digitalocean · SSharma-10 · Apr 28, 2026 · Apr 28, 2026 · Apr 28, 2026
diff --git a/specification/DigitalOcean-public.v2.yaml b/specification/DigitalOcean-public.v2.yaml
@@ -3087,27 +3087,39 @@ components:
       type: http
       scheme: bearer
       description: |
-        ## Inference API Authentication
+        ## OAuth Authentication
+
+        In order to interact with the DigitalOcean API, you or your application must
+        authenticate.
+
+        The DigitalOcean API handles this through OAuth, an open standard for
+        authorization. OAuth allows you to delegate access to your account.
+        Scopes can be used to grant full access, read-only access, or access to
+        a specific set of endpoints.
+
+        You can generate an OAuth token by visiting the [Apps & API](https://cloud.digitalocean.com/account/api/tokens)
+        section of the DigitalOcean control panel for your account.
 
-        The Inference APIs use API access keys for authentication, which are
-        separate from the DigitalOcean OAuth tokens used by the control-plane API.
+        An OAuth token functions as a complete authentication request. In effect, it
+        acts as a substitute for a username and password pair.
 
-        Include the key as a Bearer token in the `Authorization` header of each
-        request. All requests must be made over HTTPS.
+        Because of this, it is absolutely **essential** that you keep your OAuth
+        tokens secure. In fact, upon generation, the web interface will only display
+        each token a single time in order to prevent the token from being compromised.
 
-        ### Key Types
+        DigitalOcean access tokens begin with an identifiable prefix in order to
+        distinguish them from other similar tokens.
 
-        | API | Key Type | Key Pattern | How to Obtain |
-        |-----|----------|-------------|---------------|
-        | Serverless Inference | Model access key | `sk-do-*` (e.g., `sk-do-v1-abcd1234...`) | Generate in the [AI/ML section](https://cloud.digitalocean.com/gen-ai/inference/keys) of the DigitalOcean control panel |
-        | Agent Inference | Endpoint access key | Alphanumeric string (e.g., `Abc1Def2Ghi3Jkl4...`) | Provided when provisioning an agent endpoint |
+        - `dop_v1_` for personal access tokens generated in the control panel
+        - `doo_v1_` for tokens generated by applications using [the OAuth flow](https://docs.digitalocean.com/reference/api/oauth-api/)
+        - `dor_v1_` for OAuth refresh tokens
 
         ### Authenticate with a Bearer Authorization Header
 
         **Serverless Inference:**
 
         ```
-        curl -X POST -H "Authorization: Bearer $MODEL_ACCESS_KEY" "https://inference.do-ai.run/v1/chat/completions"
+        curl -X POST -H "Authorization: Bearer $DIGITALOCEAN_TOKEN" "https://inference.do-ai.run/v1/chat/completions"
         ```
 
         **Agent Inference:**
@@ -3116,9 +3128,12 @@ components:
         curl -X POST -H "Authorization: Bearer $AGENT_ACCESS_KEY" "https://{your-agent-url}.agents.do-ai.run/v1/chat/completions?agent=true"
         ```
 
-        **Note:** These keys are not interchangeable with DigitalOcean OAuth
-        tokens (`dop_v1_*`, `doo_v1_*`, `dor_v1_*`). OAuth tokens are used
-        exclusively with the control-plane API at `https://api.digitalocean.com`.
+        **Note:** Agent Inference APIs use an `agent_access_key` (endpoint access
+        key) instead of a DigitalOcean OAuth token. The `agent_access_key` is
+        provided when you provision an agent endpoint and is scoped to that
+        specific agent. It is not interchangeable with DigitalOcean OAuth tokens
+        (`dop_v1_*`, `doo_v1_*`, `dor_v1_*`), which are used with Serverless
+        Inference and the control-plane API at `https://api.digitalocean.com`.
 
 security:
   - bearer_auth: []
diff --git a/specification/inference_description.yml b/specification/inference_description.yml
@@ -9,17 +9,6 @@ introduction: |
 
   These APIs are independent of the main DigitalOcean control-plane API (`https://api.digitalocean.com`).
 
