timbal 2.8.2__tar.gz → 2.8.4__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of timbal might be problematic. Click here for more details.

Files changed (315) hide show
  1. {timbal-2.8.2 → timbal-2.8.4}/PKG-INFO +1 -1
  2. {timbal-2.8.2 → timbal-2.8.4}/pyproject.toml +6 -0
  3. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/_version.py +2 -2
  4. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/llm/messages.py +14 -1
  5. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/mcp.py +15 -2
  6. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/memory_compaction.py +1 -1
  7. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/models.py +4 -0
  8. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/llm_base.py +2 -2
  9. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/rubric.py +2 -2
  10. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/guardrails/builtins/injection.py +1 -1
  11. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/guardrails/builtins/judge.py +1 -1
  12. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/guardrails/builtins/topic.py +2 -2
  13. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/guardrails/rubric.py +1 -1
  14. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/models.yaml +137 -27
  15. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/__init__.py +63 -0
  16. timbal-2.8.4/python/timbal/tools/_oauth_store.py +267 -0
  17. timbal-2.8.4/python/timbal/tools/notion.py +1282 -0
  18. timbal-2.8.4/python/timbal/tools/qlik.py +886 -0
  19. timbal-2.8.4/python/timbal/tools/snowflake.py +952 -0
  20. {timbal-2.8.2 → timbal-2.8.4}/.gitignore +0 -0
  21. {timbal-2.8.2 → timbal-2.8.4}/LICENSE +0 -0
  22. {timbal-2.8.2 → timbal-2.8.4}/README.md +0 -0
  23. {timbal-2.8.2 → timbal-2.8.4}/docs/api-reference/ace/chat-completions.mdx +0 -0
  24. {timbal-2.8.2 → timbal-2.8.4}/docs/api-reference/ace/create-from-workforce.mdx +0 -0
  25. {timbal-2.8.2 → timbal-2.8.4}/docs/api-reference/ace/jobs/cancel.mdx +0 -0
  26. {timbal-2.8.2 → timbal-2.8.4}/docs/api-reference/ace/jobs/create.mdx +0 -0
  27. {timbal-2.8.2 → timbal-2.8.4}/docs/api-reference/ace/jobs/get.mdx +0 -0
  28. {timbal-2.8.2 → timbal-2.8.4}/docs/api-reference/ace/jobs/list.mdx +0 -0
  29. {timbal-2.8.2 → timbal-2.8.4}/docs/api-reference/ace/jobs/retry.mdx +0 -0
  30. {timbal-2.8.2 → timbal-2.8.4}/docs/api-reference/ace/link.mdx +0 -0
  31. {timbal-2.8.2 → timbal-2.8.4}/docs/api-reference/ace/list-context-vars.mdx +0 -0
  32. {timbal-2.8.2 → timbal-2.8.4}/docs/api-reference/ace/list-policies.mdx +0 -0
  33. {timbal-2.8.2 → timbal-2.8.4}/docs/api-reference/ace/unlink.mdx +0 -0
  34. {timbal-2.8.2 → timbal-2.8.4}/pyrightconfig.json +0 -0
  35. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/__init__.py +0 -0
  36. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/_openai_audio.py +0 -0
  37. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/_slots.py +0 -0
  38. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/__init__.py +0 -0
  39. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/__main__.py +0 -0
  40. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/cli_utils.py +0 -0
  41. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/cst_utils.py +0 -0
  42. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/flow.py +0 -0
  43. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/format.py +0 -0
  44. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/guardrail_specs.py +0 -0
  45. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/library.py +0 -0
  46. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/model_discovery.py +0 -0
  47. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/test.py +0 -0
  48. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/tool_discovery.py +0 -0
  49. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/transformers/__init__.py +0 -0
  50. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/transformers/add_edge.py +0 -0
  51. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/transformers/add_guardrail.py +0 -0
  52. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/transformers/add_mcp.py +0 -0
  53. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/transformers/add_step.py +0 -0
  54. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/transformers/add_tool.py +0 -0
  55. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/transformers/remove_edge.py +0 -0
  56. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/transformers/remove_guardrail.py +0 -0
  57. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/transformers/remove_step.py +0 -0
  58. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/transformers/remove_tool.py +0 -0
  59. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/transformers/set_config.py +0 -0
  60. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/transformers/set_param.py +0 -0
  61. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/codegen/transformers/set_position.py +0 -0
  62. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/collectors/__init__.py +0 -0
  63. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/collectors/base.py +0 -0
  64. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/collectors/harmony_leak.py +0 -0
  65. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/collectors/impl/__init__.py +0 -0
  66. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/collectors/impl/anthropic.py +0 -0
  67. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/collectors/impl/default.py +0 -0
  68. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/collectors/impl/message.py +0 -0
  69. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/collectors/impl/openai.py +0 -0
  70. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/collectors/impl/string.py +0 -0
  71. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/collectors/impl/timbal.py +0 -0
  72. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/collectors/registry.py +0 -0
  73. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/__init__.py +0 -0
  74. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/agent.py +0 -0
  75. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/attachment_limit.py +0 -0
  76. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/continuation.py +0 -0
  77. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/fallback_model.py +0 -0
  78. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/llm/__init__.py +0 -0
  79. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/llm/auto.py +0 -0
  80. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/llm/chat_completions.py +0 -0
  81. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/llm/clients.py +0 -0
  82. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/llm/registry.py +0 -0
  83. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/llm/responses.py +0 -0
  84. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/llm/retry.py +0 -0
  85. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/llm/router.py +0 -0
  86. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/provider_errors.py +0 -0
  87. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/runnable.py +0 -0
  88. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/session_scheduler.py +0 -0
  89. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/skill.py +0 -0
  90. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/test_model.py +0 -0
  91. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/tool.py +0 -0
  92. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/tool_result_offload.py +0 -0
  93. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/tool_set.py +0 -0
  94. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/core/workflow.py +0 -0
  95. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/errors.py +0 -0
  96. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/__init__.py +0 -0
  97. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/cli.py +0 -0
  98. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/display.py +0 -0
  99. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/fixtures/agent.py +0 -0
  100. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/fixtures/eval_examples.yaml +0 -0
  101. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/fixtures/eval_flow_validators.yaml +0 -0
  102. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/fixtures/eval_negations.yaml +0 -0
  103. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/fixtures/eval_parallel.yaml +0 -0
  104. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/fixtures/eval_subagent.yaml +0 -0
  105. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/fixtures/eval_transforms.yaml +0 -0
  106. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/fixtures/test_invalid_validator.yaml +0 -0
  107. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/models.py +0 -0
  108. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/reporters.py +0 -0
  109. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/runner.py +0 -0
  110. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/utils.py +0 -0
  111. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/__init__.py +0 -0
  112. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/_spans.py +0 -0
  113. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/base.py +0 -0
  114. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/comparison_base.py +0 -0
  115. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/contains.py +0 -0
  116. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/contains_all.py +0 -0
  117. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/contains_any.py +0 -0
  118. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/context.py +0 -0
  119. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/email.py +0 -0
  120. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/ends_with.py +0 -0
  121. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/eq.py +0 -0
  122. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/gt.py +0 -0
  123. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/gte.py +0 -0
  124. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/json.py +0 -0
  125. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/language.py +0 -0
  126. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/length.py +0 -0
  127. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/lt.py +0 -0
  128. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/lte.py +0 -0
  129. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/max_length.py +0 -0
  130. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/min_length.py +0 -0
  131. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/not_null.py +0 -0
  132. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/parallel.py +0 -0
  133. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/pattern.py +0 -0
  134. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/prompt.py +0 -0
  135. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/semantic.py +0 -0
  136. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/seq.py +0 -0
  137. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/starts_with.py +0 -0
  138. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/evals/validators/type.py +0 -0
  139. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/guardrails/__init__.py +0 -0
  140. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/guardrails/apply.py +0 -0
  141. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/guardrails/builtins/__init__.py +0 -0
  142. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/guardrails/builtins/keywords.py +0 -0
  143. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/guardrails/builtins/length.py +0 -0
  144. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/guardrails/builtins/moderate.py +0 -0
  145. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/guardrails/builtins/pii.py +0 -0
  146. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/guardrails/builtins/secrets.py +0 -0
  147. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/guardrails/judge_llm.py +0 -0
  148. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/guardrails/presets.py +0 -0
  149. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/guardrails/runner.py +0 -0
  150. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/guardrails/testing.py +0 -0
  151. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/guardrails/trace.py +0 -0
  152. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/guardrails/types.py +0 -0
  153. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/logs.py +0 -0
  154. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/platform/__init__.py +0 -0
  155. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/platform/_http_session.py +0 -0
  156. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/platform/integrations.py +0 -0
  157. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/platform/knowledge_bases/__init__.py +0 -0
  158. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/platform/knowledge_bases/query.py +0 -0
  159. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/platform/tool_proxy.py +0 -0
