Answer: To enable thinking tokens for Anthropic models in Aider, you must manually add configuration to your .aider.model.settings.yml model settings file, including a thinking block with type enabled and a budget_tokens value that you can adjust to change the target number of thinking tokens. Status: Confirmed Entry: tool/aider/models/anthropic-thinking-tokens Revision: 1 Digest: sha256:163906694815a134 (changes whenever the content changes) Timeline: Created: 2026-11-13T02:56:23Z Last changed: 2026-11-13T02:56:23Z Last verified: 2026-11-20T11:42:51Z Next check: 2026-11-21T11:42:51Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Unit | Source | As of settings file | .aider.model.settings.yml | | [1] | 2026-11-20 thinking type | enabled | | [1] | 2026-11-20 budget_tokens | 32000 | tokens | [1] | 2026-11-20 model name | anthropic/claude-3-7-sonnet-20250219 | | [1] | 2026-11-20 max_tokens | 64000 | tokens | [1] | 2026-11-20 Sources: [1] Aider. "aider.chat/docs/llms/anthropic.html". https://aider.chat/docs/llms/anthropic.html Role: primary. Accessed: 2026-11-20T11:42:51Z Quote: "add the following to your .aider.model.settings.yml model settings file" (Supports: settings file) Quote: "thinking : type : enabled" (Supports: thinking type) Quote: "budget_tokens : 32000 # Adjust this number" (Supports: budget_tokens) Quote: "- name : anthropic/claude-3-7-sonnet-20250219" (Supports: model name) Quote: "max_tokens : 64000" (Supports: max_tokens) Published: 2026-04-25T16:45:23Z Snapshot SHA-256: a7de9ed7c64be35dff589b2dad4808308cd3956ff12202e1276065e0c80821ab (captured 2026-11-13T02:56:23Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-13T02:56:23Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T11:42:51Z. No independent second source is configured for this entry Last successful check: 2026-11-20T11:42:51Z Last attempt: 2026-11-20T11:42:51Z Notes and limitations: Extracted automatically from a single official source (section "Thinking tokens"). Related: https://latestn.com/tool/aider/models/bedrock-available-models Which models are available for Aider on Amazon Bedrock? https://latestn.com/tool/aider/models/benchmark-edit-format What edit formats does Aider use in its benchmarks? https://latestn.com/tool/aider/models/benchmarking-results-notes What are the notes on benchmarking results for Aider's code editing leaderboard? https://latestn.com/tool/aider/memory-and-context/repo-map-context How does Aider use a repository map to provide context to the LLM? https://latestn.com/tool/aider/memory-and-context/set-ollama-context-window-size How do I set the context window size for Ollama models in Aider? https://latestn.com/tool/aider/models/accepts-settings-compatibility Which reasoning models does Aider support and how does accepts_settings work? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-13T02:56:23Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/aider/models/anthropic-thinking-tokens/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/aider/models/anthropic-thinking-tokens POST: https://latestn.com/dispute/tool/aider/models/anthropic-thinking-tokens with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/aider/models/anthropic-thinking-tokens?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I enable thinking tokens for Anthropic models in Aider? Revision 1, last verified 2026-11-20T11:42:51Z. https://latestn.com/tool/aider/models/anthropic-thinking-tokens (accessed 2026-11-21T10:01:52Z). @misc{LatestN_tool_aider_models_anthropic_thinking_tokens_r1, title = {How do I enable thinking tokens for Anthropic models in Aider?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/aider/models/anthropic-thinking-tokens}}, note = {Revision 1; digest sha256:163906694815a134; last verified 2026-11-20T11:42:51Z; accessed 2026-11-21T10:01:52Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/aider/models/anthropic-thinking-tokens