-  ## Authentication
-
-  In order to make requests to the Inference APIs, you must authenticate using a Bearer token.
-
-  | API | Authentication | Key Pattern |
-  |-----|----------------|-------------|
-  | Serverless Inference | Model access key | `sk-do-*` (e.g., `sk-do-v1-abcd1234efgh5678ijkl9012mnop3456qrst7890uvwx1234yzab5678cdef`) |
-  | Agent Inference | Endpoint access key | Alphanumeric string (e.g., `Abc1Def2Ghi3Jkl4Mno5Pqr6Stu7Vwx8`) |
-
-  **Note:** The Control Plane API (`https://api.digitalocean.com`) uses OAuth tokens for authentication, which is different from the inference API keys.
-
   ## Base URLs
 
   | API | Base URL |

diff --git a/specification/resources/inference/examples/curl/inference_async_invoke.yml b/specification/resources/inference/examples/curl/inference_async_invoke.yml
@@ -2,7 +2,7 @@ lang: cURL
 source: |-
   # Image Generation
   curl -X POST \
-    -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
+    -H "Authorization: Bearer $DIGITALOCEAN_TOKEN" \
     -H "Content-Type: application/json" \
     -d '{
       "model_id": "fal-ai/flux/schnell",
@@ -14,7 +14,7 @@ source: |-
 
   # Audio Generation
   curl -X POST \
-    -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
+    -H "Authorization: Bearer $DIGITALOCEAN_TOKEN" \
     -H "Content-Type: application/json" \
     -d '{
       "model_id": "fal-ai/stable-audio-25/text-to-audio",
@@ -30,7 +30,7 @@ source: |-
 
   # Text-to-Speech
   curl -X POST \
-    -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
+    -H "Authorization: Bearer $DIGITALOCEAN_TOKEN" \
     -H "Content-Type: application/json" \
     -d '{
       "model_id": "fal-ai/elevenlabs/tts/multilingual-v2",

diff --git a/specification/resources/inference/examples/curl/inference_cancel_batch.yml b/specification/resources/inference/examples/curl/inference_cancel_batch.yml
@@ -1,5 +1,5 @@
 lang: cURL
 source: |-
   curl -sS -X POST "https://inference.do-ai.run/v1/batches/0e9d1d35-3d1e-4d66-9a2f-8c7e0f6b3e21/cancel" \
-    -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
+    -H "Authorization: Bearer $DIGITALOCEAN_TOKEN" \
     -H "Content-Type: application/json" | jq
diff --git a/specification/resources/inference/examples/curl/inference_create_batch.yml b/specification/resources/inference/examples/curl/inference_create_batch.yml
@@ -2,7 +2,7 @@ lang: cURL
 source: |-
   # OpenAI provider - Chat Completions
   curl -sS -X POST "https://inference.do-ai.run/v1/batches" \
-    -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
+    -H "Authorization: Bearer $DIGITALOCEAN_TOKEN" \
     -H "Content-Type: application/json" \
     -d '{
       "file_id": "a1b2c3d4-e5f6-4789-90ab-cdef12345678",
@@ -14,7 +14,7 @@ source: |-
 
   # Anthropic provider - Messages
   curl -sS -X POST "https://inference.do-ai.run/v1/batches" \
-    -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
+    -H "Authorization: Bearer $DIGITALOCEAN_TOKEN" \
     -H "Content-Type: application/json" \
     -d '{
       "file_id": "a1b2c3d4-e5f6-4789-90ab-cdef12345678",

diff --git a/specification/resources/inference/examples/curl/inference_create_batch_file.yml b/specification/resources/inference/examples/curl/inference_create_batch_file.yml
@@ -1,7 +1,7 @@
 lang: cURL
 source: |-
   curl -sS -X POST "https://inference.do-ai.run/v1/batches/files" \
-    -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
+    -H "Authorization: Bearer $DIGITALOCEAN_TOKEN" \
     -H "Content-Type: application/json" \
     -d '{
       "file_name": "batch_requests.jsonl"

