@juspay/neurolink 13.8.12 → 13.8.13

package/CHANGELOG.md

@@ -1,8 +1,8 @@
-## [13.8.12](https://github.com/juspay/neurolink/compare/v13.8.11...v13.8.12) (2026-10-24)
+## [13.8.13](https://github.com/juspay/neurolink/compare/v13.8.12...v13.8.13) (2026-10-24)
 
 ### Bug Fixes
 
-- **(server):** apply the default body size limit to JSON and form bodies on Hono and in the proxy ([e7198e6](https://github.com/juspay/neurolink/commit/e7198e697e1ba3a5b3c28f9f3f975e96bee0bf15))
+- **(nvidia-nim):** stop recommending models NVIDIA retired in the CLI picker and guides ([892a016](https://github.com/juspay/neurolink/commit/892a016307c83b041495d0b8838cc3d46bc47de0))
 
 ## [11.2.3](https://github.com/juspay/neurolink/compare/v11.2.2...v11.2.3) (2026-08-19)
 

package/dist/utils/modelChoices.js

@@ -228,24 +228,16 @@ const TOP_MODELS_CONFIG = {
     ],
     [AIProviderName.NVIDIA_NIM]: [
         {
-            model: "meta/llama-3.3-70b-instruct",
-            description: "Recommended - Llama 3.3 70B",
+            model: NvidiaNimModels.GPT_OSS_20B,
+            description: "Recommended - gpt-oss 20B (default)",
         },
         {
-            model: "nvidia/llama-3.3-nemotron-super-49b-v1",
-            description: "Nemotron Super (reasoning)",
+            model: NvidiaNimModels.LLAMA_3_2_11B_VISION,
+            description: "Llama 3.2 11B vision",
         },
         {
-            model: "deepseek-ai/deepseek-r1",
-            description: "DeepSeek-R1 hosted on NIM",
-        },
-        {
-            model: "meta/llama-3.2-90b-vision-instruct",
-            description: "Llama 3.2 vision",
-        },
-        {
-            model: "mistralai/mixtral-8x22b-instruct-v0.1",
-            description: "Mixtral 8x22B",
+            model: NvidiaNimModels.LLAMA_3_2_90B_VISION,
+            description: "Llama 3.2 90B vision",
         },
     ],
     [AIProviderName.LM_STUDIO]: [

package/docs-site/static/search-index.json

@@ -4408,7 +4408,7 @@
 {"objectID":"f7ec45d333ef30219c7a1569e33dc05b0b489f8dced84c264c18e9fb9fe2458d","title":"Optional Variables","url":"/docs/getting-started/environment-variables#optional-variables-13","content":"Optional Variables","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"Optional Variables","lvl3":""}},
 {"objectID":"bc288fb117658972a30a2ba66e55e1dcd187c9d1da8ae1b35f52e5d645e41344","title":"NIM-Specific Extras (rarely needed)","url":"/docs/getting-started/environment-variables#nim-specific-extras-rarely-needed","content":"NIM-Specific Extras (rarely needed)","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"NIM-Specific Extras (rarely needed)","lvl3":""}},
 {"objectID":"c331d4617737a5cfad44f0f398c430267deb83896fbef84b4cda5c56ebaeef0e","title":"How to Get NVIDIA NIM API Key","url":"/docs/getting-started/environment-variables#how-to-get-nvidia-nim-api-key","content":"Visit NVIDIA Build\nSign in with your NVIDIA developer account\nOpen Settings → API Keys\nGenerate a new API key (Bearer token)","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"How to Get NVIDIA NIM API Key","lvl3":""}},
-{"objectID":"abbfcedf11a5293f784a6021af47a1967d14526ce324a2fbaaf6ac00adafc58d","title":"Supported Models","url":"/docs/getting-started/environment-variables#supported-models-11","content":"meta/llama-3.3-70b-instruct (default) - Llama 3.3 70B Instruct\nAny model listed at build.nvidia.com/models","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"Supported Models","lvl3":""}},
+{"objectID":"abbfcedf11a5293f784a6021af47a1967d14526ce324a2fbaaf6ac00adafc58d","title":"Supported Models","url":"/docs/getting-started/environment-variables#supported-models-11","content":"openai/gpt-oss-20b (default) - OpenAI gpt-oss 20B, 128K context, tool calling\nAny model listed at build.nvidia.com/models","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"Supported Models","lvl3":""}},
 {"objectID":"8f65b0307933689fcf5717a2ddab1b3fe48b44a25993beaefc0c203716cf1894","title":"14. LM Studio (Local)","url":"/docs/getting-started/environment-variables#14-lm-studio-local","content":"LM Studio is a local provider — no API key is required for standard installations.","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"14. LM Studio (Local)","lvl3":""}},
 {"objectID":"be426d22afb7ec4c8d630b72b6a1db679d001843a82df2143197d88811cbb12a","title":"Optional Variables","url":"/docs/getting-started/environment-variables#optional-variables-14","content":"Optional Variables","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"Optional Variables","lvl3":""}},
 {"objectID":"caa673ab6f5de21d611dd1eef67dd4e07afecf10d8cb0201102b839e96995bca","title":"How to Set Up LM Studio","url":"/docs/getting-started/environment-variables#how-to-set-up-lm-studio","content":"Install LM Studio from lmstudio.ai\nOpen LM Studio and download a model (e.g., Llama 3.2 3B Instruct)\nClick Local Server → Start Server\nThe server starts at http://localhost:1234/v1 by default\nNeuroLink auto-discovers the loaded model; no LM_STUDIO_MODEL needed\n\nNote: LM_STUDIO_API_KEY is only needed if you run LM Studio behind an authenticating reverse-proxy. Vanilla local installs do not require an API key.","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"How to Set Up LM Studio","lvl3":""}},
@@ -4622,12 +4622,12 @@
 {"objectID":"d82f8c3a0407aac56f55f222e4c0095b9fad1925db7a1dd2fbec190f55f331dc","title":"Basic Setup","url":"/docs/getting-started/provider-setup#basic-setup-10","content":"Basic Setup","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Basic Setup","lvl3":""}},
 {"objectID":"e7666199cf52c152bbd2e935e2d51ca0df577da915eaa38aac807a227a4c181d","title":"Optional Configuration","url":"/docs/getting-started/provider-setup#optional-configuration-9","content":"Optional Configuration","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Optional Configuration","lvl3":""}},
 {"objectID":"18321846566326d1547ba20c35f8190c7ae9c6fb3d6fb0fa9d807cdd7e32e1e0","title":"NIM-Specific Extras (Advanced)","url":"/docs/getting-started/provider-setup#nim-specific-extras-advanced","content":"These environment variables pass NIM-specific request body extensions. Leave them unset unless you have a specific need:","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"NIM-Specific Extras (Advanced)","lvl3":""}},
-{"objectID":"06fd92c3629ac0be9484c9214a7cfb3e40336689fdd7a7196b5adabb520e43ac","title":"Supported Models","url":"/docs/getting-started/provider-setup#supported-models-7","content":"meta/llama-3.3-70b-instruct (default) - Meta Llama 3.3 70B Instruct\nAny model from the NVIDIA NIM catalog","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Supported Models","lvl3":""}},
+{"objectID":"06fd92c3629ac0be9484c9214a7cfb3e40336689fdd7a7196b5adabb520e43ac","title":"Supported Models","url":"/docs/getting-started/provider-setup#supported-models-7","content":"openai/gpt-oss-20b (default) - OpenAI gpt-oss 20B, 128K context, tool calling\nAny model from the NVIDIA NIM catalog","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Supported Models","lvl3":""}},
