136 pages for maxtokens.
Titles and paths first, then pages whose text carries it. Each row opens that page as this site last read it.
develop-tests
Claude Developer Platform · in the page
test-and-evaluate/develop-tests
…{ Model = Model.ClaudeOpus5_5, MaxTokens = 1024, Messages = [new UserMessageParam { Content = prompt }], }); return ContentText…
handle-streaming-refusals
Claude Developer Platform · in the page
test-and-evaluate/strengthen-guardrails/handle-streaming-refusals
…new MessageCreateParams { Model = Model.ClaudeOpus5_5, MaxTokens = 1024, Messages = [new UserMessageParam { Content = "Hello" }] }; try { await foreach (var streamEve…
reduce-latency
Claude Developer Platform · in the page
test-and-evaluate/strengthen-guardrails/reduce-latency
…new MessageCreateParams { Model = Model.ClaudeHaiku5_5, MaxTokens = 1024, OutputConfig = new() { Effort = Effort.Low }, Messages = [ new UserMessageParam…
Agent SDK reference - Python
Claude Code CLI · in the page
agent-sdk/python
…: categories: list[ContextUsageCategory] totalTokens: int maxTokens: int rawMaxTokens: int percentage: float model: str isAutoCompactEnabled: bool memoryFiles: list[dic…
Agent SDK reference - TypeScript
Claude Code CLI · in the page
agent-sdk/typescript
…ed" | "free" | "buffer" | "deferred"; }[]; totalTokens: number; maxTokens: number; rawMaxTokens: number; percentage: number; gridRows: { color: string; isFilled: boolean; categ…
Use the mods API
Claude Code CLI · in the page
plugins/mods/api
…One word needs few tokens, and the call gives up after 15 seconds maxTokens: 20, timeoutMs: 15000, }) // r.text exists only when the model answered, so check r.isAnswered first const lab…
Mods reference
Claude Code CLI · in the page
plugins/mods/reference
…sStderrTruncated` is `true` when one was cut. | | `$.model.complete` `maxTokens` | 1024 by default, up to 64,000 or the model's output limit | | `$.fs.read` and `$.fs.write` | 4 MiB for one file | | A…
Changelog
Claude Documentation · in the page
cowork/changelog
…default model and effort. * Fixed the token limit set with `inferenceMaxTokensPerWindow` not counting the tokens that subagents and conversation compaction use. People now reach the limit sooner, mos…
Code in Claude Desktop on 3P
Claude Documentation · in the page
third-party/claude-desktop/code
…s key; its version is managed by the app's own updater. | | `inferenceMaxTokensPerWindow`, `inferenceTokenWindowHours` | The token budget is shared across Cowork and Code sessions and enforced before…
Configuration reference
Claude Documentation · in the page
third-party/claude-desktop/configuration
…days) | Code retention period | Limits | Admin Console | | [`inferenceMaxTokensPerWindow`](#inferencemaxtokensperwindow) | Max tokens per window | Limits | Admin Console | | [`inferenceTokenWindowHour…
Configuration changelog
Claude Documentation · in the page
third-party/claude-desktop/configuration-changelog
…CredentialHelperTtlSec` | `integer` | Helper script TTL | | `inferenceMaxTokensPerWindow` | `integer` | Max tokens per window | | `inferenceTokenWindowHours` | `integer` | Token cap window | **Deprec…
MCP, plugins, skills, and hooks
Claude Documentation · in the page
third-party/claude-desktop/extensions
…/claude.com/docs/third-party/claude-desktop/configuration.md#inferencemaxtokensperwindow). A scan ends in one of these results: * **Pass**: the user can use the skill. * **Caution**: the scan found…
Features
Claude Documentation · in the page
third-party/claude-desktop/feature-matrix
…/claude.com/docs/third-party/claude-desktop/configuration.md#inferencemaxtokensperwindow) > * [User management via UI](https://claude.com/docs/third-party/claude-desktop/admin-console.md#connect-your-…
Deploy Claude Desktop on 3P with an LLM gateway
Claude Documentation · in the page
third-party/claude-desktop/gateway
…/claude.com/docs/third-party/claude-desktop/configuration.md#inferencemaxtokensperwindow) in the configuration reference. ## Troubleshoot **`gateway SSO: server does not advertise device_authorizati…
Build an MCP client
Model Context Protocol · in the page
docs/2024-11-05/develop/build-client
…der() > .model("claude-sonnet-4-20250514") > .maxTokens(1024) > .messages(messages) > .tools(tools) > .build(), > ) > > val finalTex…
Understanding MCP clients
Model Context Protocol · in the page
docs/2024-11-05/learn/client-concepts
…rt helping users find the best flights based on their preferences", maxTokens: 1500 } ``` #### Example: Flight Analysis Tool Consider a travel booking server with a tool called `findBestFlight` th…
Build an MCP client
Model Context Protocol · in the page
docs/2025-03-26/develop/build-client
…der() > .model("claude-sonnet-4-20250514") > .maxTokens(1024) > .messages(messages) > .tools(tools) > .build(), > ) > > val finalTex…
Understanding MCP clients
Model Context Protocol · in the page
docs/2025-03-26/learn/client-concepts
