## Python SDK Changes:

* `open_router.beta.responses.send()`:  `response` **Changed** **Breaking** ⚠️
* `open_router.embeddings.generate()`:  `response.usage.prompt_tokens_details` **Added**
* `open_router.generations.get_generation()`:  `response.data.web_search_engine` **Added**
* `open_router.video_generation.generate()`: 
  *  `request.provider.options.baidu` **Added**

Author: speakeasybot

.devcontainer/README.md

@@ -1,4 +1,9 @@
 
+<div align="center">
+    <a href="https://codespaces.new/OpenRouterTeam/python-sdk.git/tree/main"><img src="https://github.com/codespaces/badge.svg" /></a>
+</div>
+<br>
+
 > **Remember to shutdown a GitHub Codespace when it is not in use!**
 
 # Dev Containers Quick Start

.speakeasy/gen.lock

@@ -32,7 +32,7 @@ generation:
     skipResponseBodyAssertions: false
   preApplyUnionDiscriminators: true
 python:
-  version: 0.9.1
+  version: 0.9.2
   additionalDependencies:
     dev: {}
     main: {}

.speakeasy/gen.yaml

@@ -1489,6 +1489,15 @@ components:
         - thinking
         - signature
       type: object
+    AnthropicThinkingDisplay:
+      enum:
+        - summarized
+        - omitted
+        - null
+      example: summarized
+      nullable: true
+      type: string
+      x-speakeasy-unknown-values: allow
     AnthropicThinkingTurns:
       example:
         type: thinking_turns
@@ -5965,12 +5974,12 @@ components:
         Configuration for the openrouter:image_generation server tool. Accepts all image_config params (aspect_ratio, quality, size, background, output_format, output_compression, moderation, etc.) plus a model field.
       example:
         aspect_ratio: '16:9'
-        model: openai/gpt-image-1
+        model: openai/gpt-5-image
         quality: high
       properties:
         model:
-          description: Which image generation model to use (e.g. "openai/gpt-image-1"). Defaults to "openai/gpt-image-1".
-          example: openai/gpt-image-1
+          description: Which image generation model to use (e.g. "openai/gpt-5-image"). Defaults to "openai/gpt-5-image".
+          example: openai/gpt-5-image
           type: string
       type: object
     ImageGenerationStatus:
@@ -7255,11 +7264,12 @@ components:
       properties:
         effort:
           description: >-
-            How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer. Valid values are `low`, `medium`, `high`, or `max`.
+            How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer. Valid values are `low`, `medium`, `high`, `xhigh`, or `max`.
           enum:
             - low
             - medium
             - high
+            - xhigh
             - max
             - null
           example: medium
@@ -7283,6 +7293,29 @@ components:
             - type
             - schema
           type: object
+        task_budget:
+          description: >-
+            Task budget for an agentic turn. The model sees a countdown of remaining tokens and uses it to prioritize work and wind down gracefully. Advisory — does not enforce a hard cap.
+          example:
+            total: 400000
+            type: tokens
+          nullable: true
+          properties:
+            remaining:
+              minimum: 0
+              nullable: true
+              type: integer
+            total:
+              minimum: 20000
+              type: integer
+            type:
+              enum:
+                - tokens
+              type: string
+          required:
+            - type
+            - total
+          type: object
       type: object
     MessagesPingEvent:
       description: Keep-alive ping event
@@ -7475,6 +7508,8 @@ components:
             - properties:
                 budget_tokens:
                   type: integer
+                display:
+                  $ref: '#/components/schemas/AnthropicThinkingDisplay'
                 type:
                   enum:
                     - enabled
@@ -7492,6 +7527,8 @@ components:
                 - type
               type: object
             - properties:
+                display:
+                  $ref: '#/components/schemas/AnthropicThinkingDisplay'
                 type:
                   enum:
                     - adaptive
@@ -7699,6 +7736,23 @@ components:
       allOf:
         - $ref: '#/components/schemas/BaseMessagesResult'
         - properties:
+            context_management:
+              nullable: true
+              properties:
+                applied_edits:
+                  items:
+                    additionalProperties:
+                      nullable: true
+                    properties:
+                      type:
+                        type: string
+                    required:
+                      - type
+                    type: object
+                  type: array
+              required:
+                - applied_edits
+              type: object
             provider:
               $ref: '#/components/schemas/ProviderName'
             usage:
@@ -7835,6 +7889,7 @@ components:
                 - AionLabs
                 - Alibaba
                 - Ambient
+                - Baidu
                 - Amazon Bedrock
                 - Amazon Nova
                 - Anthropic
@@ -8861,6 +8916,8 @@ components:
             service_tier:
               nullable: true
               type: string
+            text:
+              $ref: '#/components/schemas/TextExtendedConfig'
             usage:
               $ref: '#/components/schemas/Usage'
           type: object
@@ -9248,6 +9305,7 @@ components:
       example:
         id: ig_tmp_abc123
         imageUrl: https://example.com/image.png
+        result: https://example.com/image.png
         status: completed
         type: openrouter:image_generation
       properties:
@@ -9257,6 +9315,10 @@ components:
           type: string
         imageUrl:
           type: string
+        result:
+          description: The generated image as a base64-encoded string or URL, matching OpenAI image_generation_call format
