Add Inference APIs pydo and dots example

specification/DigitalOcean-public.v2.yaml

@@ -2972,14 +2972,6 @@ components:
         curl -X POST -H "Authorization: Bearer $MODEL_ACCESS_KEY" "https://inference.do-ai.run/v1/chat/completions"
         ```
 
-        ```
-        curl -X POST -H "Content-Type: application/json" -H "Authorization: Bearer $MODEL_ACCESS_KEY" -d '{"model":"claude-opus-4-6","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}' "https://inference.do-ai.run/v1/messages"
-        ```
-
-        ```
-        curl -X POST -H "Content-Type: application/json" -H "Authorization: Bearer $MODEL_ACCESS_KEY" -d '{"model":"qwen3-embedding-0.6b","input":["hello world","goodbye world"],"encoding_format":"float","user":"user-1234"}' "https://inference.do-ai.run/v1/embeddings"
-        ```
-
         **Agent Inference:**
 
         ```

specification/resources/inference/agent_inference_create_chat_completion.yml

@@ -54,5 +54,7 @@ responses:
     $ref: '../../shared/responses/unexpected_error.yml'
 x-codeSamples:
   - $ref: 'examples/curl/agentInference_create_chat_completion.yml'
+  - $ref: 'examples/python/agentInference_create_chat_completion.yml'
+  - $ref: 'examples/dots/agentInference_create_chat_completion.yml'
 security:
   - inference_bearer_auth: []

specification/resources/inference/examples/curl/inference_async_invoke.yml

@@ -1,5 +1,6 @@
 lang: cURL
 source: |-
+  # Image Generation
   curl -X POST \
     -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
     -H "Content-Type: application/json" \
@@ -10,3 +11,34 @@ source: |-
       }
     }' \
     "https://inference.do-ai.run/v1/async-invoke"
+
+  # Audio Generation
+  curl -X POST \
+    -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
+    -H "Content-Type: application/json" \
+    -d '{
+      "model_id": "fal-ai/stable-audio-25/text-to-audio",
+      "input": {
+        "prompt": "Techno song with futuristic sounds",
+        "seconds_total": 60
+      },
+      "tags": [
+        {"key": "type", "value": "test"}
+      ]
+    }' \
+    "https://inference.do-ai.run/v1/async-invoke"
+
+  # Text-to-Speech
+  curl -X POST \
+    -H "Authorization: Bearer $MODEL_ACCESS_KEY" \
+    -H "Content-Type: application/json" \
+    -d '{
+      "model_id": "fal-ai/elevenlabs/tts/multilingual-v2",
+      "input": {
+        "text": "This text-to-speech example uses DigitalOcean multilingual voice."
+      },
+      "tags": [
+        {"key": "type", "value": "test"}
+      ]
+    }' \
+    "https://inference.do-ai.run/v1/async-invoke"

specification/resources/inference/examples/dots/agentInference_create_chat_completion.yml

@@ -0,0 +1,17 @@
+lang: JavaScript
+source: |-
+  import { InferenceClient } from "@digitalocean/dots";
+
+  const client = new InferenceClient({
+      apiKey: process.env.AGENT_ACCESS_KEY,
+      baseURL: `https://${process.env.AGENT_URL}/api`,
+  });
+
+  const completion = await client.chat.completions.create({
+      model: "llama3.3-70b-instruct",
+      messages: [
+          { role: "user", content: "What is the capital of Portugal?" },
+      ],
+  });
+
+  console.log(completion.choices[0].message.content);

specification/resources/inference/examples/dots/inference_async_invoke.yml

@@ -0,0 +1,29 @@
+lang: JavaScript
+source: |-
+  import { InferenceClient } from "@digitalocean/dots";
+
+  const client = new InferenceClient({
+      apiKey: process.env.MODEL_ACCESS_KEY,
+  });
+
+  // Image Generation
+  const imgResp = await client.async_images.generate({
+      model_id: "fal-ai/flux/schnell",
+      prompt: "A futuristic city at sunset",
+  });
+  console.log(imgResp.request_id, imgResp.status);
+
+  // Audio Generation
+  const audioResp = await client.audio.generate({
+      model_id: "fal-ai/stable-audio-25/text-to-audio",
+      prompt: "Techno song with futuristic sounds",
+      seconds_total: 60,
+  });
+  console.log(audioResp.request_id, audioResp.status);
+
+  // Text-to-Speech
+  const ttsResp = await client.audio.speech.create({
+      model_id: "fal-ai/elevenlabs/tts/multilingual-v2",
+      input: "This text-to-speech example uses DigitalOcean multilingual voice.",
+  });
+  console.log(ttsResp.request_id, ttsResp.status);

specification/resources/inference/examples/dots/inference_create_chat_completion.yml

