotron 3 Ultra" },
{ id: "nvidia/nv-embedqa-e5-v5", name: "NV EmbedQA E5 v5", kind: "embedding" },
{ id: "nvidia/parakeet-ctc-1.1b-asr", name: "Parakeet CTC 1.1B", params: ["language"], kind: "stt" },
{ id: "fastpitch", name: "FastPitch", kind: "tts" },