 {"objectID":"e6822aacc3d662745a63786eb8d1399f45bb6bcac22898feda9b93b7b5a55c6d","title":"Usage Example","url":"/docs/getting-started/provider-setup#usage-example-14","content":"Usage Example","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Usage Example","lvl3":""}},
 {"objectID":"b23f6c751e3a8b2b4bfece3ba129b68e25f6e00204058cadf954d3eb8a36b82a","title":"CLI Usage","url":"/docs/getting-started/provider-setup#cli-usage-1","content":"CLI Usage","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"CLI Usage","lvl3":""}},
 {"objectID":"ec23735e5a15302451c7946e68ac107725e3f606c15810eead6bc36995b53af5","title":"Self-Hosted NIM Endpoints","url":"/docs/getting-started/provider-setup#self-hosted-nim-endpoints","content":"Override the base URL to point at your own NIM deployment:","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Self-Hosted NIM Endpoints","lvl3":""}},
 {"objectID":"01e42c60deafa5c50f53dd6572412b847c871735a4014652a0480cac5a5608ee","title":"Getting Started with NVIDIA NIM","url":"/docs/getting-started/provider-setup#getting-started-with-nvidia-nim","content":"Create Account: Visit build.nvidia.com\nOpen Settings: Navigate to Settings → API Keys\nGenerate Key: Create a new Bearer token API key\nBrowse Models: Explore the catalog at build.nvidia.com/models\nSet Environment: Export NVIDIA_NIM_API_KEY","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Getting Started with NVIDIA NIM","lvl3":""}},
-{"objectID":"2d33feba1ccdb840a4e9dbf01aaa90979c0c1335ef47a1a81b5d19e0e282dc46","title":"Environment Variables Reference","url":"/docs/getting-started/provider-setup#environment-variables-reference-3","content":"| Variable                        | Required | Default                               | Description                             |\n| ------------------------------- | -------- | ------------------------------------- | --------------------------------------- |\n| NVIDIA_NIM_API_KEY            | ✅       | -                                     | NVIDIA NIM API key (Bearer token)       |\n| NVIDIA_NIM_MODEL              | ❌       | meta/llama-3.3-70b-instruct         | Default model                           |\n| NVIDIA_NIM_BASE_URL           | ❌       | https://integrate.api.nvidia.com/v1 | Override for self-hosted NIM            |\n| NVIDIA_NIM_TOP_K              | ❌       | -                                     | Top-K sampling parameter                |\n| NVIDIA_NIM_MIN_P              | ❌       | -                                     | Min-P sampling parameter                |\n| NVIDIA_NIM_REPETITION_PENALTY | ❌       | -                                     | Repetition penalty                      |\n| NVIDIA_NIM_MIN_TOKENS         | ❌       | -                                     | Minimum tokens to generate              |\n| NVIDIA_NIM_CHAT_TEMPLATE      | ❌       | -                                     | Override model chat template (advanced) |","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Environment Variables Reference","lvl3":""}},
+{"objectID":"2d33feba1ccdb840a4e9dbf01aaa90979c0c1335ef47a1a81b5d19e0e282dc46","title":"Environment Variables Reference","url":"/docs/getting-started/provider-setup#environment-variables-reference-3","content":"| Variable                        | Required | Default                               | Description                             |\n| ------------------------------- | -------- | ------------------------------------- | --------------------------------------- |\n| NVIDIA_NIM_API_KEY            | ✅       | -                                     | NVIDIA NIM API key (Bearer token)       |\n| NVIDIA_NIM_MODEL              | ❌       | openai/gpt-oss-20b                  | Default model                           |\n| NVIDIA_NIM_BASE_URL           | ❌       | https://integrate.api.nvidia.com/v1 | Override for self-hosted NIM            |\n| NVIDIA_NIM_TOP_K              | ❌       | -                                     | Top-K sampling parameter                |\n| NVIDIA_NIM_MIN_P              | ❌       | -                                     | Min-P sampling parameter                |\n| NVIDIA_NIM_REPETITION_PENALTY | ❌       | -                                     | Repetition penalty                      |\n| NVIDIA_NIM_MIN_TOKENS         | ❌       | -                                     | Minimum tokens to generate              |\n| NVIDIA_NIM_CHAT_TEMPLATE      | ❌       | -                                     | Override model chat template (advanced) |","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Environment Variables Reference","lvl3":""}},
 {"objectID":"109acc4b5c1417599beb44840e21a88619106838727981fb5e0feae447a57038","title":"Provider ID and Aliases","url":"/docs/getting-started/provider-setup#provider-id-and-aliases-1","content":"Provider ID: nvidia-nim\nAliases: nim, nvidia","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Provider ID and Aliases","lvl3":""}},
 {"objectID":"0de45c35b35d239ea38353c402bc07233b46803a89df62d4d0aecf8fd0a53e53","title":"LM Studio Configuration","url":"/docs/getting-started/provider-setup#lm-studio","content":"LM Studio is a local AI provider — it runs models entirely on your machine with no data sent to any external service. No API key is required for standard (non-proxied) installations.","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"LM Studio Configuration","lvl3":""}},
 {"objectID":"51046d75613781b1d2770a64f2dbba80729a2e607c4aa529d60f2b53ca6676c4","title":"Prerequisites","url":"/docs/getting-started/provider-setup#prerequisites-2","content":"Install LM Studio from lmstudio.ai\nOpen LM Studio and download a model from the Discover tab\nGo to Local Server and click Start Server\n\nThe server starts at http://localhost:1234/v1 by default. NeuroLink auto-discovers the currently loaded model via /v1/models — you do not need to specify a model name.","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Prerequisites","lvl3":""}},
@@ -6053,7 +6053,7 @@
 {"objectID":"1637c68ac1e9cbfce5f16fd46aaa8835701c2f1430482c8fa9910e486a7bb625","title":"Verification status","url":"/docs/getting-started/providers/novita#verification-status","content":"Tier-2 onboarding requires evidence before a provider is accepted, and\npnpm run verify:provider-onboarding gates it in CI. This is what the\ncatalog records for Novita AI:\n\n| Probe                 | Result                                                                                                                                                                                                                                                                                                                                     |\n| --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| Roster                | authenticated GET /openai/v1/models, HTTP 200, 2026-09-05                                                                                                                                                                                                                                                                                  |\n| Auth rejection        | HTTP 401 (FAILED_TO_AUTH), 2026-09-05                                                                                                                                                                                                                                                                                                    |\n| Live capability sweep | 2026-09-05, probed against the default model. Chat, streaming, and a real structured tool call all passed. response_format: json_object succeeded both alone and combined with tools in the same request — confirmed at the SDK level, which is why structuredOutputWithTools is true for this provider, unlike Friendli or Morph. |","hierarchy":{"lvl0":"Getting Started","lvl1":"Novita AI Provider Guide","lvl2":"Verification status","lvl3":""}},