@@ -0,0 +1,16 @@
+lang: JavaScript
+source: |-
+  import { InferenceClient } from "@digitalocean/dots";
+
+  const client = new InferenceClient({
+      apiKey: process.env.MODEL_ACCESS_KEY,
+  });
+
+  const completion = await client.chat.completions.create({
+      model: "llama3.3-70b-instruct",
+      messages: [
+          { role: "user", content: "What is the capital of Portugal?" },
+      ],
+  });
+
+  console.log(completion.choices[0].message.content);

specification/resources/inference/examples/dots/inference_create_embeddings.yml

@@ -0,0 +1,18 @@
+lang: JavaScript
+source: |-
+  import { InferenceClient } from "@digitalocean/dots";
+
+  const client = new InferenceClient({
+      apiKey: process.env.MODEL_ACCESS_KEY,
+  });
+
+  const resp = await client.embeddings.create({
+      model: "qwen3-embedding-0.6b",
+      input: ["hello world", "goodbye world"],
+      encoding_format: "float",
+      user: "user-1234",
+  });
+
+  for (const item of resp.data) {
+      console.log(item.index, item.embedding.slice(0, 8));
+  }

specification/resources/inference/examples/dots/inference_create_image.yml

@@ -0,0 +1,17 @@
+lang: JavaScript
+source: |-
+  import { InferenceClient } from "@digitalocean/dots";
+
+  const client = new InferenceClient({
+      apiKey: process.env.MODEL_ACCESS_KEY,
+  });
+
+  const resp = await client.images.generate({
+      model: "openai-gpt-image-1",
+      prompt: "A cute baby sea otter floating on its back in calm blue water",
+      size: "auto",
+      quality: "auto",
+      n: 1,
+  });
+
+  console.log(resp.data[0].b64_json);

specification/resources/inference/examples/dots/inference_create_messages.yml

@@ -0,0 +1,17 @@
+lang: JavaScript
+source: |-
+  import { InferenceClient } from "@digitalocean/dots";
+
+  const client = new InferenceClient({
+      apiKey: process.env.MODEL_ACCESS_KEY,
+  });
+
+  const resp = await client.messages.create({
+      model: "claude-opus-4-6",
+      max_tokens: 1024,
+      messages: [
+          { role: "user", content: "What is the capital of Portugal?" },
+      ],
+  });
+
+  console.log(resp.content[0].text);

specification/resources/inference/examples/dots/inference_create_response.yml

@@ -0,0 +1,16 @@
+lang: JavaScript
+source: |-
+  import { InferenceClient } from "@digitalocean/dots";
+
+  const client = new InferenceClient({
+      apiKey: process.env.MODEL_ACCESS_KEY,
+  });
+
+  const resp = await client.responses.create({
+      model: "openai-gpt-oss-20b",
+      input: "What is the capital of France?",
+      max_output_tokens: 50,
+      temperature: 0.7,
+  });
+
+  console.log(resp.output_text);

specification/resources/inference/examples/dots/inference_list_models.yml

@@ -0,0 +1,13 @@
+lang: JavaScript
+source: |-
+  import { InferenceClient } from "@digitalocean/dots";
+
+  const client = new InferenceClient({
+      apiKey: process.env.MODEL_ACCESS_KEY,
+  });
+
+  const resp = await client.models.list();
+
+  for (const model of resp.data) {
+      console.log(model.id);
+  }

specification/resources/inference/examples/python/agentInference_create_chat_completion.yml