  160. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/platform/types.py +0 -0
  161. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/platform/utils.py +0 -0
  162. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/server/__init__.py +0 -0
  163. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/server/__main__.py +0 -0
  164. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/server/capacity.py +0 -0
  165. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/server/http.py +0 -0
  166. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/server/jobs.py +0 -0
  167. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/server/livekit_call_control.py +0 -0
  168. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/server/livekit_session.py +0 -0
  169. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/server/livekit_sip.py +0 -0
  170. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/server/playground.py +0 -0
  171. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/server/recording_upload.py +0 -0
  172. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/server/rtc.py +0 -0
  173. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/server/single_session.py +0 -0
  174. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/server/telephony.py +0 -0
  175. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/server/voice.html +0 -0
  176. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/server/voice.py +0 -0
  177. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/state/__init__.py +0 -0
  178. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/state/background.py +0 -0
  179. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/state/config.py +0 -0
  180. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/state/config_loader.py +0 -0
  181. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/state/context.py +0 -0
  182. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/state/dependency_analyzer.py +0 -0
  183. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/state/tracing/__init__.py +0 -0
  184. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/state/tracing/exporters/__init__.py +0 -0
  185. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/state/tracing/exporters/otel.py +0 -0
  186. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/state/tracing/providers/__init__.py +0 -0
  187. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/state/tracing/providers/base.py +0 -0
  188. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/state/tracing/providers/in_memory.py +0 -0
  189. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/state/tracing/providers/jsonl.py +0 -0
  190. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/state/tracing/providers/platform.py +0 -0
  191. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/state/tracing/providers/sqlite.py +0 -0
  192. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/state/tracing/span.py +0 -0
  193. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/state/tracing/trace.py +0 -0
  194. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/state/tracing/uploads.py +0 -0
  195. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/_creds.py +0 -0
  196. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/aircall.py +0 -0
  197. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/asana.py +0 -0
  198. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/bash.py +0 -0
  199. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/cala.py +0 -0
  200. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/cloudflare.py +0 -0
  201. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/connectif.py +0 -0
  202. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/covermanager.py +0 -0
  203. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/deepgram.py +0 -0
  204. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/dynamics_business_central.py +0 -0
  205. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/dynamics_sales.py +0 -0
  206. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/edit.py +0 -0
  207. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/elasticsearch.py +0 -0
  208. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/elevenlabs.py +0 -0
  209. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/excel.py +0 -0
  210. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/fal.py +0 -0
  211. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/fathom.py +0 -0
  212. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/firecrawl.py +0 -0
  213. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/freematica.py +0 -0
  214. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/freematica_contracts.py +0 -0
  215. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/freematica_people.py +0 -0
  216. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/freematica_purchasing.py +0 -0
  217. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/freematica_sales.py +0 -0
  218. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/gemini_images.py +0 -0
  219. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/gmail.py +0 -0
  220. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/google_analytics.py +0 -0
  221. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/google_business.py +0 -0
  222. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/google_calendar.py +0 -0
  223. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/google_docs.py +0 -0
  224. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/google_drive.py +0 -0
  225. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/google_maps.py +0 -0
  226. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/google_merchant_center.py +0 -0
  227. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/google_search_console.py +0 -0
  228. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/google_sheets.py +0 -0
  229. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/happy_scribe.py +0 -0
  230. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/higgsfield.py +0 -0
  231. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/hubspot.py +0 -0
  232. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/interaction.py +0 -0
  233. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/jira.py +0 -0
  234. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/klaviyo.py +0 -0
  235. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/knowledge_base.py +0 -0
  236. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/krea.py +0 -0
  237. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/lancedb.py +0 -0
  238. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/linkedin.py +0 -0
  239. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/mongodb.py +0 -0
  240. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/netsuite.py +0 -0
  241. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/onedrive.py +0 -0
  242. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/openai_audio.py +0 -0
  243. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/outlook.py +0 -0
  244. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/parallel.py +0 -0
  245. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/pinecone.py +0 -0
  246. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/powerbi.py +0 -0
  247. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/quiver_ai.py +0 -0
  248. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/read.py +0 -0
  249. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/replicate.py +0 -0
  250. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/resend.py +0 -0
  251. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/salesforce.py +0 -0
  252. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/scraperapi.py +0 -0
  253. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/sharepoint.py +0 -0
  254. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/shopify.py +0 -0
  255. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/slack.py +0 -0
  256. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/stripe.py +0 -0
  257. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/tavily.py +0 -0
  258. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/web_search.py +0 -0
  259. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/write.py +0 -0
  260. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/xai.py +0 -0
  261. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/zendesk.py +0 -0
  262. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/tools/zoho_crm.py +0 -0
  263. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/__init__.py +0 -0
  264. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/approval.py +0 -0
  265. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/content/__init__.py +0 -0
  266. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/content/base.py +0 -0
  267. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/content/custom.py +0 -0
  268. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/content/file.py +0 -0
  269. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/content/text.py +0 -0
  270. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/content/thinking.py +0 -0
  271. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/content/tool_result.py +0 -0
  272. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/content/tool_use.py +0 -0
  273. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/events/__init__.py +0 -0
  274. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/events/approval.py +0 -0
  275. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/events/base.py +0 -0
  276. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/events/delta.py +0 -0
  277. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/events/guardrail.py +0 -0
  278. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/events/interaction.py +0 -0
  279. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/events/output.py +0 -0
  280. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/events/start.py +0 -0
  281. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/file.py +0 -0
  282. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/message.py +0 -0
  283. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/types/run_status.py +0 -0
  284. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/utils/__init__.py +0 -0
  285. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/utils/import_spec.py +0 -0
  286. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/utils/model.py +0 -0
  287. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/utils/net.py +0 -0
  288. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/utils/schema.py +0 -0
  289. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/utils/serialization.py +0 -0
  290. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/__init__.py +0 -0
  291. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/_whisper_features.py +0 -0
  292. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/ambience.py +0 -0
  293. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/config.py +0 -0
  294. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/deepgram.py +0 -0
  295. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/deepgram_tts.py +0 -0
  296. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/elevenlabs.py +0 -0
  297. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/endpointing.py +0 -0
  298. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/eou.py +0 -0
  299. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/events.py +0 -0
  300. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/fish_audio.py +0 -0
  301. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/livekit.py +0 -0
  302. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/metrics.py +0 -0
  303. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/munsit.py +0 -0
  304. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/namo.py +0 -0
  305. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/openai.py +0 -0
  306. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/playback.py +0 -0
  307. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/providers.py +0 -0
  308. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/realtime.py +0 -0
  309. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/recording.py +0 -0
  310. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/session.py +0 -0
  311. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/smart_turn.py +0 -0
  312. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/telephony.py +0 -0
  313. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/turn_detection.py +0 -0
  314. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/vad.py +0 -0
  315. {timbal-2.8.2 → timbal-2.8.4}/python/timbal/voice/webrtc.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.5
2
2
  Name: timbal
3
- Version: 2.8.2
3
+ Version: 2.8.4
4
4
  Summary: Simple, performant, battle-tested framework for building reliable AI applications
5
5
  Project-URL: Source, https://github.com/timbal-ai/timbal
6
6
  Author-email: Timbal <team@timbal.ai>
@@ -129,6 +129,12 @@ path = "python"
129
129
  [tool.hatch.version]
130
130
  source = "vcs"
131
131
 