diff --git a/specification/resources/inference/examples/curl/inference_create_chat_completion.yml b/specification/resources/inference/examples/curl/inference_create_chat_completion.yml
@@ -2,6 +2,6 @@ lang: cURL
 source: |-
   curl -X POST \
     -H "Content-Type: application/json" \
-    -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
+    -H "Authorization: Bearer $DIGITALOCEAN_TOKEN" \
     -d '{"messages": [{"role": "user", "content": "What is the capital of Portugal?"}], "model": "meta-llama/Meta-Llama-3.1-8B-Instruct"}' \
     "https://inference.do-ai.run/v1/chat/completions"
diff --git a/specification/resources/inference/examples/curl/inference_create_embeddings.yml b/specification/resources/inference/examples/curl/inference_create_embeddings.yml
@@ -2,6 +2,6 @@ lang: cURL
 source: |-
   curl -X POST \
     -H "Content-Type: application/json" \
-    -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
+    -H "Authorization: Bearer $DIGITALOCEAN_TOKEN" \
     -d '{"model":"qwen3-embedding-0.6b","input":["hello world","goodbye world"],"encoding_format":"float","user":"user-1234"}' \
     "https://inference.do-ai.run/v1/embeddings"
diff --git a/specification/resources/inference/examples/curl/inference_create_image.yml b/specification/resources/inference/examples/curl/inference_create_image.yml
@@ -2,6 +2,6 @@ lang: cURL
 source: |-
   curl -X POST \
     -H "Content-Type: application/json" \
-    -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
+    -H "Authorization: Bearer $DIGITALOCEAN_TOKEN" \
     -d '{"prompt": "A cute baby sea otter floating on its back in calm blue water", "model": "openai-gpt-image-1", "size": "auto", "quality": "auto"}' \
     "https://inference.do-ai.run/v1/images/generations"
diff --git a/specification/resources/inference/examples/curl/inference_create_messages.yml b/specification/resources/inference/examples/curl/inference_create_messages.yml
@@ -2,6 +2,6 @@ lang: cURL
 source: |-
   curl -X POST \
     -H "Content-Type: application/json" \
-    -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
+    -H "Authorization: Bearer $DIGITALOCEAN_TOKEN" \
     -d '{"model": "claude-opus-4-6", "max_tokens": 1024, "messages": [{"role": "user", "content": "What is the capital of Portugal?"}]}' \
     "https://inference.do-ai.run/v1/messages"
diff --git a/specification/resources/inference/examples/curl/inference_create_response.yml b/specification/resources/inference/examples/curl/inference_create_response.yml
@@ -1,7 +1,7 @@
 lang: cURL
 source: |-
   curl -sS -X POST \
-    -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
+    -H "Authorization: Bearer $DIGITALOCEAN_TOKEN" \
     -H "Content-Type: application/json" \
     -d '{
       "model": "openai-gpt-oss-20b",