+          nullable: true
+          type: string
         revisedPrompt:
           type: string
         status:
@@ -9504,6 +9566,7 @@ components:
           openrouter:browser_use: '#/components/schemas/OutputBrowserUseServerToolItem'
           openrouter:code_interpreter: '#/components/schemas/OutputCodeInterpreterServerToolItem'
           openrouter:datetime: '#/components/schemas/OutputDatetimeItem'
+          openrouter:experimental__search_models: '#/components/schemas/OutputSearchModelsServerToolItem'
           openrouter:file_search: '#/components/schemas/OutputFileSearchServerToolItem'
           openrouter:image_generation: '#/components/schemas/OutputImageGenerationServerToolItem'
           openrouter:mcp: '#/components/schemas/OutputMcpServerToolItem'
@@ -9545,6 +9608,7 @@ components:
         - $ref: '#/components/schemas/OutputToolSearchServerToolItem'
         - $ref: '#/components/schemas/OutputMemoryServerToolItem'
         - $ref: '#/components/schemas/OutputMcpServerToolItem'
+        - $ref: '#/components/schemas/OutputSearchModelsServerToolItem'
     OutputItemWebSearchCall:
       example:
         action:
@@ -9788,6 +9852,32 @@ components:
           - text: Analyzed the problem and found the optimal solution.
             type: summary_text
         type: reasoning
+    OutputSearchModelsServerToolItem:
+      description: An openrouter:experimental__search_models server tool output item
+      example:
+        arguments: '{"query":"Claude Opus"}'
+        id: sm_tmp_abc123
+        query: Claude Opus
+        status: completed
+        type: openrouter:experimental__search_models
+      properties:
+        arguments:
+          description: The JSON arguments submitted to the search tool (e.g. {"query":"Claude"})
+          type: string
+        id:
+          type: string
+        query:
+          type: string
+        status:
+          $ref: '#/components/schemas/ToolCallStatus'
+        type:
+          enum:
+            - openrouter:experimental__search_models
+          type: string
+      required:
+        - status
+        - type
+      type: object
     OutputTextEditorServerToolItem:
       description: An openrouter:text_editor server tool output item
       example:
@@ -10228,6 +10318,7 @@ components:
         - AionLabs
         - Alibaba
         - Ambient
+        - Baidu
         - Amazon Bedrock
         - Amazon Nova
         - Anthropic
@@ -10533,6 +10624,7 @@ components:
             - AionLabs
             - Alibaba
             - Ambient
+            - Baidu
             - Amazon Bedrock
             - Amazon Nova
             - Anthropic
@@ -11985,7 +12077,18 @@ components:
     TextExtendedConfig:
       allOf:
         - $ref: '#/components/schemas/TextConfig'
-        - properties: {}
+        - properties:
+            verbosity:
+              enum:
+                - low
+                - medium
+                - high
+                - xhigh
+                - max
+                - null
+              nullable: true
+              type: string
+              x-speakeasy-unknown-values: allow
           type: object
       description: Text output configuration including format and verbosity
       example:
@@ -12469,6 +12572,10 @@ components:
                   additionalProperties:
                     nullable: true
                   type: object
+                baidu:
+                  additionalProperties:
+                    nullable: true
+                  type: object
                 baseten:
                   additionalProperties:
                     nullable: true
@@ -14295,6 +14402,25 @@ paths:
                         description: Number of tokens in the input
                         example: 8
                         type: integer
+                      prompt_tokens_details:
+                        description: >-
+                          Per-modality token breakdown. Only present when the input contains 2+ modalities (e.g. text + image) and the upstream provider returns modality-level usage data. Only non-zero modality counts are included.
+                        properties:
+                          audio_tokens:
+                            description: Number of audio tokens in the input
+                            type: integer
+                          image_tokens:
+                            description: Number of image tokens in the input
+                            example: 258
+                            type: integer
+                          text_tokens:
+                            description: Number of text tokens in the input
+                            example: 8
+                            type: integer
+                          video_tokens:
+                            description: Number of video tokens in the input
+                            type: integer
+                        type: object
                       total_tokens:
                         description: Total number of tokens used
                         example: 8
@@ -14855,6 +14981,11 @@ paths:
                         description: User-Agent header from the request
                         nullable: true
                         type: string
+                      web_search_engine:
+                        description: The resolved web search engine used for this generation (e.g. exa, firecrawl, parallel)
+                        example: exa
+                        nullable: true
+                        type: string
                     required:
                       - id
                       - upstream_id
@@ -14882,6 +15013,7 @@ paths:
                       - num_input_audio_prompt
                       - num_media_completion
                       - num_search_results
+                      - web_search_engine
                       - origin
                       - usage
                       - is_byok