132
+ # Versions come from git tags. On a release branch (`release/2.8`) the next version is the next patch
133
+ # (2.8.5.devN after v2.8.4); anywhere else (main, feature branches) it is the next minor (2.9.0.devN),
134
+ # so main never builds with a version a release line will publish. See RELEASING.md.
135
+ [tool.hatch.version.raw-options]
136
+ version_scheme = "release-branch-semver"
137
+
132
138
  [tool.hatch.build.hooks.vcs]
133
139
  version-file = "python/timbal/_version.py"
134
140
 
@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
18
18
  commit_id: str | None
19
19
  __commit_id__: str | None
20
20
 
21
- __version__ = version = '2.8.2'
22
- __version_tuple__ = version_tuple = (2, 8, 2)
21
+ __version__ = version = '2.8.4'
22
+ __version_tuple__ = version_tuple = (2, 8, 4)
23
23
 
24
24
  __commit_id__ = commit_id = None
@@ -1,5 +1,6 @@
1
1
  """Anthropic Messages API request adapter (anthropic)."""
2
2
 
3
+ import re
3
4
  from collections.abc import AsyncIterator, Callable
4
5
  from typing import TYPE_CHECKING, Any
5
6
 
@@ -12,6 +13,16 @@ if TYPE_CHECKING:
12
13
  from ..runnable import Runnable
13
14
 
14
15
 
16
+ # Claude models whose API rejects non-default sampling parameters with a 400 (Opus 4.7+, the Opus/Sonnet/Haiku 5
17
+ # generations, Fable and Mythos). Anthropic's model docs say to omit `temperature`, `top_p` and `top_k` for them.
18
+ _NO_SAMPLING_PARAMS = re.compile(r"^claude-(?:(?:fable|mythos)-|opus-(?:4-[78]|5)|sonnet-5|haiku-5)")
19
+
20
+
21
+ def rejects_temperature(model_name: str) -> bool:
22
+ """Whether the Anthropic API rejects a ``temperature`` value for this model (dated ids included)."""
23
+ return _NO_SAMPLING_PARAMS.match(model_name) is not None
24
+
25
+
15
26
  def prepare_messages_request(
16
27
  *,
17
28
  client: Any,
@@ -41,7 +52,9 @@ def prepare_messages_request(
41
52
  if anthropic_tools:
42
53
  anthropic_kwargs["tools"] = anthropic_tools
43
54
 
44
- if temperature is not None:
55
+ # Deterministic callers (LLM judges pin temperature=0.0) would 400 on these models, so the value is dropped
56
+ # for them. Sending it anyway via ``model_params={"temperature": ...}`` still reaches the API unchanged.
57
+ if temperature is not None and not rejects_temperature(model_name):
45
58
  anthropic_kwargs["temperature"] = temperature
46
59
 
47
60
  # Server-side automatic prompt caching (anthropic SDK >= 0.83): the API
@@ -363,6 +363,15 @@ class MCPServer(ToolSet):
363
363
  url: str | None = None
364
364
  headers: dict[str, str] = Field(default_factory=dict)
365
365
 