 {"objectID":"a28a46f2a803a788421fbf99c39dcb97d33871e99a7dc45807a98ddce3e15589","title":"Troubleshooting","url":"/docs/getting-started/providers/novita#troubleshooting","content":"| Symptom                                         | Cause                                                                                                | Fix                                                                                             |\n| ----------------------------------------------- | ---------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------- |\n| FAILED_TO_AUTH                                | NOVITA_API_KEY unset, wrong, or not sk_-prefixed                                                 | Rotate the key at https://novita.ai/settings/key-management                                     |\n| MODEL_NOT_FOUND                               | The roster changed since 2026-09-05                                                                  | Pick a current id from https://novita.ai/models or the authenticated /openai/v1/models roster |\n| Truncated or empty content on the default model | zai-org/glm-5.3-flash is a reasoning model and the catalog default max output is only 4,096 tokens | Raise maxTokens for longer or reasoning-heavy completions                                     |","hierarchy":{"lvl0":"Getting Started","lvl1":"Novita AI Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
 {"objectID":"7ce1eb2bda1d99489069643ba7316d9d1e893babf249024cf111547fbe952f66","title":"See also","url":"/docs/getting-started/providers/novita#see-also","content":"Provider setup overview\nAll providers\nTier-2 onboarding\nProvider feature compatibility","hierarchy":{"lvl0":"Getting Started","lvl1":"Novita AI Provider Guide","lvl2":"See also","lvl3":""}},
-{"objectID":"c4d6bc20fbe9d189291d36b241fffab77fac1dcbe5ff66e1df5248840997c55d","title":"NVIDIA NIM Provider Guide","url":"/docs/getting-started/providers/nvidia-nim","content":"NVIDIA NIM Provider Guide\n\nHundreds of optimised AI models on NVIDIA's GPU-accelerated inference platform — or your own self-hosted NIM deployment\n\nOverview\n\nNVIDIA NIM (NVIDIA Inference Microservices) is a managed inference platform that hosts a large catalog of open-weight models — Meta Llama, DeepSeek, Mistral, Microsoft Phi, Google Gemma, and more — all GPU-optimised and served through an OpenAI-compatible API. You can also point NeuroLink at a self-hosted NIM cluster by overriding the base URL.\n\nKey Facts\nHosted base URL: https://integrate.api.nvidia.com/v1\nProtocol: OpenAI-compatible (/v1/chat/completions)\nVision: Yes, on supported models (Llama 3.2 Vision, etc.)\nReasoning: Yes, on Nemotron and DeepSeek-R1 variants\nStreaming: Supported\nTool calling: Supported on most models\nSelf-hosting: Override NVIDIA_NIM_BASE_URL to point at a private NIM cluster\n\nNIM-Specific Extras\n\nNIM supports additional generation parameters beyond the standard OpenAI surface: top_k, min_p, repetition_penalty, min_tokens, and per-model chat_template overrides. The NeuroLink provider automatically passes these via the providerOptions.openai.body mechanism. If a model rejects an unsupported parameter with HTTP 400, the provider retries the request with that parameter stripped.\n\nQuick Start\nGet an API Key\n\nSign up at https://build.nvidia.com and create an API key under API Keys.\nConfigure Environment\n\nAdd to your .env file:\nInstall NeuroLink\nGenerate Your First Response\n\nSupported Models\n\nNIM hosts hundreds of models. NeuroLink ships with these popular models pre-enumerated:\n\nOpenAI gpt-oss (default)\n\n| Model ID             | Context | Vision | Reasoning |\n| -------------------- | ------- | ------ | --------- |\n| openai/gpt-oss-20b | 128K    | No     | No        |\n\nMeta Llama\n\n| Model ID                             | Context | Vision | Reasoning |\n| ------------------------------------ | ------- | ------ | --------- |\n| meta/llama-3.3-70b-instruct        | 128K    | No     | No        |\n| meta/llama-3.1-405b-instruct       | 128K    | No     | No        |\n| meta/llama-3.1-70b-instruct        | 128K    | No     | No        |\n| meta/llama-3.2-90b-vision-instruct | 128K    | Yes    | No        |\n| meta/llama-3.2-11b-vision-instruct | 128K    | Yes    | No        |\n\nNVIDIA Nemotron (Reasoning)\n\n| Model ID                                 | Context | Vision | Reasoning |\n| ---------------------------------------- | ------- | ------ | --------- |\n| nvidia/llama-3.3-nemotron-super-49b-v1 | 128K    | No     | Yes       |\n| nvidia/llama-3.1-nemotron-nano-8b-v1   | 128K    | No     | Yes       |\n| nvidia/llama-3.1-nemotron-70b-instruct | 128K    | No     | Yes       |\n\nDeepSeek (Hosted on NIM)\n\n| Model ID                                    | Context | Vision | Reasoning |\n| ------------------------------------------- | ------- | ------ | --------- |\n| deepseek-ai/deepseek-r1                   | 128K    | No     | Yes       |\n| deepseek-ai/deepseek-r1-distill-llama-70b | 128K    | No     | Yes       |\n\nOther Models\n\n| Model ID                                | Context | Notes            |\n| --------------------------------------- | ------- | ---------------- |\n| mistralai/mixtral-8x22b-instruct-v0.1 | 64K     | Large MoE        |\n| mistralai/mixtral-8x7b-instruct-v0.1  | 32K     | Efficient MoE    |\n| microsoft/phi-4                       | 16K     | Compact, capable |\n| google/gemma-3-27b-it                 | 128K    | Google Gemma     |\n\nAvailability, checked 2026-10-02. NVIDIA's GET https://integrate.api.nvidia.com/v1/models did not list meta/llama-3.3-70b-instruct, meta/llama-3.1-70b-instruct, deepseek-ai/deepseek-r1-distill-llama-70b or google/gemma-3-27b-it. The NvidiaNimModels enum records a probe on 2026-08-26 in which these answered \"no longer available\", and keeps the members so existing code compiles. meta/llama-3.1-405b-instruct, deepseek-ai/deepseek-r1, mistralai/mixtral-8x22b-instruct-v0.1, mistralai/mixtral-8x7b-instruct-v0.1 and microsoft/phi-4 were also absent from that list on that date, and meta/llama-3.2-90b-vision-instruct was listed.\n\nBrowse the full catalog at https://build.nvidia.com/models. You can pass any model ID via --model or model: — NIM returns 404 for IDs that are not in the catalog.