PierreLeGuen · Sep 23, 2026 · Aug 24, 2026 · Aug 24, 2026 · Aug 24, 2026 · Aug 24, 2026
diff --git a/.github/INTEGRATION_GUIDE_TEMPLATE.md b/.github/INTEGRATION_GUIDE_TEMPLATE.md
@@ -60,8 +60,9 @@ Use the gateway base URL by default:
 https://cloud-api.near.ai/v1
 ```
 
-Only mention direct completions when the tool accepts arbitrary per-model base
-URLs. Otherwise, link to Direct Completions instead of adding unverified config.
+Use the Gateway in new integration guides. Do not add direct-completions
+configuration or links; direct endpoints are experimental and are not
+recommended for new integrations.
 
 ### Model ID
 
@@ -109,7 +110,6 @@ Link to canonical NEAR AI Cloud docs instead of repeating long explanations:
 
 - OpenAI Compatibility: `/cloud/guides/openai-compatibility`
 - Model Discovery: `/cloud/guides/integrations/model-discovery`
-- Direct Completions: `/cloud/private-inference#direct-completions`
 - Available Models: `/cloud/models`
 
 ### Sources Checked

diff --git a/cloud/guides/e2ee-chat-completions.mdx b/cloud/guides/e2ee-chat-completions.mdx
diff --git a/cloud/guides/fusion.mdx b/cloud/guides/fusion.mdx
@@ -89,7 +89,7 @@ Use `tool_choice: "required"` when you want Fusion to run immediately. If you om
 
 | Field | Required | Description |
 |-------|----------|-------------|
-| `analysis_models` | Yes* | Panel models to ask before synthesis. Required unless the deployment configures `FUSION_DEFAULT_ANALYSIS_MODELS`. Model names may include or omit a leading `~`; NEAR AI strips it before direct endpoint lookup. |
+| `analysis_models` | Yes* | Panel models to ask before synthesis. Required unless the deployment configures `FUSION_DEFAULT_ANALYSIS_MODELS`. Model names may include or omit a leading `~`; NEAR AI ignores the prefix when resolving the model. |
 | `model` | No | Judge model. Defaults to the request `model` when omitted. |
 | `max_tool_calls` | No | Maximum inner web-search tool calls for panel and judge requests. |
 | `max_completion_tokens` | No | Token cap for panel and judge completions. |

diff --git a/cloud/guides/integrations/aider-zed.mdx b/cloud/guides/integrations/aider-zed.mdx
@@ -150,7 +150,6 @@ If you only set `OPENAI_API_KEY` for Aider, either export `NEARAI_API_KEY="$OPEN
 - [Model Discovery and Refresh](/cloud/guides/integrations/model-discovery)
 - [OpenAI Compatibility](/cloud/guides/openai-compatibility)
 - [Available Models](/cloud/models)
-- [Private Inference - Direct Completions](/cloud/private-inference#direct-completions)
 - [Continue](/cloud/guides/integrations/continue)
 - [Cline, Roo Code, and Kilo Code](/cloud/guides/integrations/cline-roo-kilo)
 

diff --git a/cloud/guides/integrations/cline-roo-kilo.mdx b/cloud/guides/integrations/cline-roo-kilo.mdx
@@ -164,7 +164,6 @@ Sources checked on 2026-06-23: Cline OpenAI Compatible provider docs, Roo Code O
 
 - [Model Discovery and Refresh](/cloud/guides/integrations/model-discovery)
 - [OpenAI Compatibility](/cloud/guides/openai-compatibility)
-- [Private Inference - Direct Completions](/cloud/private-inference#direct-completions)
 - [Available Models](/cloud/models)
 - [Continue](/cloud/guides/integrations/continue)
 - [Aider and Zed](/cloud/guides/integrations/aider-zed)

diff --git a/cloud/guides/integrations/continue.mdx b/cloud/guides/integrations/continue.mdx
@@ -130,7 +130,6 @@ models:
 - [Model Discovery and Refresh](/cloud/guides/integrations/model-discovery)
 - [OpenAI Compatibility](/cloud/guides/openai-compatibility)
 - [Available Models](/cloud/models)
-- [Private Inference - Direct Completions](/cloud/private-inference#direct-completions)
 - [Cline, Roo Code, and Kilo Code](/cloud/guides/integrations/cline-roo-kilo)
 - [Aider and Zed](/cloud/guides/integrations/aider-zed)
 

diff --git a/cloud/guides/integrations/cursor.mdx b/cloud/guides/integrations/cursor.mdx
@@ -129,7 +129,6 @@ If curl works, test Cursor with a plain text Chat or Plan prompt. If Cursor fail
 
 - [Model Discovery and Refresh](/cloud/guides/integrations/model-discovery)
 - [OpenAI Compatibility](/cloud/guides/openai-compatibility)
-- [Private Inference - Direct Completions](/cloud/private-inference#direct-completions)
 - [Available Models](/cloud/models)
 - [Continue](/cloud/guides/integrations/continue)
 - [Cline, Roo Code, and Kilo Code](/cloud/guides/integrations/cline-roo-kilo)

diff --git a/cloud/guides/integrations/dify.mdx b/cloud/guides/integrations/dify.mdx
@@ -128,7 +128,6 @@ If curl fails, fix the NEAR AI Cloud key, model ID, or base URL before changing
 - [Model Discovery and Refresh](/cloud/guides/integrations/model-discovery)
 - [OpenAI Compatibility](/cloud/guides/openai-compatibility)
 - [Available Models](/cloud/models)
-- [Private Inference - Direct Completions](/cloud/private-inference#direct-completions)
 - [Open WebUI](/cloud/guides/integrations/open-webui)
 - [LibreChat](/cloud/guides/integrations/librechat)
 

diff --git a/cloud/guides/integrations/index.mdx b/cloud/guides/integrations/index.mdx
@@ -37,7 +37,7 @@ Use the OpenAI client guide when you are configuring code directly. Use the inte
 
 ## Model Discovery
 
-NEAR AI Cloud can add new models over time. Use the [Model Discovery guide](/cloud/guides/integrations/model-discovery) to check the current model list, choose between gateway and direct completions endpoints, and copy the right model ID into clients that do not refresh automatically.
+NEAR AI Cloud can add new models over time. Use the [Model Discovery guide](/cloud/guides/integrations/model-discovery) to check the current Gateway model list and copy the right model ID into clients that do not refresh automatically.
 