366
+ auth: httpx.Auth | None = Field(default=None, exclude=True)
367
+ """``httpx.Auth`` applied to every HTTP request, for credentials that rotate during a
368
+ session (``headers`` are fixed at connect). E.g. ``SnowflakeAuth`` re-mints its
369
+ key-pair JWT before the one-hour expiry and retries once on 401.
370
+
371
+ The auth flow runs in the transport's owner task, which has an empty context (no
372
+ ``RunContext``). If the object defines ``async prepare()``, it is awaited in the
373
+ caller's context before every request; resolve anything identity-bound there."""
374
+
366
375
  timeout: float | None = DEFAULT_TIMEOUT_SECONDS
367
376
  """Seconds to wait for the server to answer a request on an established session
368
377
  (``tools/list``, ``tools/call``). Defaults to ``DEFAULT_TIMEOUT_SECONDS`` (10 minutes);
@@ -439,8 +448,8 @@ class MCPServer(ToolSet):
439
448
  @model_validator(mode="after")
440
449
  def _validate_transport_fields(self) -> "MCPServer":
441
450
  if self.service is not None:
442
- if self.transport != "http" or self.url is not None or self.headers:
443
- raise ValueError("service='api' requires HTTP transport without url or headers")
451
+ if self.transport != "http" or self.url is not None or self.headers or self.auth is not None:
452
+ raise ValueError("service='api' requires HTTP transport without url, headers or auth")
444
453
  if self.transport == "stdio":
445
454
  if not self.command:
446
455
  raise ValueError("'command' is required for stdio transport")
@@ -520,6 +529,7 @@ class MCPServer(ToolSet):
520
529
  assert self.url is not None
521
530
  async with httpx.AsyncClient(
522
531
  headers=self.headers if self.headers else None,
532
+ auth=self.auth,
523
533
  timeout=self._http_timeout(),
524
534
  follow_redirects=True,
525
535
  ) as http_client:
@@ -720,6 +730,9 @@ class MCPServer(ToolSet):
720
730
  """
721
731
  if timeout is _USE_SERVER_TIMEOUT:
722
732
  timeout = self.timeout
733
+ prepare = getattr(self.auth, "prepare", None)
734
+ if prepare is not None:
735
+ await prepare()
723
736
  for attempt in (1, 2):
724
737
  session = await self._connect()
725
738
  owner = self._session_task
@@ -715,7 +715,7 @@ def summarize(
715
715
  threshold: Trigger summarization when message count exceeds this.
716
716
  model: Model for summarization. Defaults to None, which uses the
717
717
  agent's own model. Override with a cheaper model like
718
- 'openai/gpt-5-mini' to reduce cost.
718
+ 'anthropic/claude-haiku-5-5' to reduce cost.
719
719
  keep_last_n: Number of recent messages to keep unsummarized.
720
720
  max_summary_tokens: Maximum tokens for the summary response.
721
721
  preserve_user_messages: Carry the user's messages from the summarized region
@@ -148,6 +148,7 @@ def has_cache_write_pricing(model_id: str) -> bool:
148
148
  # ---------------------------------------------------------------------------
149
149
  # Model type with provider prefixes
150
150
  Model = Literal[
151
+ "anthropic/claude-fable-5-2",
151
152
  "anthropic/claude-fable-5-1",
152
153
  "anthropic/claude-fable-5",
153
154
  "anthropic/claude-opus-5-5",
@@ -162,8 +163,11 @@ Model = Literal[
162
163
  "anthropic/claude-sonnet-4-5",
163
164
  "anthropic/claude-haiku-5-5",
164
165
  "anthropic/claude-haiku-4-5",
166
+ "openai/gpt-6.2-astra",
167
+ "openai/gpt-6.2-sol",
165
168
  "openai/gpt-6-astra",
166
169
  "openai/gpt-6.1-sol",
170
+ "openai/gpt-6.1-terra",
167
171
  "openai/gpt-6-sol",
168
172
  "openai/gpt-6-luna",
169
173
  "openai/gpt-5.5",
@@ -22,7 +22,7 @@ class LLMValidator(BaseValidator):
22
22
  Attributes:
23
23
  system_prompt: System prompt for the LLM. Can be customized in YAML.
24
24
  Subclasses should provide a default value.
25
- model: LLM model to use for validation. Defaults to "openai/gpt-5-mini".
25
+ model: LLM model to use for validation. Defaults to "anthropic/claude-haiku-5-5".
26
26
  Can be customized in YAML.
27
27
 
28
28
  Subclasses should implement:
@@ -31,7 +31,7 @@ class LLMValidator(BaseValidator):
31
31
  """
32
32
 
33
33
  system_prompt: str # Must be set in subclass or YAML
34
- model: str = "openai/gpt-5-mini" # Can be overridden in YAML
34
+ model: str = "anthropic/claude-haiku-5-5" # Can be overridden in YAML
35
35
 
36
36
  @abstractmethod
37
37
  def get_user_prompt(self, actual_value: Any) -> str:
@@ -33,7 +33,7 @@ class RubricValidator(BaseValidator):
33
33
  name: recommendations
34
34
  weight: 2
35
35
  pass_threshold: 0.75
36
- model: openai/gpt-5-mini
36
+ model: anthropic/claude-haiku-5-5
37
37
  context: "The agent produced a price-comparison report."
38
38
 
39
39
  # Markdown rubric (bullet lines become criteria):
@@ -47,7 +47,7 @@ class RubricValidator(BaseValidator):
47
47
  """
48
48
 
49
49
  name: Literal["rubric!"] = "rubric!" # type: ignore
50
- model: SkipValidation[Any] = "openai/gpt-5-mini"
50
+ model: SkipValidation[Any] = "anthropic/claude-haiku-5-5"
51
51
  """Judge model. Use a small, cheap model."""
52
52
  pass_threshold: float = 1.0
53
53
  """Weighted fraction of criteria that must pass (1.0 = all)."""
@@ -64,7 +64,7 @@ class PromptInjection(Guardrail):
64
64
  stages: set[GuardrailStage] = Field(default_factory=lambda: {GuardrailStage.INPUT})
65
65
  action: str = "block"
66
66
  model: Any = None
67
- """Optional LLM classifier model — a model string (e.g. 'openai/gpt-5-mini'), or any
67
+ """Optional LLM classifier model — a model string (e.g. 'anthropic/claude-haiku-5-5'), or any
68
68
  model instance the router accepts (FallbackModel, TestModel). None = patterns only."""
69
69
  max_classifier_chars: int = 8_000
70
70
  """Input beyond this is truncated before classification (patterns still see all of it)."""
@@ -58,7 +58,7 @@ class LLMJudge(Guardrail):
58
58
  """Rubric mode: weighted fraction of criteria that must pass (1.0 = all)."""
59
59
  rubric_context: str | None = None
60
60
  """Optional task description shown to every rubric judge."""
61
- model: Any = "openai/gpt-5-mini"
61
+ model: Any = "anthropic/claude-haiku-5-5"
62
62
  max_chars: int = 16_000
63
63
 
64
64
  def __init__(self, criteria: str | None = None, **kwargs: Any) -> None:
@@ -21,7 +21,7 @@ class TopicGuard(Guardrail):
21
21
  ```python
22
22
  TopicGuard(allow=["billing", "shipping"],
23
23
  blocked_message="I can only help with billing and shipping.")
24
- TopicGuard(deny=["medical advice", "legal advice"], model="openai/gpt-5-mini")
24
+ TopicGuard(deny=["medical advice", "legal advice"], model="anthropic/claude-haiku-5-5")
25
25
  ```
26
26
  """
27
27
 
@@ -32,7 +32,7 @@ class TopicGuard(Guardrail):
32
32
  """Topics the agent may discuss. Anything else is off-topic."""
33
33
  deny: list[str] = Field(default_factory=list)
34
34
  """Topics that are always off-topic (checked in addition to allow)."""
35
- model: Any = "openai/gpt-5-mini"
35
+ model: Any = "anthropic/claude-haiku-5-5"
36
36
  """Classifier model: a model string, or any model instance the router accepts."""
37
37
  max_chars: int = 8_000
38
38
 
@@ -195,7 +195,7 @@ async def grade_rubric(
195
195
  rubric: Any,
196
196
  text: str,
197
197
  *,
198
- model: Any = "openai/gpt-5-mini",
198
+ model: Any = "anthropic/claude-haiku-5-5",
199
199
  context: str | None = None,
200
200
  pass_threshold: float = 1.0,
201
201
  max_concurrency: int = 8,
@@ -31,11 +31,31 @@
31
31
  # ultrafast: 6.0
32
32
 
