@code-yeongyu/senpi 2026.6.10 → 2026.6.13

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.
Files changed (285) hide show
  1. package/CHANGELOG.md +68 -1
  2. package/README.md +21 -21
  3. package/dist/cli/startup-ui.d.ts +10 -0
  4. package/dist/cli/startup-ui.d.ts.map +1 -1
  5. package/dist/cli/startup-ui.js +72 -1
  6. package/dist/cli/startup-ui.js.map +1 -1
  7. package/dist/core/agent-session.d.ts.map +1 -1
  8. package/dist/core/agent-session.js +3 -2
  9. package/dist/core/agent-session.js.map +1 -1
  10. package/dist/core/bash-executor.d.ts.map +1 -1
  11. package/dist/core/bash-executor.js +31 -7
  12. package/dist/core/bash-executor.js.map +1 -1
  13. package/dist/core/extensions/builtin/compaction/degradation-monitor.d.ts +0 -1
  14. package/dist/core/extensions/builtin/compaction/degradation-monitor.d.ts.map +1 -1
  15. package/dist/core/extensions/builtin/compaction/degradation-monitor.js +0 -1
  16. package/dist/core/extensions/builtin/compaction/degradation-monitor.js.map +1 -1
  17. package/dist/core/extensions/builtin/compaction/index.d.ts.map +1 -1
  18. package/dist/core/extensions/builtin/compaction/index.js +4 -4
  19. package/dist/core/extensions/builtin/compaction/index.js.map +1 -1
  20. package/dist/core/extensions/builtin/compaction/policy.d.ts +0 -5
  21. package/dist/core/extensions/builtin/compaction/policy.d.ts.map +1 -1
  22. package/dist/core/extensions/builtin/compaction/policy.js +0 -4
  23. package/dist/core/extensions/builtin/compaction/policy.js.map +1 -1
  24. package/dist/core/extensions/builtin/compaction/speculative.d.ts +0 -6
  25. package/dist/core/extensions/builtin/compaction/speculative.d.ts.map +1 -1
  26. package/dist/core/extensions/builtin/compaction/speculative.js +0 -3
  27. package/dist/core/extensions/builtin/compaction/speculative.js.map +1 -1
  28. package/dist/core/extensions/builtin/gpt-apply-patch/extension.d.ts +1 -1
  29. package/dist/core/extensions/builtin/gpt-apply-patch/extension.d.ts.map +1 -1
  30. package/dist/core/extensions/builtin/gpt-apply-patch/extension.js +10 -2
  31. package/dist/core/extensions/builtin/gpt-apply-patch/extension.js.map +1 -1
  32. package/dist/core/extensions/builtin/permission-system/cli.d.ts +0 -3
  33. package/dist/core/extensions/builtin/permission-system/cli.d.ts.map +1 -1
  34. package/dist/core/extensions/builtin/permission-system/cli.js +0 -13
  35. package/dist/core/extensions/builtin/permission-system/cli.js.map +1 -1
  36. package/dist/core/extensions/builtin/prompt-preset/kimi-k2-7.d.ts +3 -0
  37. package/dist/core/extensions/builtin/prompt-preset/kimi-k2-7.d.ts.map +1 -0
  38. package/dist/core/extensions/builtin/prompt-preset/kimi-k2-7.js +10 -0
  39. package/dist/core/extensions/builtin/prompt-preset/kimi-k2-7.js.map +1 -0
  40. package/dist/core/extensions/builtin/prompt-preset/presets.d.ts.map +1 -1
  41. package/dist/core/extensions/builtin/prompt-preset/presets.js +12 -0
  42. package/dist/core/extensions/builtin/prompt-preset/presets.js.map +1 -1
  43. package/dist/core/extensions/builtin/prompt-preset/settings.d.ts +1 -1
  44. package/dist/core/extensions/builtin/prompt-preset/settings.d.ts.map +1 -1
  45. package/dist/core/extensions/builtin/prompt-preset/settings.js +1 -0
  46. package/dist/core/extensions/builtin/prompt-preset/settings.js.map +1 -1
  47. package/dist/core/extensions/types.d.ts +1 -0