.speakeasy/out.openapi.yaml

@@ -2,19 +2,20 @@ speakeasyVersion: 1.680.0
 sources:
     OpenRouter API:
         sourceNamespace: open-router-chat-completions-api
-        sourceRevisionDigest: sha256:3982892b2b8f82bfc2a26a0f6fcc9512b665a1051dc240a9cfa29001b9453aa9
-        sourceBlobDigest: sha256:727d3c1f7d36ffbf94c57b565536d8a16804eaef4c4043dd6c98152fc1629c8f
+        sourceRevisionDigest: sha256:b3a5e353c4475e477a187e50b4178cc6e85e3c93f0c7f5708bf2383e9e951ba4
+        sourceBlobDigest: sha256:eec16a3c2be924a3a45cfcbc28b70c92dc94cd9332d5fdc930ab22a229003c49
         tags:
             - latest
+            - speakeasy-sdk-regen-1776300046
             - 1.0.0
 targets:
     open-router:
         source: OpenRouter API
         sourceNamespace: open-router-chat-completions-api
-        sourceRevisionDigest: sha256:3982892b2b8f82bfc2a26a0f6fcc9512b665a1051dc240a9cfa29001b9453aa9
-        sourceBlobDigest: sha256:727d3c1f7d36ffbf94c57b565536d8a16804eaef4c4043dd6c98152fc1629c8f
+        sourceRevisionDigest: sha256:b3a5e353c4475e477a187e50b4178cc6e85e3c93f0c7f5708bf2383e9e951ba4
+        sourceBlobDigest: sha256:eec16a3c2be924a3a45cfcbc28b70c92dc94cd9332d5fdc930ab22a229003c49
         codeSamplesNamespace: open-router-python-code-samples
-        codeSamplesRevisionDigest: sha256:db86aed74d199f265e2e20442ef652dac0911c8a657ccb3e6614d56a26b8b44e
+        codeSamplesRevisionDigest: sha256:c265c6339f5c03b8e72b3417df8d101b76a5aa8f98218e1a85518f92a935c9bd
 workflow:
     workflowVersion: 1.0.0
     speakeasyVersion: 1.680.0

.speakeasy/workflow.lock

@@ -169,6 +169,36 @@ asyncio.run(main())
 
 <!-- No Custom HTTP Client [http-client] -->
 
+<!-- Start Pagination [pagination] -->
+## Pagination
+
+Some of the endpoints in this SDK support pagination. To use pagination, you make your SDK calls as usual, but the
+returned response object will have a `Next` method that can be called to pull down the next group of results. If the
+return value of `Next` is `None`, then there are no more pages to be fetched.
+
+Here's an example of one such pagination call:
+```python
+from openrouter import OpenRouter
+import os
+
+
+with OpenRouter(
+    http_referer="<value>",
+    x_open_router_title="<value>",
+    x_open_router_categories="<value>",
+    api_key=os.getenv("OPENROUTER_API_KEY", ""),
+) as open_router:
+
+    res = open_router.guardrails.list()
+
+    while res is not None:
+        # Handle items
+
+        res = res.next()
+
+```
+<!-- End Pagination [pagination] -->
+
 <!-- Start Resource Management [resource-management] -->
 ## Resource Management
 

README-PYPI.md

@@ -8,4 +8,14 @@ Based on:
 ### Generated
 - [python v0.0.16] .
 ### Releases
-- [PyPI v0.0.16] https://pypi.org/project/openrouter/0.0.16 - .
+- [PyPI v0.0.16] https://pypi.org/project/openrouter/0.0.16 - .
+
+## 2026-04-19 00:38:53
+### Changes
+Based on:
+- OpenAPI Doc  
+- Speakeasy CLI 1.680.0 (2.788.4) https://github.com/speakeasy-api/speakeasy
+### Generated
+- [python v0.9.2] .
+### Releases
+- [PyPI v0.9.2] https://pypi.org/project/openrouter/0.9.2 - .