33
33
  models:
34
+ - id: anthropic/claude-fable-5-2
35
+ provider: anthropic
36
+ display_name: Claude Fable 5.2
37
+ description: Anthropic's most capable generally available model — successor to Fable 5.1 for long-running agentic coding,
38
+ knowledge work, and research, at a 20% lower price.
39
+ notes: 'Released Nov 9, 2026; verified 2026-11-20 against the model reference and pricing. Adaptive thinking is always on
40
+ (disabled/budgeted thinking return 400); effort accepts low|medium|high|xhigh|max, default high. `tool_choice`
41
+ any/tool return 400 — use strict tools or structured outputs instead. Omit temperature, top_p, top_k. Cache reads
42
+ are $0.20 per 1M tokens (0.025x input). Batch is $4/$20. Fast mode (Claude API) is $16/$80 and cannot be combined
43
+ with Batch. 1M context at standard rates, 128K max output, Jun 2026 knowledge cutoff. Requires 30-day data retention;
44
+ not available under ZDR. Refusals return stop_reason refusal; server-side fallback targets are Opus 4.8 and Opus 5.'
45
+ input_price: 8.0
46
+ output_price: 40.0
47
+ cached_input_price: 0.2
48
+ cache_write_price: 10.0
49
+ cache_write_1h_price: 16.0
50
+ service_tiers:
51
+ fast: 2.0
52
+ context_window: 1000000
53
+ capabilities: [vision, tools, reasoning]
34
54
  - id: anthropic/claude-fable-5-1
35
55
  provider: anthropic
36
56
  display_name: Claude Fable 5.1
37
- description: Anthropic's most capable generally available model — successor to Fable 5 for long-running agentic coding,
38
- knowledge work, and research, with fewer false-positive safety refusals in multi-turn agent loops.
57
+ description: Previous Fable generation for long-running agentic coding, knowledge work, and research, with fewer
58
+ false-positive safety refusals in multi-turn agent loops. Superseded by Fable 5.2 at a 20% lower price.
39
59
  notes: Adaptive thinking is always on. Cache reads are $0.25 per 1M tokens (0.025x input).
40
60
  `tool_choice` any/tool return 400 — use strict tools or structured outputs instead. Requires 30-day data retention;
41
61
  not available under ZDR.
@@ -167,6 +187,7 @@ models:
167
187
  provider: anthropic
168
188
  display_name: Claude Opus 4.5
169
189
  description: Previous-generation Opus model with high intelligence for complex reasoning tasks.
190
+ notes: "Status checked 2026-11-20 against Anthropic's deprecations page: active, retirement not sooner than November 24, 2026. Prefer claude-opus-5-5 or claude-opus-4-8."
170
191
  input_price: 5.0
171
192
  output_price: 25.0
172
193
  cached_input_price: 0.5
@@ -227,6 +248,7 @@ models:
227
248
  display_name: Claude Haiku 4.5
228
249
  description: Previous Haiku generation for office document processing and high-volume business analysis. Superseded by
229
250
  Haiku 5.5.
251
+ notes: "Status checked 2026-11-20 against Anthropic's deprecations page: listed active with retirement 'not sooner than October 15, 2026', a date that has already passed, so retirement may be announced at any time. Prefer claude-haiku-5-5."
230
252
  input_price: 1.0
231
253
  output_price: 5.0
232
254
  cached_input_price: 0.1
@@ -234,11 +256,66 @@ models:
234
256
  cache_write_1h_price: 2.0
235
257
  context_window: 200000
236
258
  capabilities: [vision, tools, reasoning]
259
+ - id: openai/gpt-6.2-astra
260
+ provider: openai
261
+ display_name: GPT-6.2 Astra
262
+ description: OpenAI's flagship model for the hardest end-to-end work — complex reasoning, agentic coding, computer
263
+ use, research, and document creation. Successor to GPT-6 Astra at 20% lower prices.
264
+ notes: 'Released Nov 17, 2026; verified 2026-11-20 against the model reference and API pricing. Standard short-context
265
+ pricing is $8/$40 per 1M tokens; cached input $0.40, 30m cache writes $10 (12h writes $20). Prompts over 272K input
266
+ tokens bill the full request at long-context rates ($16/$60, cached $0.80, cache writes $20). Batch is 50% of
267
+ Standard; Fast mode (`service_tier: "fast"`) is 2x. Ultrafast is promotionally 3x through Feb 28, 2027 and 6x from
268
+ Mar 1, 2027 (the 6x list rate is catalogued). Flex is not supported. `reasoning.effort` accepts
269
+ low|medium|high|xhigh|max (`none` returns 400; no default published — start with medium). Function tools require
270
+ the Responses API (Timbal default). 1.05M context (922K max input), 128K max output, May 18, 2026 knowledge cutoff.
271
+ Supports ZDR for approved organizations. Regional processing adds 10%.'
272
+ input_price: 8.0
273
+ output_price: 40.0
274
+ cached_input_price: 0.4
275
+ cache_write_price: 10.0
276
+ long_context:
277
+ threshold: 272000
278
+ input_price: 16.0
279
+ output_price: 60.0
280
+ cached_input_price: 0.8
281
+ cache_write_price: 20.0
282
+ service_tiers:
283
+ fast: 2.0
284
+ ultrafast: 6.0
285
+ context_window: 1050000
286
+ capabilities: [vision, tools, reasoning]
287
+ - id: openai/gpt-6.2-sol
288
+ provider: openai
289
+ display_name: GPT-6.2 Sol
290
+ description: OpenAI model for complex coding, computer use, and professional work at a lower cost than Astra.
291
+ notes: 'Released Nov 17, 2026; verified 2026-11-20 against the model reference and API pricing. Standard rates per 1M
292
+ tokens are $2 input, $0.10 cache reads, $2.50 cache writes (30m; 12h writes $5), and $10 output. Above 272K input
293
+ tokens the full request costs $4/$15, cached $0.20, cache writes $5. Batch is 50% of Standard; Fast costs 2x.
294
+ Ultrafast is promotionally 3x through Feb 28, 2027 and 6x from Mar 1, 2027 (the 6x list rate is catalogued).
295
+ Flex is not supported. Reasoning accepts low, medium, high, xhigh, max; `none` returns 400 and no default is
296
+ published (start with medium). Tool calling requires Responses; Chat Completions supports text without tools.
297
+ 1.05M context (922K max input), 128K max output, Jun 1, 2026 knowledge cutoff. Supports ZDR for approved
298
+ organizations. Regional processing adds 10%.'
299
+ input_price: 2.0
300
+ output_price: 10.0
301
+ cached_input_price: 0.1
302
+ cache_write_price: 2.5
303
+ long_context:
304
+ threshold: 272000
305
+ input_price: 4.0
306
+ output_price: 15.0
307
+ cached_input_price: 0.2
308
+ cache_write_price: 5.0
309
+ service_tiers:
310
+ fast: 2.0
311
+ ultrafast: 6.0
312
+ context_window: 1050000
313
+ capabilities: [vision, tools, reasoning]
237
314
  - id: openai/gpt-6-astra
238
315
  provider: openai
239
316
  display_name: GPT-6 Astra
240
- description: OpenAI's most capable model, built for the hardest end-to-end work — complex reasoning, agentic coding, computer