\n\nSDK Usage\n\nBasic Generation\n\nUsing a Specific Model\n\nReasoning with thinkingLevel\n\nReasoning-capable models (Nemotron, DeepSeek-R1) accept a thinking flag via NIM's chat_template_kwargs. Pass thinkingLevel to activate it:\n\nLevels: minimal (no thinking) | low | medium | high\n\nIf the model does not support chat_template_kwargs.thinking, the provider automatically retries without it.\n\nStreaming\n\nPer-Call Credential Override\n\nFor self-hosted NIM clusters, override the base URL per call:\n\nCLI Usage\n\nBasic Commands\n\nProvider Aliases\n\n| Alias        | Example                 |\n| ------------ | ----------------------- |\n| nvidia-nim | --provider nvidia-nim |\n| nvidia     | --provider nvidia     |\n| nim        | --provider nim        |\n\nC","hierarchy":{"lvl0":"Getting Started","lvl1":"NVIDIA NIM Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"c4d6bc20fbe9d189291d36b241fffab77fac1dcbe5ff66e1df5248840997c55d","title":"NVIDIA NIM Provider Guide","url":"/docs/getting-started/providers/nvidia-nim","content":"NVIDIA NIM Provider Guide\n\nHundreds of optimised AI models on NVIDIA's GPU-accelerated inference platform — or your own self-hosted NIM deployment\n\nOverview\n\nNVIDIA NIM (NVIDIA Inference Microservices) is a managed inference platform that hosts a large catalog of open-weight models — Meta Llama, DeepSeek, Mistral, Microsoft Phi, Google Gemma, and more — all GPU-optimised and served through an OpenAI-compatible API. You can also point NeuroLink at a self-hosted NIM cluster by overriding the base URL.\n\nKey Facts\nHosted base URL: https://integrate.api.nvidia.com/v1\nProtocol: OpenAI-compatible (/v1/chat/completions)\nVision: Yes, on supported models (Llama 3.2 Vision, etc.)\nReasoning: Yes, on Nemotron and DeepSeek-R1 variants\nStreaming: Supported\nTool calling: Supported on most models\nSelf-hosting: Override NVIDIA_NIM_BASE_URL to point at a private NIM cluster\n\nNIM-Specific Extras\n\nNIM supports additional generation parameters beyond the standard OpenAI surface: top_k, min_p, repetition_penalty, min_tokens, and per-model chat_template overrides. The NeuroLink provider automatically passes these via the providerOptions.openai.body mechanism. If a model rejects an unsupported parameter with HTTP 400, the provider retries the request with that parameter stripped.\n\nQuick Start\nGet an API Key\n\nSign up at https://build.nvidia.com and create an API key under API Keys.\nConfigure Environment\n\nAdd to your .env file:\nInstall NeuroLink\nGenerate Your First Response\n\nSupported Models\n\nNIM hosts hundreds of models. NeuroLink ships with these popular models pre-enumerated:\n\nOpenAI gpt-oss (default)\n\n| Model ID             | Context | Vision | Reasoning |\n| -------------------- | ------- | ------ | --------- |\n| openai/gpt-oss-20b | 128K    | No     | No        |\n\nMeta Llama\n\n| Model ID                             | Context | Vision | Reasoning |\n| ------------------------------------ | ------- | ------ | --------- |\n| meta/llama-3.3-70b-instruct        | 128K    | No     | No        |\n| meta/llama-3.1-405b-instruct       | 128K    | No     | No        |\n| meta/llama-3.1-70b-instruct        | 128K    | No     | No        |\n| meta/llama-3.2-90b-vision-instruct | 128K    | Yes    | No        |\n| meta/llama-3.2-11b-vision-instruct | 128K    | Yes    | No        |\n\nNVIDIA Nemotron (Reasoning)\n\n| Model ID                                 | Context | Vision | Reasoning |\n| ---------------------------------------- | ------- | ------ | --------- |\n| nvidia/llama-3.3-nemotron-super-49b-v1 | 128K    | No     | Yes       |\n| nvidia/llama-3.1-nemotron-nano-8b-v1   | 128K    | No     | Yes       |\n| nvidia/llama-3.1-nemotron-70b-instruct | 128K    | No     | Yes       |\n\nDeepSeek (Hosted on NIM)\n\n| Model ID                                    | Context | Vision | Reasoning |\n| ------------------------------------------- | ------- | ------ | --------- |\n| deepseek-ai/deepseek-r1                   | 128K    | No     | Yes       |\n| deepseek-ai/deepseek-r1-distill-llama-70b | 128K    | No     | Yes       |\n\nOther Models\n\n| Model ID                                | Context | Notes            |\n| --------------------------------------- | ------- | ---------------- |\n| mistralai/mixtral-8x22b-instruct-v0.1 | 64K     | Large MoE        |\n| mistralai/mixtral-8x7b-instruct-v0.1  | 32K     | Efficient MoE    |\n| microsoft/phi-4                       | 16K     | Compact, capable |\n| google/gemma-3-27b-it                 | 128K    | Google Gemma     |\n\nAvailability, checked 2026-10-24. NVIDIA's GET https://integrate.api.nvidia.com/v1/models lists openai/gpt-oss-20b, meta/llama-3.2-90b-vision-instruct, meta/llama-3.2-11b-vision-instruct and nvidia/llama-3.1-nemotron-70b-instruct from the tables above, and none of the others. A chat request to meta/llama-3.3-70b-instruct or meta/llama-3.1-70b-instruct answers HTTP 410, \"has reached its end of life on 2026-08-26T09:00:00Z and is no longer available\"; nvidia/llama-3.3-nemotron-super-49b-v1 and mistralai/mixtral-8x22b-instruct-v0.1 also answer 410, and deepseek-ai/deepseek-r1 and meta/llama-3.1-405b-instruct answer 404. nvidia/llama-3.1-nemotron-70b-instruct is listed but answered 404 (\"not found for account\") to the key used for the check. openai/gpt-oss-20b and meta/llama-3.2-11b-vision-instruct each answered a plain request and a tool-calling request. The NvidiaNimModels enum keeps the retired members so existing code compiles.\n\nBrowse the full catalog at https://build.nvidia.com/models. You can pass any model ID via --model or model: — NIM returns 404 for IDs that are not in the catalog.\n\nSDK Usage\n\nBasic Generation\n\nUsing a Specific Model\n\nReasoning with thinkingLevel\n\nReasoning-capable models (Nemotron, DeepSeek-R1) accept a thinking flag via NIM's chat_template_kwargs. Pass thinkingLevel to activate it:\n\nLevels: minimal (no thinking) | low | medium | high\n\nIf the model does not support chat_template_kwargs.thinking, the provider automatically retries without it.\n\nStreaming\n\nPer-Call Credential Override\n","hierarchy":{"lvl0":"Getting Started","lvl1":"NVIDIA NIM Provider Guide","lvl2":"","lvl3":""}},
 {"objectID":"b3c7e6b9de265c001fb3ea1118f2467719f7d5d7b47d0d1219803161adaa97f3","title":"NVIDIA NIM Provider Guide","url":"/docs/getting-started/providers/nvidia-nim#nvidia-nim-provider-guide","content":"Hundreds of optimised AI models on NVIDIA's GPU-accelerated inference platform — or your own self-hosted NIM deployment","hierarchy":{"lvl0":"Getting Started","lvl1":"NVIDIA NIM Provider Guide","lvl2":"NVIDIA NIM Provider Guide","lvl3":""}},
 {"objectID":"bdd47b6d8dc71c8c6e099e6aaf6d4b1322ee018e437203f0f8213316ead4bc6a","title":"Overview","url":"/docs/getting-started/providers/nvidia-nim#overview","content":"NVIDIA NIM (NVIDIA Inference Microservices) is a managed inference platform that hosts a large catalog of open-weight models — Meta Llama, DeepSeek, Mistral, Microsoft Phi, Google Gemma, and more — all GPU-optimised and served through an OpenAI-compatible API. You can also point NeuroLink at a self-hosted NIM cluster by overriding the base URL.","hierarchy":{"lvl0":"Getting Started","lvl1":"NVIDIA NIM Provider Guide","lvl2":"Overview","lvl3":""}},