 ```bash
 curl https://cloud-api.near.ai/v1/models

diff --git a/cloud/guides/integrations/librechat.mdx b/cloud/guides/integrations/librechat.mdx
@@ -162,7 +162,6 @@ If curl fails, fix the NEAR AI Cloud key, model ID, or network path before chang
 - [Model Discovery and Refresh](/cloud/guides/integrations/model-discovery)
 - [OpenAI Compatibility](/cloud/guides/openai-compatibility)
 - [Available Models](/cloud/models)
-- [Private Inference - Direct Completions](/cloud/private-inference#direct-completions)
 - [Open WebUI](/cloud/guides/integrations/open-webui)
 - [Dify](/cloud/guides/integrations/dify)
 - [LiteLLM Proxy](/cloud/guides/integrations/litellm)

diff --git a/cloud/guides/integrations/litellm.mdx b/cloud/guides/integrations/litellm.mdx
@@ -186,7 +186,6 @@ If curl fails, fix the NEAR AI Cloud key, model ID, or network path before chang
 - [Model Discovery and Refresh](/cloud/guides/integrations/model-discovery)
 - [OpenAI Compatibility](/cloud/guides/openai-compatibility)
 - [Available Models](/cloud/models)
-- [Private Inference - Direct Completions](/cloud/private-inference#direct-completions)
 - [LibreChat](/cloud/guides/integrations/librechat)
 - [Open WebUI](/cloud/guides/integrations/open-webui)
 

diff --git a/cloud/guides/integrations/model-discovery.mdx b/cloud/guides/integrations/model-discovery.mdx
@@ -5,7 +5,7 @@ description: "Discover current NEAR AI Cloud models and refresh stale client mod
 ---
 
 
-Use this guide when a client does not show a newly released NEAR AI Cloud model, or when you need to decide between the gateway model ID and a direct completions endpoint.
+Use this guide when a client does not show a newly released NEAR AI Cloud model.
 