241
- use, research, and document creation. Successor to GPT-5.6 Sol.
317
+ description: Previous Astra generation for the hardest end-to-end work — complex reasoning, agentic coding, computer
318
+ use, research, and document creation. Successor to GPT-5.6 Sol; superseded by GPT-6.2 Astra at 20% lower prices.
242
319
  notes: 'Standard short-context pricing is $10/$50 per 1M tokens; cached input $1 (0.1x), cache writes $12.50 (1.25x). Prompts
243
320
  over 272K input tokens bill the full request at long-context rates ($20/$75, cached $2, cache writes $25). Batch/Flex are
244
321
  50% of Standard; Fast mode (`service_tier: "fast"`) is 2x; Ultrafast is 6x. `reasoning.effort` accepts low|medium|high|xhigh|max (API
@@ -264,7 +341,7 @@ models:
264
341
  - id: openai/gpt-6.1-sol
265
342
  provider: openai
266
343
  display_name: GPT-6.1 Sol
267
- description: OpenAI model for complex coding, computer use, and professional work at a lower cost than Astra.
344
+ description: Previous Sol generation for complex coding, computer use, and professional work. Superseded by GPT-6.2 Sol at the same price.
268
345
  notes: 'Verified 2026-10-03 against the model card and API pricing. Standard rates per 1M tokens are $2 input,
269
346
  $0.10 cache reads, $2.50 cache writes, and $10 output. Above 272K input tokens the full request costs
270
347
  $4/$15, cached $0.20, cache writes $5. Batch/Flex cost 50% of Standard; Fast costs 2x.
@@ -289,6 +366,32 @@ models:
289
366
  ultrafast: 6.0
290
367
  context_window: 1050000
291
368
  capabilities: [vision, tools, reasoning]
369
+ - id: openai/gpt-6.1-terra
370
+ provider: openai
371
+ display_name: GPT-6.1 Terra
372
+ description: OpenAI model for fast, efficient visual reasoning, precise computer use, and clear writing, priced between Sol and Luna.
373
+ notes: 'Verified 2026-11-20 against the model reference and API pricing (release date not published there). Standard rates
374
+ per 1M tokens are $1 input, $0.05 cache reads, $1.25 cache writes (30m; 12h writes $2.50), and $5 output. Above 272K
375
+ input tokens the full request costs $2/$7.50, cached $0.10, cache writes $2.50. Batch/Flex cost 50% of Standard (Flex is
376
+ being wound down and will not be added to new models); Fast costs 2x; Ultrafast is not offered. Reasoning accepts
377
+ none, low, medium (default), high, xhigh, max. Tool calling requires Responses; Chat Completions supports text without
378
+ tools. 1.05M context (922K max input), 128K max output, Jun 1, 2026 knowledge cutoff. Regional processing adds 10%
379
+ where eligible. ZDR support is not stated on the model page.'
380
+ input_price: 1.0
381
+ output_price: 5.0
382
+ cached_input_price: 0.05
383
+ cache_write_price: 1.25
384
+ long_context:
385
+ threshold: 272000
386
+ input_price: 2.0
387
+ output_price: 7.5
388
+ cached_input_price: 0.1
389
+ cache_write_price: 2.5
390
+ service_tiers:
391
+ flex: 0.5
392
+ fast: 2.0
393
+ context_window: 1050000
394
+ capabilities: [vision, tools, reasoning]
292
395
  - id: openai/gpt-6-sol
293
396
  provider: openai
294
397
  display_name: GPT-6 Sol
@@ -370,8 +473,8 @@ models:
370
473
  provider: openai
371
474
  display_name: GPT-5.6 Sol
372
475
  description: OpenAI GPT-5.6 flagship tier for the hardest coding, agentic, and long-horizon tasks.
373
- notes: 'Promotional rates retained because post-promotion rates are not published. Available at least
374
- through November 21, 2026: $4/$20 input/output per 1M tokens, cached input $0.40, cache writes $5.
476
+ notes: 'Promotional rates retained because post-promotion rates are not published. Promotional pricing
477
+ is available until November 30, 2026 (per the OpenAI pricing page; re-verify after that date): $4/$20 input/output per 1M tokens, cached input $0.40, cache writes $5.
375
478
  Above 272K input tokens the full request costs $8/$30, cached input $0.80, cache writes $10.'
376
479
  input_price: 4.0
377
480
  output_price: 20.0
@@ -498,6 +601,7 @@ models:
498
601
  provider: openai
499
602
  display_name: GPT-5
500
603
  description: OpenAI GPT-5 base model.
604
+ notes: "Status checked 2026-11-20 against OpenAI's deprecations page. Deprecated (notice June 11, 2026); shuts down December 11, 2026, including its dated snapshot. Prefer gpt-6.1-sol."
501
605
  input_price: 1.25
502
606
  output_price: 10.0
503
607
  cached_input_price: 0.125
@@ -507,6 +611,7 @@ models:
507
611
  provider: openai
508
612
  display_name: GPT-5 Mini
509
613
  description: Compact GPT-5 variant for everyday tasks.
614
+ notes: "Status checked 2026-11-20 against OpenAI's deprecations page. Deprecated (notice June 11, 2026); shuts down December 11, 2026, including its dated snapshot. Prefer gpt-6.1-terra."
510
615
  input_price: 0.25
511
616
  output_price: 2.0
512
617
  cached_input_price: 0.025
@@ -516,6 +621,7 @@ models:
516
621
  provider: openai
517
622
  display_name: GPT-5 Nano
518
623
  description: Ultra-lightweight GPT-5 variant for cost-sensitive use cases.
624
+ notes: "Status checked 2026-11-20 against OpenAI's deprecations page. Deprecated (notice June 11, 2026); shuts down December 11, 2026, including its dated snapshot. Prefer gpt-6-luna."
519
625
  input_price: 0.05
520
626
  output_price: 0.4
521
627
  cached_input_price: 0.005
@@ -525,6 +631,7 @@ models:
525
631
  provider: openai
526
632
  display_name: GPT-4.1
527
633
  description: Improved instruction-following and multimodal model with a 1M token context window.
634
+ notes: "Status checked 2026-11-20 against OpenAI's deprecations page. Dated snapshot deprecated (notice October 14, 2026); shuts down January 14, 2027. The bare alias is not named on the page. Prefer gpt-6-luna."
528
635
  input_price: 2.0
529
636
  output_price: 8.0
530
637
  cached_input_price: 0.5
@@ -534,6 +641,7 @@ models:
534
641
  provider: openai
535
642
  display_name: GPT-4.1 Mini
536
643
  description: Compact GPT-4.1 variant for everyday multimodal tasks.
644
+ notes: "Status checked 2026-11-20 against OpenAI's deprecations page. Dated snapshot deprecated (notice October 14, 2026); shuts down January 14, 2027. The bare alias is not named on the page. Prefer gpt-6-luna."
537
645
  input_price: 0.4
538
646
  output_price: 1.6
539
647
  cached_input_price: 0.1
@@ -543,7 +651,7 @@ models:
543
651
  provider: openai
544
652
  display_name: GPT-4.1 Nano
545
653
  description: Smallest GPT-4.1 variant for high-volume, cost-sensitive workloads.
546
- notes: Deprecated; scheduled shutdown October 23, 2026.
654