  48. package/dist/core/extensions/types.d.ts.map +1 -1
  49. package/dist/core/extensions/types.js.map +1 -1
  50. package/dist/core/model-registry.d.ts +0 -3
  51. package/dist/core/model-registry.d.ts.map +1 -1
  52. package/dist/core/model-registry.js +3 -3
  53. package/dist/core/model-registry.js.map +1 -1
  54. package/dist/core/model-resolver.d.ts +1 -0
  55. package/dist/core/model-resolver.d.ts.map +1 -1
  56. package/dist/core/model-resolver.js +43 -6
  57. package/dist/core/model-resolver.js.map +1 -1
  58. package/dist/core/project-trust.js +2 -2
  59. package/dist/core/project-trust.js.map +1 -1
  60. package/dist/core/resolve-config-value.d.ts +0 -4
  61. package/dist/core/resolve-config-value.d.ts.map +1 -1
  62. package/dist/core/resolve-config-value.js +0 -15
  63. package/dist/core/resolve-config-value.js.map +1 -1
  64. package/dist/core/session-manager.d.ts.map +1 -1
  65. package/dist/core/session-manager.js +11 -2
  66. package/dist/core/session-manager.js.map +1 -1
  67. package/dist/core/settings-manager.d.ts +6 -0
  68. package/dist/core/settings-manager.d.ts.map +1 -1
  69. package/dist/core/settings-manager.js +17 -0
  70. package/dist/core/settings-manager.js.map +1 -1
  71. package/dist/core/tools/edit-diff.d.ts +0 -5
  72. package/dist/core/tools/edit-diff.d.ts.map +1 -1
  73. package/dist/core/tools/edit-diff.js +0 -7
  74. package/dist/core/tools/edit-diff.js.map +1 -1
  75. package/dist/core/tools/index.d.ts +0 -5
  76. package/dist/core/tools/index.d.ts.map +1 -1
  77. package/dist/core/tools/index.js +0 -67
  78. package/dist/core/tools/index.js.map +1 -1
  79. package/dist/core/tools/output-accumulator.d.ts +3 -5
  80. package/dist/core/tools/output-accumulator.d.ts.map +1 -1
  81. package/dist/core/tools/output-accumulator.js +38 -34
  82. package/dist/core/tools/output-accumulator.js.map +1 -1
  83. package/dist/core/tools/tail-window.d.ts +15 -0
  84. package/dist/core/tools/tail-window.d.ts.map +1 -0
  85. package/dist/core/tools/tail-window.js +75 -0
  86. package/dist/core/tools/tail-window.js.map +1 -0
  87. package/dist/core/trust-manager.d.ts +8 -3
  88. package/dist/core/trust-manager.d.ts.map +1 -1
  89. package/dist/core/trust-manager.js +26 -11
  90. package/dist/core/trust-manager.js.map +1 -1
  91. package/dist/index.d.ts +1 -1
  92. package/dist/index.d.ts.map +1 -1
  93. package/dist/index.js +1 -1
  94. package/dist/index.js.map +1 -1
  95. package/dist/main.d.ts.map +1 -1
  96. package/dist/main.js +17 -6
  97. package/dist/main.js.map +1 -1
  98. package/dist/modes/interactive/aborted-error-label.d.ts +2 -0
  99. package/dist/modes/interactive/aborted-error-label.d.ts.map +1 -0
  100. package/dist/modes/interactive/aborted-error-label.js +8 -0
  101. package/dist/modes/interactive/aborted-error-label.js.map +1 -0
  102. package/dist/modes/interactive/components/first-time-setup.d.ts +25 -0
  103. package/dist/modes/interactive/components/first-time-setup.d.ts.map +1 -0
  104. package/dist/modes/interactive/components/first-time-setup.js +101 -0
  105. package/dist/modes/interactive/components/first-time-setup.js.map +1 -0
  106. package/dist/modes/interactive/components/index.d.ts +1 -0
  107. package/dist/modes/interactive/components/index.d.ts.map +1 -1
  108. package/dist/modes/interactive/components/index.js +1 -0
  109. package/dist/modes/interactive/components/index.js.map +1 -1