…rt helping users find the best flights based on their preferences", maxTokens: 1500 } ``` #### Example: Flight Analysis Tool Consider a travel booking server with a tool called `findBestFlight` th…
Build an MCP client
Model Context Protocol · in the page
docs/2025-06-18/develop/build-client
…der() > .model("claude-sonnet-4-20250514") > .maxTokens(1024) > .messages(messages) > .tools(tools) > .build(), > ) > > val finalTex…
Understanding MCP clients
Model Context Protocol · in the page
docs/2025-06-18/learn/client-concepts
…rt helping users find the best flights based on their preferences", maxTokens: 1500 } ``` #### Example: Flight Analysis Tool Consider a travel booking server with a tool called `findBestFlight` th…
Build an MCP client
Model Context Protocol · in the page
docs/2025-11-25/develop/build-client
…der() > .model("claude-sonnet-4-20250514") > .maxTokens(1024) > .messages(messages) > .tools(tools) > .build(), > ) > > val finalTex…
Understanding MCP clients
Model Context Protocol · in the page
docs/2025-11-25/learn/client-concepts
…rt helping users find the best flights based on their preferences", maxTokens: 1500 } ``` #### Example: Flight Analysis Tool Consider a travel booking server with a tool called `findBestFlight` th…
Build an MCP client
Model Context Protocol · in the page
docs/2026-07-28/develop/build-client
…sageCreateParams.builder() > .model(MODEL) > .maxTokens(MAX_TOKENS) > .messages(messages) > .tools(tools) > .build(), > ) > > val fi…
Understanding MCP clients
Model Context Protocol · in the page
docs/2026-07-28/learn/client-concepts
…rt helping users find the best flights based on their preferences", maxTokens: 1500 } ``` #### Example: Flight Analysis Tool Consider a travel booking server with a tool called `findBestFlight` th…
Build an MCP client
Model Context Protocol · in the page
docs/draft/develop/build-client
…sageCreateParams.builder() > .model(MODEL) > .maxTokens(MAX_TOKENS) > .messages(messages) > .tools(tools) > .build(), > ) > > val fi…
Understanding MCP clients
Model Context Protocol · in the page
docs/draft/learn/client-concepts
…rt helping users find the best flights based on their preferences", maxTokens: 1500 } ``` #### Example: Flight Analysis Tool Consider a travel booking server with a tool called `findBestFlight` th…
SEP-2322: Multi Round-Trip Requests
Model Context Protocol · in the page
seps/2322-MRTR
…}, "systemPrompt": "You are a helpful assistant.", "maxTokens": 100 } } } ``` The client would then send the responses in the following form: ```json5 theme={null} "inputResp…
Sampling
Model Context Protocol · in the page
specification/2024-11-05/client/sampling
…: 0.5 }, "systemPrompt": "You are a helpful assistant.", "maxTokens": 100 } } ``` **Response:** ```json theme={null} { "jsonrpc": "2.0", "id": 1, "result": { "role": "assista…
Sampling
Model Context Protocol · in the page
specification/2025-03-26/client/sampling
…: 0.5 }, "systemPrompt": "You are a helpful assistant.", "maxTokens": 100 } } ``` **Response:** ```json theme={null} { "jsonrpc": "2.0", "id": 1, "result": { "role": "assista…
Sampling
Model Context Protocol · in the page
specification/2025-06-18/client/sampling
…: 0.5 }, "systemPrompt": "You are a helpful assistant.", "maxTokens": 100 } } ``` **Response:** ```json theme={null} { "jsonrpc": "2.0", "id": 1, "result": { "role": "assista…
Schema Reference
Model Context Protocol · in the page
specification/2025-06-18/schema
…d-signature-symbol">;</span><br /> <span class="tsd-kind-property">maxTokens</span><span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signatu…
Sampling
Model Context Protocol · in the page
specification/2025-11-25/client/sampling
…: 0.5 }, "systemPrompt": "You are a helpful assistant.", "maxTokens": 100 } } ``` **Response:** ```json theme={null} { "jsonrpc": "2.0", "id": 1, "result": { "role": "assista…
Multi Round-Trip Requests
Model Context Protocol · in the page
specification/2026-07-28/basic/patterns/mrtr
…], "systemPrompt": "You are a helpful assistant.", "maxTokens": 100 } } } ``` #### InputResponses An [`InputResponses`](https://modelcontextprotocol.io/specification/2026-07-…
Sampling
Model Context Protocol · in the page
specification/2026-07-28/client/sampling
…u are a helpful assistant.", "includeContext": "thisServer", "maxTokens": 100 } } ``` **Client result (returned inside `inputResponses` on the retried request):** ```json theme={null} {…
Multi Round-Trip Requests
Model Context Protocol · in the page
specification/draft/basic/patterns/mrtr
…], "systemPrompt": "You are a helpful assistant.", "maxTokens": 100 } } } ``` #### InputResponses An [`InputResponses`](https://modelcontextprotocol.io/specification/draft/sc…
Sampling
Model Context Protocol · in the page
specification/draft/client/sampling
…u are a helpful assistant.", "includeContext": "thisServer", "maxTokens": 100 } } ``` **Client result (returned inside `inputResponses` on the retried request):** ```json theme={null} {…