+ notes: "Status checked 2026-11-20 against OpenAI's deprecations page. Shut down October 23, 2026 (replacement: gpt-5.6-luna); requests are expected to fail. Kept only so existing references still type-check."
547
655
  input_price: 0.1
548
656
  output_price: 0.4
549
657
  cached_input_price: 0.025
@@ -553,6 +661,7 @@ models:
553
661
  provider: openai
554
662
  display_name: GPT-4o
555
663
  description: Omni model combining vision, audio, and text understanding in a 128K context.
664
+ notes: "Status checked 2026-11-20 against OpenAI's deprecations page. Snapshots gpt-4o-2024-08-06 and gpt-4o-2024-11-20 are deprecated and shut down January 14, 2027 (gpt-4o-2024-05-13 shut down October 23, 2026). The bare alias is not named on the page. Prefer gpt-6-luna."
556
665
  input_price: 2.5
557
666
  output_price: 10.0
558
667
  cached_input_price: 1.25
@@ -562,6 +671,7 @@ models:
562
671
  provider: openai
563
672
  display_name: GPT-4o Mini
564
673
  description: Fast, affordable small model for focused tasks.
674
+ notes: "Status checked 2026-11-20 against OpenAI's deprecations page. Snapshot gpt-4o-mini-2024-07-18 is deprecated and shuts down January 14, 2027. The bare alias is not named on the page. Prefer gpt-6-luna."
565
675
  input_price: 0.15
566
676
  output_price: 0.6
567
677
  cached_input_price: 0.075
@@ -571,7 +681,7 @@ models:
571
681
  provider: openai
572
682
  display_name: o4 Mini
573
683
  description: Compact reasoning model balancing speed and deep thinking.
574
- notes: Deprecated; scheduled shutdown October 23, 2026.
684
+ notes: "Status checked 2026-11-20 against OpenAI's deprecations page. Shut down October 23, 2026 (replacement: gpt-5.6-terra); requests are expected to fail. Kept only so existing references still type-check."
575
685
  input_price: 1.1
576
686
  output_price: 4.4
577
687
  cached_input_price: 0.275
@@ -581,7 +691,7 @@ models:
581
691
  provider: openai
582
692
  display_name: o3
583
693
  description: Advanced reasoning model for complex math, science, and coding.
584
- notes: Deprecated; dated snapshot retires December 11, 2026.
694
+ notes: "Status checked 2026-11-20 against OpenAI's deprecations page. Deprecated (notice June 11, 2026); o3 and o3-2025-04-16 shut down December 11, 2026. Prefer gpt-6.1-sol."
585
695
  input_price: 2.0
586
696
  output_price: 8.0
587
697
  cached_input_price: 0.5
@@ -591,7 +701,7 @@ models:
591
701
  provider: openai
592
702
  display_name: o3 Mini
593
703
  description: Compact o3 variant for efficient deep reasoning.
594
- notes: Deprecated; scheduled shutdown October 23, 2026.
704
+ notes: "Status checked 2026-11-20 against OpenAI's deprecations page. Shut down October 23, 2026 (replacement: gpt-5.6-sol); requests are expected to fail. Kept only so existing references still type-check."
595
705
  input_price: 1.1
596
706
  output_price: 4.4
597
707
  cached_input_price: 0.55
@@ -601,7 +711,7 @@ models:
601
711
  provider: openai
602
712
  display_name: o3 Pro
603
713
  description: High-compute o3 variant for the most demanding reasoning tasks.
604
- notes: Deprecated; dated snapshot retires December 11, 2026.
714
+ notes: "Status checked 2026-11-20 against OpenAI's deprecations page. Deprecated (notice June 11, 2026); o3-pro and o3-pro-2025-06-10 shut down December 11, 2026. Prefer gpt-6.1-sol with reasoning.mode=pro (Responses API)."
605
715
  input_price: 20.0
606
716
  output_price: 80.0
607
717
  context_window: 200000
@@ -610,7 +720,7 @@ models:
610
720
  provider: openai
611
721
  display_name: o1
612
722
  description: First-generation reasoning model with extended thinking for complex problems.
613
- notes: Deprecated; scheduled shutdown October 23, 2026.
723
+ notes: "Status checked 2026-11-20 against OpenAI's deprecations page. Shut down October 23, 2026 (replacement: gpt-5.6-sol); requests are expected to fail. Kept only so existing references still type-check."
614
724
  input_price: 15.0
615
725
  output_price: 60.0
616
726
  cached_input_price: 7.5
@@ -635,6 +745,8 @@ models:
635
745
  provider: togetherai
636
746
  display_name: Llama 3.3 70B Instruct Turbo
637
747
  description: Multilingual 70B model delivering enhanced performance and matching Llama 3.2 90B on text-only tasks.
748
+ notes: "Together's deprecations page (checked 2026-11-20) lists this model as removed from serverless on 2026-10-22; dedicated endpoint only. Probe: 'non-serverless model'."
749
+ dedicated_only: true
638
750
  input_price: 1.04
639
751
  output_price: 1.04
640
752
  context_window: 131072
@@ -767,6 +879,7 @@ models:
767
879
  provider: togetherai
768
880
  display_name: MiniMax M3 (Together)
769
881
  description: MiniMax M3 multimodal model on Together for chat, agents, and long-context workloads.
882
+ notes: "Together's deprecations page (checked 2026-11-20) lists this model as removed from serverless on 2026-11-06 (replacement MiniMaxAI/MiniMax-M3.1-Flash, dedicated). Probe: 'endpoint has no deployments configured'."
770
883
  input_price: 0.3
771
884
  output_price: 1.2
772
885
  context_window: 524288
@@ -834,6 +947,7 @@ models:
834
947
  provider: togetherai
835
948
  display_name: DeepSeek V4 Flash 0731 (Together)
836
949
  description: DeepSeek V4 Flash 0731 on Together serverless.
950
+ notes: "Together's deprecations page (checked 2026-11-20) lists this model as removed from serverless on 2026-10-22. Probe: 'endpoint has no deployments configured'."
837
951
  input_price: 0.14
838
952
  output_price: 0.28
839
953
  context_window: 1048576
@@ -902,8 +1016,7 @@ models:
902
1016
  output_price: 6.0
903
1017
  context_window: 1000000
904
1018
  capabilities: [vision, tools, reasoning]
905
- notes: 'Cached-input pricing unresolved: serverless docs quote $0.50/1M, while pricing and model pages quote $0.25/1M. No
906
- cached rate is assigned until confirmed. https://docs.together.ai/docs/serverless/models and https://www.together.ai/models/qwen3-8-max'
1019
+ notes: "Together's deprecations page (checked 2026-11-20) lists this model as removed from serverless on 2026-11-04; not available dedicated either. Probe: 'non-serverless model'. Cached-input pricing unresolved: serverless docs quote $0.50/1M, while pricing and model pages quote $0.25/1M. No cached rate is assigned until confirmed. https://docs.together.ai/docs/serverless/models and https://www.together.ai/models/qwen3-8-max"
907
1020
  - id: google/gemini-4-argon
908
1021
  provider: google
909
1022
  display_name: Gemini 4 Argon
@@ -1040,8 +1153,7 @@ models:
1040
1153
  provider: google
1041
1154
  display_name: Gemini 2.5 Pro
1042
1155