  110. package/dist/modes/interactive/components/tool-execution.d.ts +6 -0
  111. package/dist/modes/interactive/components/tool-execution.d.ts.map +1 -1
  112. package/dist/modes/interactive/components/tool-execution.js +45 -0
  113. package/dist/modes/interactive/components/tool-execution.js.map +1 -1
  114. package/dist/modes/interactive/components/trust-selector.d.ts.map +1 -1
  115. package/dist/modes/interactive/components/trust-selector.js +4 -4
  116. package/dist/modes/interactive/components/trust-selector.js.map +1 -1
  117. package/dist/modes/interactive/interactive-mode.d.ts +1 -0
  118. package/dist/modes/interactive/interactive-mode.d.ts.map +1 -1
  119. package/dist/modes/interactive/interactive-mode.js +18 -18
  120. package/dist/modes/interactive/interactive-mode.js.map +1 -1
  121. package/dist/modes/interactive/theme/theme.d.ts +0 -4
  122. package/dist/modes/interactive/theme/theme.d.ts.map +1 -1
  123. package/dist/modes/interactive/theme/theme.js +0 -7
  124. package/dist/modes/interactive/theme/theme.js.map +1 -1
  125. package/dist/modes/print-mode.d.ts.map +1 -1
  126. package/dist/modes/print-mode.js +1 -1
  127. package/dist/modes/print-mode.js.map +1 -1
  128. package/dist/modes/rpc/event-output-buffer.d.ts +10 -0
  129. package/dist/modes/rpc/event-output-buffer.d.ts.map +1 -0
  130. package/dist/modes/rpc/event-output-buffer.js +27 -0
  131. package/dist/modes/rpc/event-output-buffer.js.map +1 -0
  132. package/dist/modes/rpc/jsonl.d.ts.map +1 -1
  133. package/dist/modes/rpc/jsonl.js +9 -11
  134. package/dist/modes/rpc/jsonl.js.map +1 -1
  135. package/dist/modes/rpc/rpc-mode.d.ts.map +1 -1
  136. package/dist/modes/rpc/rpc-mode.js +17 -7
  137. package/dist/modes/rpc/rpc-mode.js.map +1 -1
  138. package/dist/modes/rpc/rpc-types.d.ts +0 -1
  139. package/dist/modes/rpc/rpc-types.d.ts.map +1 -1
  140. package/dist/modes/rpc/rpc-types.js.map +1 -1
  141. package/dist/package-manager-cli.d.ts.map +1 -1
  142. package/dist/package-manager-cli.js +10 -3
  143. package/dist/package-manager-cli.js.map +1 -1
  144. package/dist/utils/shell.d.ts.map +1 -1
  145. package/dist/utils/shell.js +14 -0
  146. package/dist/utils/shell.js.map +1 -1
  147. package/docs/compaction-guide.md +9 -9
  148. package/docs/compaction.md +2 -2
  149. package/docs/containerization.md +22 -22
  150. package/docs/custom-provider.md +13 -13
  151. package/docs/development.md +4 -2
  152. package/docs/extensions.md +18 -19
  153. package/docs/index.md +4 -4
  154. package/docs/json.md +21 -15
  155. package/docs/keybindings.md +6 -3
  156. package/docs/models.md +6 -6
  157. package/docs/packages.md +11 -11
  158. package/docs/prompt-templates.md +2 -2
  159. package/docs/providers.md +9 -9
  160. package/docs/rpc.md +14 -13
  161. package/docs/sdk.md +13 -9
  162. package/docs/security.md +14 -10
  163. package/docs/session-format.md +4 -4
  164. package/docs/sessions.md +14 -14
  165. package/docs/settings.md +14 -12
  166. package/docs/skills.md +8 -8
  167. package/docs/terminal-setup.md +2 -2
  168. package/docs/termux.md +3 -3
  169. package/docs/tui.md +4 -4
  170. package/docs/usage.md +52 -59
  171. package/examples/extensions/custom-provider-anthropic/package-lock.json +2 -2
  172. package/examples/extensions/custom-provider-anthropic/package.json +1 -1