 Most tools should use:
 
@@ -48,47 +48,14 @@ The response uses OpenAI-style model objects plus NEAR AI Cloud metadata. Import
 
 As checked on 2026-06-23, the live GLM 5.2 gateway record reports `top_provider.context_length: 500000`, `top_provider.max_completion_tokens: 131072`, and `max_output_length: 131072`.
 
-## Discover direct completions endpoints
-
-Direct completions endpoints are listed at:
-
-```bash
-curl https://completions.near.ai/endpoints
-```
-
-To find the GLM 5.2 direct completions endpoint:
-
-```bash
-curl -fsSL https://completions.near.ai/endpoints \
-  | jq '.endpoints[] | select(.domain == "glm-5-2.completions.near.ai")'
-```
-
-As checked on 2026-06-23, that endpoint is:
-
-```text
-https://glm-5-2.completions.near.ai/v1
-```
-
-The endpoints registry (`GET https://completions.near.ai/endpoints`) lists both `z-ai/glm-5.2` and `zai-org/GLM-5.2-FP8` for this domain, but the endpoint's own `GET https://glm-5-2.completions.near.ai/v1/models` currently returns only `z-ai/glm-5.2`. Use `z-ai/glm-5.2`. The `zai-org/GLM-5.2-FP8` served name still resolves at the direct endpoint, but treat it as a fallback only when your client needs that exact served model name.
-
-## Gateway vs direct completions
-
-Use the gateway by default:
+## Use the Gateway
 
 ```text
 https://cloud-api.near.ai/v1
 ```
 
 The gateway is the best fit for most third-party clients because one base URL can reach the full NEAR AI Cloud model catalog, and clients that auto-fetch models can use `GET /v1/models`.
 
-Use direct completions only when you intentionally want one model's TEE endpoint:
-
-```text
-https://glm-5-2.completions.near.ai/v1
-```
-
-Direct completions can reduce routing hops and exposes the model-specific route set described in [Private Inference - Direct Completions](/cloud/private-inference#direct-completions). It is not a replacement for the gateway model catalog in clients that expect one provider to list every model.
-
 ## Why client model lists go stale
 
 Client model lists can become stale for three common reasons:
@@ -103,8 +70,6 @@ When NEAR releases a new model, check `https://cloud-api.near.ai/v1/models`, cop
 z-ai/glm-5.2
 ```
 
-If you are configuring a direct completions endpoint, also check `https://completions.near.ai/endpoints` and confirm the endpoint's `models` array includes the model name you plan to send.
-
 ## Tool behavior matrix
 
 | Behavior | Tools | Refresh action |
@@ -137,40 +102,23 @@ curl https://cloud-api.near.ai/v1/chat/completions \
   }'
 ```
 
-Use the direct completions endpoint only after confirming it lists the model:
-
-```bash
-curl -fsS https://glm-5-2.completions.near.ai/v1/chat/completions \
-  -H "Authorization: Bearer $NEARAI_API_KEY" \
-  -H "Content-Type: application/json" \
-  -d '{
-    "model": "z-ai/glm-5.2",
-    "messages": [
-      {"role": "user", "content": "Reply with only: near-ai-ok"}
-    ],
-    "max_tokens": 20
-  }'
-```
-
 ## Troubleshooting
 
 | Symptom | Likely cause | Fix |
 | --- | --- | --- |
 | model not listed | The client cached an older model list, uses a catalog that has not updated, or requires manual config. | Run the `/v1/models` curl check, copy `z-ai/glm-5.2`, and paste it into the client's custom model field. Re-save, reconnect, or restart the client. |
 | `401` | Missing, invalid, or expired NEAR AI Cloud API key. | Generate or copy a NEAR AI Cloud API key, store it in the client's secret field or environment variable, and retry without logging the key. |
-| Wrong base URL includes `/chat/completions` | The client expects a base URL, but the full request endpoint was pasted. | Use `https://cloud-api.near.ai/v1` for gateway config, or `https://glm-5-2.completions.near.ai/v1` for direct completions config. Do not append `/chat/completions` to a base URL field. |
+| Wrong base URL includes `/chat/completions` | The client expects a base URL, but the full request endpoint was pasted. | Use `https://cloud-api.near.ai/v1`. Do not append `/chat/completions` to a base URL field. |
 