 {"objectID":"70e960324b4417bd885aed19e36a44abbedba28c263ff2bf2e6024c995e0915d","title":"Key Facts","url":"/docs/getting-started/providers/nvidia-nim#key-facts","content":"Hosted base URL: https://integrate.api.nvidia.com/v1\nProtocol: OpenAI-compatible (/v1/chat/completions)\nVision: Yes, on supported models (Llama 3.2 Vision, etc.)\nReasoning: Yes, on Nemotron and DeepSeek-R1 variants\nStreaming: Supported\nTool calling: Supported on most models\nSelf-hosting: Override NVIDIA_NIM_BASE_URL to point at a private NIM cluster","hierarchy":{"lvl0":"Getting Started","lvl1":"NVIDIA NIM Provider Guide","lvl2":"Key Facts","lvl3":""}},
@@ -6067,7 +6067,7 @@
 {"objectID":"041d61fa62afb3ac253f977f945401de38379d0f20f40075103a0fa368137747","title":"Meta Llama","url":"/docs/getting-started/providers/nvidia-nim#meta-llama","content":"| Model ID                             | Context | Vision | Reasoning |\n| ------------------------------------ | ------- | ------ | --------- |\n| meta/llama-3.3-70b-instruct        | 128K    | No     | No        |\n| meta/llama-3.1-405b-instruct       | 128K    | No     | No        |\n| meta/llama-3.1-70b-instruct        | 128K    | No     | No        |\n| meta/llama-3.2-90b-vision-instruct | 128K    | Yes    | No        |\n| meta/llama-3.2-11b-vision-instruct | 128K    | Yes    | No        |","hierarchy":{"lvl0":"Getting Started","lvl1":"NVIDIA NIM Provider Guide","lvl2":"Meta Llama","lvl3":""}},
 {"objectID":"3c188653cca3eebd5cc90f43252ad42029a4fa888bfb2b470139e4e0db08e26a","title":"NVIDIA Nemotron (Reasoning)","url":"/docs/getting-started/providers/nvidia-nim#nvidia-nemotron-reasoning","content":"| Model ID                                 | Context | Vision | Reasoning |\n| ---------------------------------------- | ------- | ------ | --------- |\n| nvidia/llama-3.3-nemotron-super-49b-v1 | 128K    | No     | Yes       |\n| nvidia/llama-3.1-nemotron-nano-8b-v1   | 128K    | No     | Yes       |\n| nvidia/llama-3.1-nemotron-70b-instruct | 128K    | No     | Yes       |","hierarchy":{"lvl0":"Getting Started","lvl1":"NVIDIA NIM Provider Guide","lvl2":"NVIDIA Nemotron (Reasoning)","lvl3":""}},
 {"objectID":"4d9aca0894a65a52648a73478e1c73b487411326cf63e05eb8159fd8fef0c5aa","title":"DeepSeek (Hosted on NIM)","url":"/docs/getting-started/providers/nvidia-nim#deepseek-hosted-on-nim","content":"| Model ID                                    | Context | Vision | Reasoning |\n| ------------------------------------------- | ------- | ------ | --------- |\n| deepseek-ai/deepseek-r1                   | 128K    | No     | Yes       |\n| deepseek-ai/deepseek-r1-distill-llama-70b | 128K    | No     | Yes       |","hierarchy":{"lvl0":"Getting Started","lvl1":"NVIDIA NIM Provider Guide","lvl2":"DeepSeek (Hosted on NIM)","lvl3":""}},
-{"objectID":"8eccc475db8aa2e29bd49cd7c0ecb93be5b813979af07749f0c218abe7a71bd8","title":"Other Models","url":"/docs/getting-started/providers/nvidia-nim#other-models","content":"| Model ID                                | Context | Notes            |\n| --------------------------------------- | ------- | ---------------- |\n| mistralai/mixtral-8x22b-instruct-v0.1 | 64K     | Large MoE        |\n| mistralai/mixtral-8x7b-instruct-v0.1  | 32K     | Efficient MoE    |\n| microsoft/phi-4                       | 16K     | Compact, capable |\n| google/gemma-3-27b-it                 | 128K    | Google Gemma     |\n\nAvailability, checked 2026-10-02. NVIDIA's GET https://integrate.api.nvidia.com/v1/models did not list meta/llama-3.3-70b-instruct, meta/llama-3.1-70b-instruct, deepseek-ai/deepseek-r1-distill-llama-70b or google/gemma-3-27b-it. The NvidiaNimModels enum records a probe on 2026-08-26 in which these answered \"no longer available\", and keeps the members so existing code compiles. meta/llama-3.1-405b-instruct, deepseek-ai/deepseek-r1, mistralai/mixtral-8x22b-instruct-v0.1, mistralai/mixtral-8x7b-instruct-v0.1 and microsoft/phi-4 were also absent from that list on that date, and meta/llama-3.2-90b-vision-instruct was listed.\n\nBrowse the full catalog at https://build.nvidia.com/models. You can pass any model ID via --model or model: — NIM returns 404 for IDs that are not in the catalog.","hierarchy":{"lvl0":"Getting Started","lvl1":"NVIDIA NIM Provider Guide","lvl2":"Other Models","lvl3":""}},
+{"objectID":"8eccc475db8aa2e29bd49cd7c0ecb93be5b813979af07749f0c218abe7a71bd8","title":"Other Models","url":"/docs/getting-started/providers/nvidia-nim#other-models","content":"| Model ID                                | Context | Notes            |\n| --------------------------------------- | ------- | ---------------- |\n| mistralai/mixtral-8x22b-instruct-v0.1 | 64K     | Large MoE        |\n| mistralai/mixtral-8x7b-instruct-v0.1  | 32K     | Efficient MoE    |\n| microsoft/phi-4                       | 16K     | Compact, capable |\n| google/gemma-3-27b-it                 | 128K    | Google Gemma     |\n\nAvailability, checked 2026-10-24. NVIDIA's GET https://integrate.api.nvidia.com/v1/models lists openai/gpt-oss-20b, meta/llama-3.2-90b-vision-instruct, meta/llama-3.2-11b-vision-instruct and nvidia/llama-3.1-nemotron-70b-instruct from the tables above, and none of the others. A chat request to meta/llama-3.3-70b-instruct or meta/llama-3.1-70b-instruct answers HTTP 410, \"has reached its end of life on 2026-08-26T09:00:00Z and is no longer available\"; nvidia/llama-3.3-nemotron-super-49b-v1 and mistralai/mixtral-8x22b-instruct-v0.1 also answer 410, and deepseek-ai/deepseek-r1 and meta/llama-3.1-405b-instruct answer 404. nvidia/llama-3.1-nemotron-70b-instruct is listed but answered 404 (\"not found for account\") to the key used for the check. openai/gpt-oss-20b and meta/llama-3.2-11b-vision-instruct each answered a plain request and a tool-calling request. The NvidiaNimModels enum keeps the retired members so existing code compiles.\n\nBrowse the full catalog at https://build.nvidia.com/models. You can pass any model ID via --model or model: — NIM returns 404 for IDs that are not in the catalog.","hierarchy":{"lvl0":"Getting Started","lvl1":"NVIDIA NIM Provider Guide","lvl2":"Other Models","lvl3":""}},
 {"objectID":"13a92a3d0f9f1c15c2bb97769daa214d7a883699f08b4789ce05ba89f0b1724b","title":"Basic Generation","url":"/docs/getting-started/providers/nvidia-nim#basic-generation","content":"Basic Generation","hierarchy":{"lvl0":"Getting Started","lvl1":"NVIDIA NIM Provider Guide","lvl2":"Basic Generation","lvl3":""}},
 {"objectID":"3bc7919c7e5bb6f759acdf2b78470d89c4ec5fc0d637553c2c123240b504a105","title":"Using a Specific Model","url":"/docs/getting-started/providers/nvidia-nim#using-a-specific-model","content":"Using a Specific Model","hierarchy":{"lvl0":"Getting Started","lvl1":"NVIDIA NIM Provider Guide","lvl2":"Using a Specific Model","lvl3":""}},