diff --git a/specification/resources/inference/examples/curl/inference_get_batch.yml b/specification/resources/inference/examples/curl/inference_get_batch.yml
@@ -1,5 +1,5 @@
 lang: cURL
 source: |-
   curl -sS -X GET "https://inference.do-ai.run/v1/batches/0e9d1d35-3d1e-4d66-9a2f-8c7e0f6b3e21" \
-    -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
+    -H "Authorization: Bearer $DIGITALOCEAN_TOKEN" \
     -H "Content-Type: application/json"
diff --git a/specification/resources/inference/examples/curl/inference_get_batch_results.yml b/specification/resources/inference/examples/curl/inference_get_batch_results.yml
@@ -1,5 +1,5 @@
 lang: cURL
 source: |-
   curl -sS -X GET "https://inference.do-ai.run/v1/batches/0e9d1d35-3d1e-4d66-9a2f-8c7e0f6b3e21/results" \
-    -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
+    -H "Authorization: Bearer $DIGITALOCEAN_TOKEN" \
     -H "Content-Type: application/json" | jq
diff --git a/specification/resources/inference/examples/curl/inference_list_batches.yml b/specification/resources/inference/examples/curl/inference_list_batches.yml
@@ -1,5 +1,5 @@
 lang: cURL
 source: |-
   curl -sS -X GET "https://inference.do-ai.run/v1/batches?limit=20" \
-    -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
+    -H "Authorization: Bearer $DIGITALOCEAN_TOKEN" \
     -H "Content-Type: application/json" | jq
diff --git a/specification/resources/inference/examples/curl/inference_list_models.yml b/specification/resources/inference/examples/curl/inference_list_models.yml
@@ -2,5 +2,5 @@ lang: cURL
 source: |-
   curl -X GET \
     -H "Content-Type: application/json" \
-    -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
+    -H "Authorization: Bearer $DIGITALOCEAN_TOKEN" \
     "https://inference.do-ai.run/v1/models"
diff --git a/specification/resources/inference/examples/dots/inference_async_invoke.yml b/specification/resources/inference/examples/dots/inference_async_invoke.yml
@@ -3,7 +3,7 @@ source: |-
   import { InferenceClient } from "@digitalocean/dots";
 
   const client = new InferenceClient({
-      apiKey: process.env.MODEL_ACCESS_KEY,
+      apiKey: process.env.DIGITALOCEAN_TOKEN,
   });
 
   // Image Generation

diff --git a/specification/resources/inference/examples/dots/inference_create_chat_completion.yml b/specification/resources/inference/examples/dots/inference_create_chat_completion.yml
@@ -3,7 +3,7 @@ source: |-
   import { InferenceClient } from "@digitalocean/dots";
 
   const client = new InferenceClient({
-      apiKey: process.env.MODEL_ACCESS_KEY,
+      apiKey: process.env.DIGITALOCEAN_TOKEN,
   });
 
   const completion = await client.chat.completions.create({

diff --git a/specification/resources/inference/examples/dots/inference_create_embeddings.yml b/specification/resources/inference/examples/dots/inference_create_embeddings.yml
@@ -3,7 +3,7 @@ source: |-
   import { InferenceClient } from "@digitalocean/dots";
 
   const client = new InferenceClient({
-      apiKey: process.env.MODEL_ACCESS_KEY,
+      apiKey: process.env.DIGITALOCEAN_TOKEN,
   });
 
   const resp = await client.embeddings.create({

diff --git a/specification/resources/inference/examples/dots/inference_create_image.yml b/specification/resources/inference/examples/dots/inference_create_image.yml
@@ -3,7 +3,7 @@ source: |-
   import { InferenceClient } from "@digitalocean/dots";
 
   const client = new InferenceClient({
-      apiKey: process.env.MODEL_ACCESS_KEY,
+      apiKey: process.env.DIGITALOCEAN_TOKEN,
   });
 
   const resp = await client.images.generate({

diff --git a/specification/resources/inference/examples/dots/inference_create_messages.yml b/specification/resources/inference/examples/dots/inference_create_messages.yml
@@ -3,7 +3,7 @@ source: |-
   import { InferenceClient } from "@digitalocean/dots";
 
   const client = new InferenceClient({
-      apiKey: process.env.MODEL_ACCESS_KEY,
+      apiKey: process.env.DIGITALOCEAN_TOKEN,
   });
 
   const resp = await client.messages.create({

diff --git a/specification/resources/inference/examples/dots/inference_create_response.yml b/specification/resources/inference/examples/dots/inference_create_response.yml
@@ -3,7 +3,7 @@ source: |-
   import { InferenceClient } from "@digitalocean/dots";
 
   const client = new InferenceClient({
-      apiKey: process.env.MODEL_ACCESS_KEY,
+      apiKey: process.env.DIGITALOCEAN_TOKEN,
   });
 