 ## Related guides
 
 - [OpenAI Compatibility](/cloud/guides/openai-compatibility)
 - [Available Models](/cloud/models)
-- [Private Inference - Direct Completions](/cloud/private-inference#direct-completions)
 - [Integrations Overview](/cloud/guides/integrations)
 
 ## Sources Checked
 
 Sources checked on 2026-06-23:
 
 - [NEAR AI Cloud models API](https://cloud-api.near.ai/v1/models)
-- [NEAR AI Cloud direct completions endpoints](https://completions.near.ai/endpoints)
 - [models.dev catalog](https://models.dev/)
diff --git a/cloud/guides/integrations/open-webui.mdx b/cloud/guides/integrations/open-webui.mdx
@@ -117,7 +117,6 @@ If either curl command fails, fix the NEAR AI Cloud key, model ID, or network pa
 - [Model Discovery and Refresh](/cloud/guides/integrations/model-discovery)
 - [OpenAI Compatibility](/cloud/guides/openai-compatibility)
 - [Available Models](/cloud/models)
-- [Private Inference - Direct Completions](/cloud/private-inference#direct-completions)
 - [LibreChat](/cloud/guides/integrations/librechat)
 - [Dify](/cloud/guides/integrations/dify)
 

diff --git a/cloud/guides/integrations/opencode.mdx b/cloud/guides/integrations/opencode.mdx
@@ -6,7 +6,7 @@ description: "Configure OpenCode to use NEAR AI Cloud as an OpenAI-compatible pr
 
 [OpenCode](https://opencode.ai/) is a terminal coding agent that resolves its providers from the public [models.dev](https://models.dev/) catalog. NEAR AI Cloud is already in that catalog as the `nearai` provider, so in the common case you do not write a provider block at all: set an API key, point `model` at a NEAR AI model, and OpenCode handles the rest.
 
-You only need a manual provider entry in two cases: the model you want is newer than the catalog, or you want to reach a model's TEE directly instead of going through the gateway. Both are covered below.
+You only need a manual provider entry when the model you want is newer than the catalog or your OpenCode version predates the catalog's `nearai` entry. Both cases use the Gateway configuration below.
 
 ## Prerequisites
 
@@ -33,7 +33,7 @@ The catalog already sets the gateway base URL for the `nearai` provider:
 https://cloud-api.near.ai/v1
 ```
 
-You only set `options.baseURL` yourself when overriding it, for example to use a direct completions endpoint. Do not append `/chat/completions`; OpenCode adds the path when it calls the API.
+You only set `options.baseURL` yourself in a full provider block. Do not append `/chat/completions`; OpenCode adds the path when it calls the API.
 
 ## Model ID
 
@@ -139,26 +139,6 @@ NEAR AI Cloud exposes 50+ models. OpenCode's documented `whitelist` and `blackli
 }
 ```
 
-### Direct completions
-
-To bypass the gateway and connect straight to a model's TEE, override `baseURL` with that model's direct endpoint:
-
-```json opencode.json
-{
-  "$schema": "https://opencode.ai/config.json",
-  "model": "nearai/z-ai/glm-5.3-flash",
-  "provider": {
-    "nearai": {
-      "options": {
-        "baseURL": "https://glm-5-3-flash.completions.near.ai/v1"
-      }
-    }
-  }
-}
-```
-
-A direct endpoint serves exactly one model, so this override applies to the whole `nearai` provider. If you switch between models, keep the gateway base URL instead. See [Direct Completions](/cloud/private-inference#direct-completions).
-
 ## Refresh models
 
 OpenCode does not call NEAR AI Cloud's `/v1/models`. Its picker comes from the models.dev catalog, so a newly released NEAR AI model appears only after the catalog updates.
@@ -216,14 +196,12 @@ opencode run "Reply with only: near-ai-ok"
 | OpenCode reports an unknown provider or model | The provider key must be `nearai`, and `model` must be `nearai/<model-id>` — including the slash inside the model ID, as in `nearai/z-ai/glm-5.3-flash`. |
 | The model replies but never calls tools | The manual model entry is missing `tool_call: true`. Catalog entries set this; hand-written ones default to off. |
 | Replies are empty or truncated mid-thought | A reasoning model hit the output limit. Raise `limit.output` in the model entry to match `max_output_length` from `/v1/models`. |
-| A direct completions base URL rejects the model | Each `*.completions.near.ai` endpoint serves one model. Confirm with `curl https://<endpoint>/v1/models` that it advertises the ID you configured. |
 