@@ -0,0 +1,18 @@
+lang: Python
+source: |-
+  import os
+  from pydo import Client
+
+  client = Client(
+      token=os.environ.get("AGENT_ACCESS_KEY"),
+      agent_endpoint=os.environ.get("AGENT_ENDPOINT"),
+  )
+
+  resp = client.agent.chat.completions.create(
+      model="llama3.3-70b-instruct",
+      messages=[
+          {"role": "user", "content": "What is the capital of Portugal?"},
+      ],
+  )
+
+  print(resp.choices[0].message.content)

specification/resources/inference/examples/python/inference_async_invoke.yml

@@ -0,0 +1,28 @@
+lang: Python
+source: |-
+  import os
+  from pydo import Client
+
+  client = Client(token=os.environ.get("MODEL_ACCESS_KEY"))
+
+  # Image Generation
+  resp = client.async_images.generate(
+      model_id="fal-ai/flux/schnell",
+      prompt="A futuristic city at sunset",
+  )
+  print(resp.request_id, resp.status)
+
+  # Audio Generation
+  resp = client.audio.generate(
+      model_id="fal-ai/stable-audio-25/text-to-audio",
+      prompt="Techno song with futuristic sounds",
+      seconds_total=60,
+  )
+  print(resp.request_id, resp.status)
+
+  # Text-to-Speech
+  resp = client.audio.speech.create(
+      input="This text-to-speech example uses DigitalOcean multilingual voice.",
+      model_id="fal-ai/elevenlabs/tts/multilingual-v2",
+  )
+  print(resp.request_id, resp.status)

specification/resources/inference/examples/python/inference_create_chat_completion.yml

@@ -0,0 +1,15 @@
+lang: Python
+source: |-
+  import os
+  from pydo import Client
+
+  client = Client(token=os.environ.get("MODEL_ACCESS_KEY"))
+
+  resp = client.chat.completions.create(
+      model="llama3.3-70b-instruct",
+      messages=[
+          {"role": "user", "content": "What is the capital of Portugal?"},
+      ],
+  )
+
+  print(resp.choices[0].message.content)

specification/resources/inference/examples/python/inference_create_embeddings.yml

@@ -0,0 +1,16 @@
+lang: Python
+source: |-
+  import os
+  from pydo import Client
+
+  client = Client(token=os.environ.get("MODEL_ACCESS_KEY"))
+
+  resp = client.embeddings.create(
+      model="qwen3-embedding-0.6b",
+      input=["hello world", "goodbye world"],
+      encoding_format="float",
+      user="user-1234",
+  )
+
+  for item in resp.data:
+      print(item.index, item.embedding[:8])

specification/resources/inference/examples/python/inference_create_image.yml

@@ -0,0 +1,16 @@
+lang: Python
+source: |-
+  import os
+  from pydo import Client
+
+  client = Client(token=os.environ.get("MODEL_ACCESS_KEY"))
+
+  resp = client.images.generate(
+      model="openai-gpt-image-1",
+      prompt="A cute baby sea otter floating on its back in calm blue water",
+      size="auto",
+      quality="auto",
+      n=1,
+  )
+
+  print(resp.data[0].b64_json)

specification/resources/inference/examples/python/inference_create_messages.yml

@@ -0,0 +1,16 @@
+lang: Python
+source: |-
+  import os
+  from pydo import Client
+
+  client = Client(token=os.environ.get("MODEL_ACCESS_KEY"))
+
+  resp = client.messages.create(
+      model="claude-opus-4-6",
+      max_tokens=1024,
+      messages=[
+          {"role": "user", "content": "What is the capital of Portugal?"},
+      ],
+  )
+
+  print(resp.content[0].text)

specification/resources/inference/examples/python/inference_create_response.yml

@@ -0,0 +1,15 @@
+lang: Python
+source: |-
+  import os
+  from pydo import Client
+
+  client = Client(token=os.environ.get("MODEL_ACCESS_KEY"))
+
+  resp = client.responses.create(
+      model="openai-gpt-oss-20b",
+      input="What is the capital of France?",
+      max_output_tokens=50,
+      temperature=0.7,
+  )
+
+  print(resp.output[0].content[0].text)

specification/resources/inference/examples/python/inference_list_models.yml

@@ -0,0 +1,11 @@
+lang: Python
+source: |-
+  import os
+  from pydo import Client
+
+  client = Client(token=os.environ.get("MODEL_ACCESS_KEY"))
+
+  resp = client.models.list()
+
+  for model in resp.data:
+      print(model.id)