  173. package/examples/extensions/custom-provider-gitlab-duo/package.json +1 -1
  174. package/examples/extensions/gondolin/package-lock.json +2 -2
  175. package/examples/extensions/gondolin/package.json +1 -1
  176. package/examples/extensions/sandbox/package-lock.json +2 -2
  177. package/examples/extensions/sandbox/package.json +1 -1
  178. package/examples/extensions/with-deps/package-lock.json +2 -2
  179. package/examples/extensions/with-deps/package.json +1 -1
  180. package/node_modules/@earendil-works/pi-agent-core/README.md +4 -3
  181. package/node_modules/@earendil-works/pi-agent-core/dist/agent-loop.js +8 -0
  182. package/node_modules/@earendil-works/pi-agent-core/dist/agent-loop.js.map +1 -1
  183. package/node_modules/@earendil-works/pi-agent-core/dist/harness/types.d.ts +0 -2
  184. package/node_modules/@earendil-works/pi-agent-core/dist/harness/types.d.ts.map +1 -1
  185. package/node_modules/@earendil-works/pi-agent-core/dist/harness/types.js +0 -4
  186. package/node_modules/@earendil-works/pi-agent-core/dist/harness/types.js.map +1 -1
  187. package/node_modules/@earendil-works/pi-agent-core/dist/types.d.ts +7 -2
  188. package/node_modules/@earendil-works/pi-agent-core/dist/types.d.ts.map +1 -1
  189. package/node_modules/@earendil-works/pi-agent-core/dist/types.js.map +1 -1
  190. package/node_modules/@earendil-works/pi-agent-core/package.json +2 -2
  191. package/node_modules/@earendil-works/pi-ai/README.md +2 -4
  192. package/node_modules/@earendil-works/pi-ai/dist/api-registry.d.ts +0 -1
  193. package/node_modules/@earendil-works/pi-ai/dist/api-registry.d.ts.map +1 -1
  194. package/node_modules/@earendil-works/pi-ai/dist/api-registry.js +0 -3
  195. package/node_modules/@earendil-works/pi-ai/dist/api-registry.js.map +1 -1
  196. package/node_modules/@earendil-works/pi-ai/dist/models.d.ts.map +1 -1
  197. package/node_modules/@earendil-works/pi-ai/dist/models.generated.d.ts +252 -470
  198. package/node_modules/@earendil-works/pi-ai/dist/models.generated.d.ts.map +1 -1
  199. package/node_modules/@earendil-works/pi-ai/dist/models.generated.js +533 -740
  200. package/node_modules/@earendil-works/pi-ai/dist/models.generated.js.map +1 -1
  201. package/node_modules/@earendil-works/pi-ai/dist/models.js +12 -5
  202. package/node_modules/@earendil-works/pi-ai/dist/models.js.map +1 -1
  203. package/node_modules/@earendil-works/pi-ai/dist/providers/amazon-bedrock.d.ts.map +1 -1
  204. package/node_modules/@earendil-works/pi-ai/dist/providers/amazon-bedrock.js +11 -2
  205. package/node_modules/@earendil-works/pi-ai/dist/providers/amazon-bedrock.js.map +1 -1
  206. package/node_modules/@earendil-works/pi-ai/dist/providers/anthropic.d.ts.map +1 -1
  207. package/node_modules/@earendil-works/pi-ai/dist/providers/anthropic.js +29 -16
  208. package/node_modules/@earendil-works/pi-ai/dist/providers/anthropic.js.map +1 -1
  209. package/node_modules/@earendil-works/pi-ai/dist/providers/google-shared.d.ts +0 -4
  210. package/node_modules/@earendil-works/pi-ai/dist/providers/google-shared.d.ts.map +1 -1
  211. package/node_modules/@earendil-works/pi-ai/dist/providers/google-shared.js +0 -13
  212. package/node_modules/@earendil-works/pi-ai/dist/providers/google-shared.js.map +1 -1
  213. package/node_modules/@earendil-works/pi-ai/dist/providers/openai-codex-responses.d.ts.map +1 -1
  214. package/node_modules/@earendil-works/pi-ai/dist/providers/openai-codex-responses.js +3 -1