  description: Legacy Pro model for reasoning, coding, and multimodal analysis; available to previous users.
1043
- notes: 'Access restricted to existing users since 2026-09-18; not deprecated. Above 200,000 input tokens the full
1044
- request uses the long-context tier. Cache storage is separate.'
1156
+ notes: "Shuts down December 1, 2026; requests then route to gemini-3.8-flash (Gemini deprecations page, checked 2026-11-20). Not selectable in AI Studio; API access restricted to existing users since 2026-09-18. Above 200,000 input tokens the full request uses the long-context tier. Cache storage is separate."
1045
1157
  input_price: 1.25
1046
1158
  output_price: 10.0
1047
1159
  cached_input_price: 0.125
@@ -1057,7 +1169,7 @@ models:
1057
1169
  display_name: Gemini 2.5 Pro TTS
1058
1170
  description: Text-to-speech variant of Gemini 2.5 Pro for generating audio output from text input.
1059
1171
  notes: 'Native Gemini TTS API required; not supported by the Agent chat route. Output is audio at $20 per 1M audio
1060
- tokens, not a text output rate. 16,384 max output tokens. Shuts down 2026-11-17; migrate to
1172
+ tokens, not a text output rate. 16,384 max output tokens. Shuts down 2026-12-18; migrate to
1061
1173
  gemini-3.8-flash-tts or gemini-3.8-flash-lite-tts. https://ai.google.dev/gemini-api/docs/deprecations'
1062
1174
  input_price: 1.0
1063
1175
  output_price: null
@@ -1067,8 +1179,7 @@ models:
1067
1179
  provider: google
1068
1180
  display_name: Gemini 2.5 Flash
1069
1181
  description: Legacy Flash model for multimodal reasoning and tool use; available to previous users.
1070
- notes: 'Access restricted to existing users since 2026-09-18; not deprecated. Paid Standard text/image/video rates.
1071
- Audio input is $1 and cached audio $0.10 per 1M tokens, not represented by these text rates.'
1182
+ notes: "Shuts down December 1, 2026; requests then route to gemini-3.5-flash-lite (Gemini deprecations page, checked 2026-11-20). Not selectable in AI Studio; API access restricted to existing users since 2026-09-18. Paid Standard text/image/video rates. Audio input is $1 and cached audio $0.10 per 1M tokens, not represented by these text rates."
1072
1183
  input_price: 0.3
1073
1184
  output_price: 2.5
1074
1185
  cached_input_price: 0.03
@@ -1102,7 +1213,7 @@ models:
1102
1213
  display_name: Gemini 2.5 Flash TTS
1103
1214
  description: Text-to-speech variant of Gemini 2.5 Flash for audio generation at lower cost.
1104
1215
  notes: 'Native Gemini TTS API required; not supported by the Agent chat route. Output is audio at $10 per 1M audio
1105
- tokens, not a text output rate. 16,384 max output tokens. Shuts down 2026-11-17; migrate to
1216
+ tokens, not a text output rate. 16,384 max output tokens. Shuts down 2026-12-18; migrate to
1106
1217
  gemini-3.8-flash-tts or gemini-3.8-flash-lite-tts. https://ai.google.dev/gemini-api/docs/deprecations'
1107
1218
  input_price: 0.5
1108
1219
  output_price: null
@@ -1112,8 +1223,7 @@ models:
1112
1223
  provider: xai
1113
1224
  display_name: Grok Build 0.1
1114
1225
  description: Coding model for agentic software engineering with image input, reasoning, and function calling.
1115
- notes: 'Global API rates. At >=200K prompt tokens, full-request input/output/cache rates double.
1116
- Batch API is not supported. Aliases include grok-code-fast-1; use this canonical ID.'
1226
+ notes: "Not listed on docs.x.ai/docs/models (checked 2026-11-20) and the live API returns 'does not exist or your team does not have access'. Treat as unavailable unless your team has access. Global API rates. At >=200K prompt tokens, full-request input/output/cache rates double. Batch API is not supported. Aliases include grok-code-fast-1; use this canonical ID."
1117
1227
  input_price: 1.0
1118
1228
  output_price: 2.0
1119
1229
  cached_input_price: 0.2
@@ -1197,7 +1307,7 @@ models:
1197
1307
  provider: groq
1198
1308
  display_name: Qwen3.8 27B (Groq)
1199
1309
  description: Qwen3.8 27B multimodal with hybrid thinking/instruct modes, delivered at Groq's ultra-low latency.
1200
- notes: Preview tier. Qwen3.6 27B was retired for free/developer accounts on 2026-09-14. See https://console.groq.com/docs/deprecations
1310
+ notes: "Preview tier; Groq may discontinue preview models at short notice (checked 2026-11-20). Qwen3.6 27B was retired for free/developer accounts on 2026-09-14. See https://console.groq.com/docs/deprecations"
1201
1311
  input_price: 0.8
1202
1312
  output_price: 4.0
1203
1313
  context_window: 131072
@@ -1738,7 +1848,7 @@ models:
1738
1848
  provider: moonshot
1739
1849
  display_name: Kimi K2.7 Code
1740
1850
  description: Moonshot coding-focused multimodal model with thinking mode for long-context programming agents.
1741
- notes: Cache-hit input is $0.19 / 1M tokens.
1851
+ notes: "Moonshot lists this under Deprecated Models (checked 2026-11-20): unavailable to newly registered users; users registered before November 1 can keep using it; deprecation expected late December 2026. K2-series models retire by end of December 2026. Cache-hit input is $0.19 / 1M tokens."
1742
1852
  input_price: 0.95
1743
1853
  output_price: 4.0
1744
1854
  cached_input_price: 0.19
@@ -1748,7 +1858,7 @@ models:
1748
1858
  provider: moonshot
1749
1859
  display_name: Kimi K2.7 Code HighSpeed
1750
1860
  description: Same Kimi K2.7 Code weights with higher output throughput (~180 tok/s) for interactive coding agents.
1751
- notes: Cache-hit input is $0.38 / 1M tokens.
1861
+ notes: "Moonshot lists this under Deprecated Models (checked 2026-11-20): unavailable to newly registered users; users registered before November 1 can keep using it; deprecation expected late December 2026. K2-series models retire by end of December 2026. Cache-hit input is $0.38 / 1M tokens."
1752
1862
  input_price: 1.9
1753
1863
  output_price: 8.0
1754
1864
  cached_input_price: 0.38
@@ -1758,7 +1868,7 @@ models:
1758
1868
  provider: moonshot
1759
1869
  display_name: Kimi K2.6
1760
1870
  description: Moonshot general-purpose multimodal MoE with thinking/non-thinking modes for chat, agents, and vision.
1761
- notes: Cache-hit input is $0.16 / 1M tokens.
1871
+ notes: "Moonshot lists this under Deprecated Models (checked 2026-11-20): unavailable to newly registered users; users registered before November 1 can keep using it; deprecation expected late December 2026. K2-series models retire by end of December 2026. Cache-hit input is $0.16 / 1M tokens."
1762
1872
  input_price: 0.95
1763
1873
  output_price: 4.0
1764
1874
  cached_input_price: 0.16