 {"objectID":"def6f89a4845940b499d11b73fb1b4c4aee4bf4315cfbf3828168d4b874c3f39","title":"Reasoning with thinkingLevel","url":"/docs/getting-started/providers/nvidia-nim#reasoning-with-thinkinglevel","content":"Reasoning-capable models (Nemotron, DeepSeek-R1) accept a thinking flag via NIM's chat_template_kwargs. Pass thinkingLevel to activate it:\n\nLevels: minimal (no thinking) | low | medium | high\n\nIf the model does not support chat_template_kwargs.thinking, the provider automatically retries without it.","hierarchy":{"lvl0":"Getting Started","lvl1":"NVIDIA NIM Provider Guide","lvl2":"Reasoning with thinkingLevel","lvl3":""}},
@@ -6081,6 +6081,7 @@
 {"objectID":"e113acee1e904cde2e3295ebbb99df56e1d4d712cf149f774c8fbaad6ada6770","title":"\"Invalid NVIDIA NIM API key\"","url":"/docs/getting-started/providers/nvidia-nim#invalid-nvidia-nim-api-key","content":"The NVIDIA_NIM_API_KEY is missing, expired, or incorrect.\n\nGet or rotate keys at https://build.nvidia.com/settings/api-keys.","hierarchy":{"lvl0":"Getting Started","lvl1":"NVIDIA NIM Provider Guide","lvl2":"\"Invalid NVIDIA NIM API key\"","lvl3":""}},
 {"objectID":"25669258e3b272543a86496e295868082d0146aff134a84ead2bdf65fccb3ffb","title":"\"NVIDIA NIM rate limit exceeded\"","url":"/docs/getting-started/providers/nvidia-nim#nvidia-nim-rate-limit-exceeded","content":"Your account has hit its request-per-minute or token-per-day limit. Upgrade your account, reduce request frequency, or implement backoff. Check your current usage at https://build.nvidia.com/usage.","hierarchy":{"lvl0":"Getting Started","lvl1":"NVIDIA NIM Provider Guide","lvl2":"\"NVIDIA NIM rate limit exceeded\"","lvl3":""}},
 {"objectID":"8fa05f7794655a8b226d68b36d26031af67d19af32b9435a02357b7f8e719862","title":"\"NVIDIA NIM model not available\"","url":"/docs/getting-started/providers/nvidia-nim#nvidia-nim-model-not-available","content":"The model ID is not in the NIM catalog, or your account tier does not have access.\n\nUse the exact model ID shown on the model's page (e.g., openai/gpt-oss-20b).","hierarchy":{"lvl0":"Getting Started","lvl1":"NVIDIA NIM Provider Guide","lvl2":"\"NVIDIA NIM model not available\"","lvl3":""}},
+{"objectID":"6bc455b9dba112ad4d4cb452dc286e558ef9098ae2c16dd0048d985ed1edad6f","title":"HTTP 410 \"has reached its end of life\"","url":"/docs/getting-started/providers/nvidia-nim#http-410-has-reached-its-end-of-life","content":"The request named a model NVIDIA has retired, for example meta/llama-3.1-70b-instruct or meta/llama-3.3-70b-instruct (retired 2026-08-26). If you did not pass model:, look for a stale NVIDIA_NIM_MODEL in your .env or shell: it takes precedence over the built-in default (openai/gpt-oss-20b). Remove it or set it to a model from the current catalog.","hierarchy":{"lvl0":"Getting Started","lvl1":"NVIDIA NIM Provider Guide","lvl2":"HTTP 410 \"has reached its end of life\"","lvl3":""}},
 {"objectID":"34d171d7ade8a31dfc31588bfccef6e920cd37a662a53089aabb5983a7d2694c","title":"\"NVIDIA NIM quota exceeded\"","url":"/docs/getting-started/providers/nvidia-nim#nvidia-nim-quota-exceeded","content":"Account-level token or compute quota reached. Check your NIM dashboard.","hierarchy":{"lvl0":"Getting Started","lvl1":"NVIDIA NIM Provider Guide","lvl2":"\"NVIDIA NIM quota exceeded\"","lvl3":""}},
 {"objectID":"0697a2c79b09552d2abfdc5d788f32dfeec83add6b8a40e67389ef43b6f77ac9","title":"HTTP 400 with reasoning_budget or chat_template in the error","url":"/docs/getting-started/providers/nvidia-nim#http-400-with-reasoning_budget-or-chat_template-in-the-error","content":"The model does not support one of the NIM-specific extras. The provider automatically retries without the rejected parameter. If you see this error surfaced, it means the second attempt also failed — check the rest of the error message for the root cause.","hierarchy":{"lvl0":"Getting Started","lvl1":"NVIDIA NIM Provider Guide","lvl2":"HTTP 400 with reasoning_budget or chat_template in the error","lvl3":""}},
 {"objectID":"403e25d3806bf5242a71a8e510fac16e068f907380e7f22d15d2393cbf3f28f4","title":"Thinking level has no visible effect","url":"/docs/getting-started/providers/nvidia-nim#thinking-level-has-no-visible-effect","content":"Not all models support chat_template_kwargs.thinking. If the model rejects the parameter, the provider retries the request without it and produces a normal (non-reasoning) response. Use a Nemotron or DeepSeek-R1 model for guaranteed reasoning support.","hierarchy":{"lvl0":"Getting Started","lvl1":"NVIDIA NIM Provider Guide","lvl2":"Thinking level has no visible effect","lvl3":""}},
@@ -9765,7 +9766,7 @@
 {"objectID":"5850b5e6ab599e2c9e2952653e0db0616ccd777c908edd1b43dd4381d0d1eab7","title":"12. OpenAI Compatible","url":"/docs/reference/provider-comparison#12-openai-compatible","content":"Provider ID: openai-compatible\nDefault Model: Auto-discovered\n\nStrengths:\nWorks with any OpenAI-compatible endpoint\nvLLM, FastChat, LocalAI support\nCustom deployment flexibility\nAuto-discovers available models\n\nWeaknesses:\nCapabilities entirely backend-dependent\nNo standardized capability detection\nConfiguration varies by provider\nAuthentication varies\n\nBest For:\nCustom deployments (vLLM, FastChat)\nInternal model serving\nPrivate cloud deployments\nWhen you control the backend\n\nPricing:\nDepends entirely on backend provider\nSelf-hosted: Infrastructure costs only\nCloud-hosted: Provider-specific pricing","hierarchy":{"lvl0":"Reference","lvl1":"AI Provider Comparison Guide","lvl2":"12. OpenAI Compatible","lvl3":""}},
 {"objectID":"260fb153eca401bd1ca6ed426b7f594aba2907dd9389b79d0bfe62380fc8a7be","title":"13. OpenRouter","url":"/docs/reference/provider-comparison#13-openrouter","content":"Provider ID: openrouter\nDefault Model: anthropic/claude-3-5-sonnet\n\nStrengths:\nAccess to 300+ models from 60+ providers\nMany FREE models available\nAutomatic failover\nUnified API for all models\nCost tracking\n\nWeaknesses:\nTool support varies by model\nVision support varies by model\nCredit-based pricing system\nModel availability can change\n\nBest For:\nAccess to many providers via one API\nCost optimization (free models available)\nRapid prototyping\nWhen you want provider flexibility\n\nPricing:\nFree models available:\nGoogle Gemini 2.0 Flash: FREE\nMeta Llama 3.3 70B: FREE\nQwen models: FREE\nPaid models:\nClaude 3.5 Sonnet: $3.00/$15.00 per 1M tokens\nGPT-4o: $2.50/$10.00 per 1M tokens","hierarchy":{"lvl0":"Reference","lvl1":"AI Provider Comparison Guide","lvl2":"13. OpenRouter","lvl3":""}},
 {"objectID":"e3aa53a228f2eb44916ad3d765c881b2565668588e1c94e1df543232a78413f6","title":"14. DeepSeek","url":"/docs/reference/provider-comparison#14-deepseek","content":"Provider ID: deepseek\nDefault Model: deepseek-chat\nAliases: ds\n\nStrengths:\nVery competitive pricing (among the cheapest frontier-quality models)\ndeepseek-reasoner (R1) — strong open-weight reasoning model\nOpenAI-compatible API — minimal integration overhead\nTool calling supported on both models\n\nWeaknesses:\nNo vision / multimodal support\nCloud-only (data sent to DeepSeek servers in China — consider for compliance)\nNo PDF support\n\nBest For:\nCost-sensitive text and reasoning workloads\nAgentic tool-calling pipelines where budget matters\nExperimenting with open-weight-quality reasoning at low cost\n\nPricing:\ndeepseek-chat (V3): ~$0.14/$0.28 per 1M tokens\ndeepseek-reasoner (R1): ~$0.55/$2.19 per 1M tokens","hierarchy":{"lvl0":"Reference","lvl1":"AI Provider Comparison Guide","lvl2":"14. DeepSeek","lvl3":""}},