 ## Related guides
 
 - [Model Discovery and Refresh](/cloud/guides/integrations/model-discovery)
 - [OpenAI Compatibility](/cloud/guides/openai-compatibility)
 - [Available Models](/cloud/models)
-- [Private Inference - Direct Completions](/cloud/private-inference#direct-completions)
 - [Goose](/cloud/guides/opencode-goose)
 - [Cline, Roo Code, and Kilo Code](/cloud/guides/integrations/cline-roo-kilo)
 

diff --git a/cloud/guides/openai-compatibility.mdx b/cloud/guides/openai-compatibility.mdx
@@ -14,28 +14,17 @@ To use the OpenAI SDKs with NEAR AI Cloud, you simply need to override the `base
 
 ### Base URL
 
-NEAR AI Cloud offers two base URL options:
-
-**Gateway** (routes to any model):
+Use the NEAR AI Cloud Gateway base URL:
 ```
 https://cloud-api.near.ai/v1
 ```
 
-**Direct Completions** (connects straight to a model's TEE):
-```
-https://{slug}.completions.near.ai/v1
-```
-
-For example, `https://qwen35-122b.completions.near.ai/v1` connects directly to Qwen3.5-122B. See [completions.near.ai/endpoints](https://completions.near.ai/endpoints) for all available endpoints.
-
-Both URLs use the same API key. Direct completions offer lower latency and a simpler trust model since TLS terminates directly in the model's TEE. See [Private Inference — Direct Completions](/cloud/private-inference#direct-completions) for details.
-
 ### API Key
 You can generate your API key in the [NEAR AI Cloud Dashboard](https://cloud.near.ai/dashboard/organizations).
 
 ### Request IDs
 
-Gateway responses from `https://cloud-api.near.ai/v1` and direct completions responses from `https://{slug}.completions.near.ai/v1` include an `X-Request-Id` response header. Support may ask you for this value when debugging a request.
+Gateway responses from `https://cloud-api.near.ai/v1` include an `X-Request-Id` response header. Support may ask you for this value when debugging a request.
 
 `X-Request-Id` is opaque support/debugging metadata; it is not W3C `traceparent` or distributed trace context. If you send your own `X-Request-Id`, use a non-sensitive UUID value. `X-Request-Id` values must not contain secrets or PII. `X-Org-Id` and `X-Workspace-Id` are internal tenant headers; public clients cannot set or override them.
 
@@ -177,7 +166,7 @@ NEAR AI Cloud supports the following core OpenAI API features:
 NEAR AI Cloud also provides non-OpenAI extensions:
 
 - **Reranking** (`/v1/rerank`) - Score documents against a query
-- **Privacy classification** (`/v1/privacy/classify`) - Detect personally identifiable information through the gateway, or through a privacy-filter direct completions backend when that backend is selected and available
+- **Privacy classification** (`/v1/privacy/classify`) - Detect personally identifiable information through the gateway
 - **Privacy redaction** (`/v1/privacy/redact`) - Gateway-only endpoint for redacting personally identifiable information
 - **Attestation & Signatures** (`/v1/attestation/report`, `/v1/signature/{chat_id}`) - See [Verification](/cloud/verification)
 

diff --git a/cloud/guides/opencode-goose.mdx b/cloud/guides/opencode-goose.mdx
@@ -146,7 +146,6 @@ Keep `max_tokens` generous on reasoning models. GLM 5.3 Flash spends its first t
 - [Model Discovery and Refresh](/cloud/guides/integrations/model-discovery)
 - [OpenAI Compatibility](/cloud/guides/openai-compatibility)
 - [Available Models](/cloud/models)
-- [Private Inference - Direct Completions](/cloud/private-inference#direct-completions)
 - [Cline, Roo Code, and Kilo Code](/cloud/guides/integrations/cline-roo-kilo)
 
 ## Sources Checked