   const resp = await client.responses.create({

diff --git a/specification/resources/inference/examples/dots/inference_list_models.yml b/specification/resources/inference/examples/dots/inference_list_models.yml
@@ -3,7 +3,7 @@ source: |-
   import { InferenceClient } from "@digitalocean/dots";
 
   const client = new InferenceClient({
-      apiKey: process.env.MODEL_ACCESS_KEY,
+      apiKey: process.env.DIGITALOCEAN_TOKEN,
   });
 
   const resp = await client.models.list();

diff --git a/specification/resources/inference/examples/python/inference_async_invoke.yml b/specification/resources/inference/examples/python/inference_async_invoke.yml
@@ -3,7 +3,7 @@ source: |-
   import os
   from pydo import Client
 
-  client = Client(token=os.environ.get("MODEL_ACCESS_KEY"))
+  client = Client(token=os.environ.get("DIGITALOCEAN_TOKEN"))
 
   # Image Generation
   resp = client.async_images.generate(

diff --git a/specification/resources/inference/examples/python/inference_create_chat_completion.yml b/specification/resources/inference/examples/python/inference_create_chat_completion.yml
@@ -3,7 +3,7 @@ source: |-
   import os
   from pydo import Client
 
-  client = Client(token=os.environ.get("MODEL_ACCESS_KEY"))
+  client = Client(token=os.environ.get("DIGITALOCEAN_TOKEN"))
 
   resp = client.chat.completions.create(
       model="llama3.3-70b-instruct",

diff --git a/specification/resources/inference/examples/python/inference_create_embeddings.yml b/specification/resources/inference/examples/python/inference_create_embeddings.yml
@@ -3,7 +3,7 @@ source: |-
   import os
   from pydo import Client
 
-  client = Client(token=os.environ.get("MODEL_ACCESS_KEY"))
+  client = Client(token=os.environ.get("DIGITALOCEAN_TOKEN"))
 
   resp = client.embeddings.create(
       model="qwen3-embedding-0.6b",

diff --git a/specification/resources/inference/examples/python/inference_create_image.yml b/specification/resources/inference/examples/python/inference_create_image.yml
@@ -3,7 +3,7 @@ source: |-
   import os
   from pydo import Client
 
-  client = Client(token=os.environ.get("MODEL_ACCESS_KEY"))
+  client = Client(token=os.environ.get("DIGITALOCEAN_TOKEN"))
 
   resp = client.images.generate(
       model="openai-gpt-image-1",

diff --git a/specification/resources/inference/examples/python/inference_create_messages.yml b/specification/resources/inference/examples/python/inference_create_messages.yml
@@ -3,7 +3,7 @@ source: |-
   import os
   from pydo import Client
 
-  client = Client(token=os.environ.get("MODEL_ACCESS_KEY"))
+  client = Client(token=os.environ.get("DIGITALOCEAN_TOKEN"))
 
   resp = client.messages.create(
       model="claude-opus-4-6",

diff --git a/specification/resources/inference/examples/python/inference_create_response.yml b/specification/resources/inference/examples/python/inference_create_response.yml
@@ -3,7 +3,7 @@ source: |-
   import os
   from pydo import Client
 
-  client = Client(token=os.environ.get("MODEL_ACCESS_KEY"))
+  client = Client(token=os.environ.get("DIGITALOCEAN_TOKEN"))
 
   resp = client.responses.create(
       model="openai-gpt-oss-20b",

diff --git a/specification/resources/inference/examples/python/inference_list_models.yml b/specification/resources/inference/examples/python/inference_list_models.yml
@@ -3,7 +3,7 @@ source: |-
   import os
   from pydo import Client
 
-  client = Client(token=os.environ.get("MODEL_ACCESS_KEY"))
+  client = Client(token=os.environ.get("DIGITALOCEAN_TOKEN"))
 
   resp = client.models.list()