-{"objectID":"6e5ecdf1db31b0952ff3e3ab0758af1a084052e528319de6bc88f64cef9c3d97","title":"15. NVIDIA NIM","url":"/docs/reference/provider-comparison#15-nvidia-nim","content":"Provider ID: nvidia-nim\nDefault Model: meta/llama-3.3-70b-instruct\nAliases: nvidia, nim\n\nStrengths:\nAccess to NVIDIA-hosted Llama, Mistral, Nemotron, DeepSeek models\nThinking/reasoning supported on Nemotron-Reasoning and DeepSeek-R1 models\nVision supported on vision-capable models (Phi-3-vision, Llama 3.2 Vision)\nOpenAI-compatible API with NIM-specific extras (top_k, min_p, reasoning_budget)\nGraceful retry on 400 errors — drops unsupported extras automatically\n\nWeaknesses:\nTool and vision capability depends entirely on the specific hosted model\nRequires NVIDIA NGC API key\nNo PDF support\n\nBest For:\nRunning NVIDIA-optimized Llama/Mistral/Nemotron models in the cloud\nReasoning workloads via hosted DeepSeek-R1 or Nemotron\nDevelopers already in the NVIDIA ecosystem (NGC, DGX Cloud)\n\nPricing:\nVaries by model; new accounts receive free credits\nSee https://build.nvidia.com/models for per-model pricing","hierarchy":{"lvl0":"Reference","lvl1":"AI Provider Comparison Guide","lvl2":"15. NVIDIA NIM","lvl3":""}},
+{"objectID":"6e5ecdf1db31b0952ff3e3ab0758af1a084052e528319de6bc88f64cef9c3d97","title":"15. NVIDIA NIM","url":"/docs/reference/provider-comparison#15-nvidia-nim","content":"Provider ID: nvidia-nim\nDefault Model: openai/gpt-oss-20b\nAliases: nvidia, nim\n\nStrengths:\nAccess to NVIDIA-hosted Llama, Mistral, Nemotron, DeepSeek models\nThinking/reasoning supported on Nemotron-Reasoning and DeepSeek-R1 models\nVision supported on vision-capable models (Phi-3-vision, Llama 3.2 Vision)\nOpenAI-compatible API with NIM-specific extras (top_k, min_p, reasoning_budget)\nGraceful retry on 400 errors — drops unsupported extras automatically\n\nWeaknesses:\nTool and vision capability depends entirely on the specific hosted model\nRequires NVIDIA NGC API key\nNo PDF support\n\nBest For:\nRunning NVIDIA-optimized Llama/Mistral/Nemotron models in the cloud\nReasoning workloads via hosted DeepSeek-R1 or Nemotron\nDevelopers already in the NVIDIA ecosystem (NGC, DGX Cloud)\n\nPricing:\nVaries by model; new accounts receive free credits\nSee https://build.nvidia.com/models for per-model pricing","hierarchy":{"lvl0":"Reference","lvl1":"AI Provider Comparison Guide","lvl2":"15. NVIDIA NIM","lvl3":""}},
 {"objectID":"3d848b89e6f368d83d5eb4c1857ca90c4fa81391f9da441b10fb82227632408f","title":"16. LM Studio","url":"/docs/reference/provider-comparison#16-lm-studio","content":"Provider ID: lm-studio\nDefault Model: Auto-discovered from running server\nAliases: lmstudio, lms\n\nStrengths:\nCompletely FREE (local execution via LM Studio desktop app)\nMaximum privacy — no data sent to cloud\nAuto-discovers the currently loaded model via /v1/models\nVision supported on compatible models (LLaVA, Llama 3.2 Vision, Qwen-VL, etc.)\nTool calling supported on compatible models\n\nWeaknesses:\nRequires LM Studio app and a loaded model\nModel quality and capability depend entirely on what is loaded\nNo PDF support\nSmall local models may give inconsistent structured output\n\nBest For:\nPrivacy-critical local inference\nOffline / air-gapped environments\nDevelopment and experimentation without cloud costs\nTesting multiple open-weight models via a GUI\n\nPricing:\nFREE (hardware costs only)\nRequires local GPU for best performance","hierarchy":{"lvl0":"Reference","lvl1":"AI Provider Comparison Guide","lvl2":"16. LM Studio","lvl3":""}},
 {"objectID":"a0f05ec8e14d9e4fb69779c0c25f1e732ae384b506c5be585c5089cd457f293f","title":"17. llama.cpp","url":"/docs/reference/provider-comparison#17-llamacpp","content":"Provider ID: llamacpp\nDefault Model: Auto-discovered from running llama-server\nAliases: llama.cpp, llama-cpp\n\nStrengths:\nCompletely FREE (local execution via llama-server)\nMaximum privacy — no data sent to cloud\nGGUF model support — run quantized models on CPU or GPU\nAuto-discovers loaded model via /v1/models\nVision supported on compatible models (LLaVA, Llama 3.2 Vision)\nTool calling supported when server started with --jinja flag\n\nWeaknesses:\nRequires building / downloading llama-server and a GGUF model\nTool calling requires --jinja flag at server startup\nModel quality depends on the GGUF model loaded\nNo PDF support\nSmall local models may give inconsistent structured output\n\nBest For:\nMaximum privacy and air-gapped deployments\nCPU inference without a GPU\nRunning heavily quantized models at low resource cost\nPower users who want direct control over model serving\n\nPricing:\nFREE (hardware costs only)\nNo API costs or rate limits","hierarchy":{"lvl0":"Reference","lvl1":"AI Provider Comparison Guide","lvl2":"17. llama.cpp","lvl3":""}},
 {"objectID":"7a70d0d5fafc012db75fd708bf54e3db3a35a71ce61eb67049e87218bbc874d4","title":"Voice Providers","url":"/docs/reference/provider-comparison#voice-providers","content":"Voice providers handle audio I/O and are distinct from LLM text-generation providers. They are categorised by function: Text-to-Speech (TTS), Speech-to-Text (STT), and Realtime (bidirectional audio over WebSocket).\n\n| Provider            | Type     | Protocol         | Streaming | Formats                                               | Auth                                               |\n| ------------------- | -------- | ---------------- | --------- | ----------------------------------------------------- | -------------------------------------------------- |\n| google-ai (TTS) | TTS      | REST (gRPC SDK)  | No        | MP3, WAV, OGG                                         | Service Account (GOOGLE_APPLICATION_CREDENTIALS) |\n| openai-tts      | TTS      | REST             | No        | MP3, WAV, OGG, Opus                                   | API Key                                            |\n| elevenlabs      | TTS      | REST             | No        | MP3, WAV (PCM), Opus                                  | API Key                                            |\n| azure-tts       | TTS      | REST             | No        | MP3, WAV (PCM), Opus                                  | API Key + Region                                   |\n| whisper         | STT      | REST             | No        | WAV, MP3, M4A, FLAC, OGG, Opus, WebM, MP4, MPEG, MPGA | API Key                                            |\n| google-stt      | STT      | REST             | No        | WAV, FLAC, MP3, OGG                                   | API Key or Service Account                         |\n| deepgram        | STT      | REST + WebSocket | Yes       | WAV, MP3, OGG, FLAC                                   | API Key                                            |\n| azure-stt       | STT      | REST             | No        | WAV¹, OGG, Opus                                       | API Key + Region                                   |\n| openai-realtime | Realtime | WebSocket        | Yes       | PCM16,","hierarchy":{"lvl0":"Reference","lvl1":"AI Provider Comparison Guide","lvl2":"Voice Providers","lvl3":""}},
@@ -9843,7 +9844,7 @@
 {"objectID":"adefcedd575b72009c4bc0f61997c4250040929f014824c6c6cdbbe7fa0ef1e6","title":"Enterprise Production","url":"/docs/reference/provider-selection#enterprise-production","content":"Recommended Stack:\n\nEnterprise Requirements Checklist:\n[x] SLA guarantees (99.9%+)\n[x] HIPAA/SOC2 compliance\n[x] Multi-region deployment\n[x] Provider failover strategy\n[x] Cost monitoring and alerts","hierarchy":{"lvl0":"Reference","lvl1":"Provider Selection Guide","lvl2":"Enterprise Production","lvl3":""}},
 {"objectID":"00ead7f5ba563f9adeac903fd53da014cebdb61e277745108608ac4774e49f57","title":"Research and Analysis","url":"/docs/reference/provider-selection#research-and-analysis","content":"Recommended Stack:","hierarchy":{"lvl0":"Reference","lvl1":"Provider Selection Guide","lvl2":"Research and Analysis","lvl3":""}},
 {"objectID":"1272876f7ecd7e162c7ae353a481e9a18a6d43fa20e84116552e1ac6b188cea8","title":"Cost-Efficient Reasoning (DeepSeek)","url":"/docs/reference/provider-selection#cost-efficient-reasoning-deepseek","content":"Choose DeepSeek when you need frontier-quality reasoning at a fraction of the cost of Anthropic or OpenAI.\nWhen to choose: Text-only agentic workflows, chain-of-thought reasoning tasks, budget-constrained production.\nProvider ID: deepseek\nKey models: deepseek-chat (V3 — general purpose), deepseek-reasoner (R1 — reasoning)\nNot suitable for: Vision, PDF, or image processing tasks.\nCredential needed: DEEPSEEK_API_KEY (get one at https://platform.deepseek.com)","hierarchy":{"lvl0":"Reference","lvl1":"Provider Selection Guide","lvl2":"Cost-Efficient Reasoning (DeepSeek)","lvl3":""}},
-{"objectID":"a91dc684aba34ed7cc14c808212a1a4ccc3bf679374984bb60818d50498bae4f","title":"NVIDIA-Hosted Models (NVIDIA NIM)","url":"/docs/reference/provider-selection#nvidia-hosted-models-nvidia-nim","content":"Choose NVIDIA NIM when you want NVIDIA-curated hosted inference — Llama, Nemotron, Mistral, and DeepSeek-R1 — accessed via an NVIDIA API key.\nWhen to choose: You want Llama 3.x or Nemotron models served at scale; you need thinking/reasoning via hosted DeepSeek-R1 or Nemotron-Reasoning; you are already an NGC customer.\nProvider ID: nvidia-nim\nKey models: meta/llama-3.3-70b-instruct, nvidia/nemotron-4-340b-instruct, DeepSeek-R1 variants\nVision: Available on select models (Phi-3-vision, Llama 3.2 Vision); check https://build.nvidia.com/models.\nNot suitable for: PDF processing; vision on non-vision models.\nCredential needed: NVIDIA_NIM_API_KEY (get one at https://build.nvidia.com/settings/api-keys)","hierarchy":{"lvl0":"Reference","lvl1":"Provider Selection Guide","lvl2":"NVIDIA-Hosted Models (NVIDIA NIM)","lvl3":""}},
+{"objectID":"a91dc684aba34ed7cc14c808212a1a4ccc3bf679374984bb60818d50498bae4f","title":"NVIDIA-Hosted Models (NVIDIA NIM)","url":"/docs/reference/provider-selection#nvidia-hosted-models-nvidia-nim","content":"Choose NVIDIA NIM when you want NVIDIA-curated hosted inference — Llama, Nemotron, Mistral, and DeepSeek-R1 — accessed via an NVIDIA API key.\nWhen to choose: You want Llama 3.x or Nemotron models served at scale; you need thinking/reasoning via hosted DeepSeek-R1 or Nemotron-Reasoning; you are already an NGC customer.\nProvider ID: nvidia-nim\nKey models: openai/gpt-oss-20b (default), nvidia/nemotron-4-340b-instruct, DeepSeek-R1 variants\nVision: Available on select models (Phi-3-vision, Llama 3.2 Vision); check https://build.nvidia.com/models.\nNot suitable for: PDF processing; vision on non-vision models.\nCredential needed: NVIDIA_NIM_API_KEY (get one at https://build.nvidia.com/settings/api-keys)","hierarchy":{"lvl0":"Reference","lvl1":"Provider Selection Guide","lvl2":"NVIDIA-Hosted Models (NVIDIA NIM)","lvl3":""}},
 {"objectID":"cc36677fe4f4c550b7760d8c16ffddec196c19f2498027b05576b3ba4fa37105","title":"Local Inference via LM Studio","url":"/docs/reference/provider-selection#local-inference-via-lm-studio","content":"Choose LM Studio when you want a desktop GUI for managing and running local models, with zero cloud cost and maximum privacy.\nWhen to choose: You want a GUI to browse, download, and switch models; you need local inference without managing llama-server manually; vision models like LLaVA or Qwen-VL are attractive.\nProvider ID: lm-studio\nModel: Auto-discovered from the loaded model (or pass an explicit model name).\nDefault base URL: http://localhost:1234/v1\nNot suitable for: Production at scale (single machine); PDF processing.\nSetup: Download LM Studio, load a model, click \"Start Server\".","hierarchy":{"lvl0":"Reference","lvl1":"Provider Selection Guide","lvl2":"Local Inference via LM Studio","lvl3":""}},
 {"objectID":"72e9be8e5b8e718308f0fe7360bcba27aae8b42fffa35be62d9a4ef188c470ae","title":"Local Inference via llama.cpp","url":"/docs/reference/provider-selection#local-inference-via-llamacpp","content":"Choose llama.cpp when you want the lowest-level, most resource-efficient local inference — especially on CPU or with heavily quantized GGUF models.\nWhen to choose: You need CPU-only inference; you want direct llama-server process control; you are running in a headless / server environment.\nProvider ID: llamacpp\nModel: Auto-discovered from the running llama-server (or pass an explicit model name).\nDefault base URL: http://localhost:8080/v1\nTool calling: Requires server to be started with --jinja flag.\nNot suitable for: PDF processing; production at scale without additional infrastructure.\nSetup: ./llama-server -m model.gguf --port 8080 [--jinja]","hierarchy":{"lvl0":"Reference","lvl1":"Provider Selection Guide","lvl2":"Local Inference via llama.cpp","lvl3":""}},
 {"objectID":"f6ce3650e34df2b638d084f777182ef05448c55cc7487917a52a5f6a3a2b4864","title":"Privacy-Critical Applications","url":"/docs/reference/provider-selection#privacy-critical-applications","content":"Recommended Stack:","hierarchy":{"lvl0":"Reference","lvl1":"Provider Selection Guide","lvl2":"Privacy-Critical Applications","lvl3":""}},

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@juspay/neurolink",
-  "version": "13.8.12",
+  "version": "13.8.13",
   "packageManager": "pnpm@10.15.1",
   "description": "The pipe layer of an AI nervous system: one interface connecting provider neurons to your application, across three inference types — generate, stream and decide. `decide` returns typed, calibrated judgements from a non-generative model (~400ms, ~$0.00002/call) for routing, tool selection and context budgeting. MCP-native (4 transports), voice TTS/STT/realtime, RAG, agents, memory, compaction, 9 observability exporters. OpenAI · Anthropic · Gemini · Bedrock · Azure · Ollama · TypeSafe Jev and more.",
   "author": {