  215. package/node_modules/@earendil-works/pi-ai/dist/providers/openai-codex-responses.js.map +1 -1
  216. package/node_modules/@earendil-works/pi-ai/dist/providers/simple-options.d.ts +0 -6
  217. package/node_modules/@earendil-works/pi-ai/dist/providers/simple-options.d.ts.map +1 -1
  218. package/node_modules/@earendil-works/pi-ai/dist/providers/simple-options.js +0 -14
  219. package/node_modules/@earendil-works/pi-ai/dist/providers/simple-options.js.map +1 -1
  220. package/node_modules/@earendil-works/pi-ai/dist/types.d.ts +7 -0
  221. package/node_modules/@earendil-works/pi-ai/dist/types.d.ts.map +1 -1
  222. package/node_modules/@earendil-works/pi-ai/dist/types.js.map +1 -1
  223. package/node_modules/@earendil-works/pi-ai/dist/utils/event-stream.d.ts +4 -1
  224. package/node_modules/@earendil-works/pi-ai/dist/utils/event-stream.d.ts.map +1 -1
  225. package/node_modules/@earendil-works/pi-ai/dist/utils/event-stream.js +59 -19
  226. package/node_modules/@earendil-works/pi-ai/dist/utils/event-stream.js.map +1 -1
  227. package/node_modules/@earendil-works/pi-ai/dist/utils/overflow.d.ts +1 -5
  228. package/node_modules/@earendil-works/pi-ai/dist/utils/overflow.d.ts.map +1 -1
  229. package/node_modules/@earendil-works/pi-ai/dist/utils/overflow.js +3 -8
  230. package/node_modules/@earendil-works/pi-ai/dist/utils/overflow.js.map +1 -1
  231. package/node_modules/@earendil-works/pi-ai/package.json +1 -1
  232. package/node_modules/@earendil-works/pi-tui/README.md +1 -2
  233. package/node_modules/@earendil-works/pi-tui/dist/components/editor.d.ts +2 -0
  234. package/node_modules/@earendil-works/pi-tui/dist/components/editor.d.ts.map +1 -1
  235. package/node_modules/@earendil-works/pi-tui/dist/components/editor.js +93 -9
  236. package/node_modules/@earendil-works/pi-tui/dist/components/editor.js.map +1 -1
  237. package/node_modules/@earendil-works/pi-tui/dist/components/markdown.d.ts +3 -1
  238. package/node_modules/@earendil-works/pi-tui/dist/components/markdown.d.ts.map +1 -1
  239. package/node_modules/@earendil-works/pi-tui/dist/components/markdown.js +89 -2
  240. package/node_modules/@earendil-works/pi-tui/dist/components/markdown.js.map +1 -1
  241. package/node_modules/@earendil-works/pi-tui/dist/fuzzy.d.ts +1 -1
  242. package/node_modules/@earendil-works/pi-tui/dist/fuzzy.js +2 -2
  243. package/node_modules/@earendil-works/pi-tui/dist/fuzzy.js.map +1 -1
  244. package/node_modules/@earendil-works/pi-tui/dist/index.d.ts +2 -2
  245. package/node_modules/@earendil-works/pi-tui/dist/index.d.ts.map +1 -1
  246. package/node_modules/@earendil-works/pi-tui/dist/index.js +2 -2
  247. package/node_modules/@earendil-works/pi-tui/dist/index.js.map +1 -1
  248. package/node_modules/@earendil-works/pi-tui/dist/stdin-buffer.d.ts +1 -0
  249. package/node_modules/@earendil-works/pi-tui/dist/stdin-buffer.d.ts.map +1 -1
  250. package/node_modules/@earendil-works/pi-tui/dist/stdin-buffer.js +15 -8
  251. package/node_modules/@earendil-works/pi-tui/dist/stdin-buffer.js.map +1 -1
  252. package/node_modules/@earendil-works/pi-tui/dist/terminal-image.d.ts +0 -1
  253. package/node_modules/@earendil-works/pi-tui/dist/terminal-image.d.ts.map +1 -1
  254. package/node_modules/@earendil-works/pi-tui/dist/terminal-image.js +4 -7
  255. package/node_modules/@earendil-works/pi-tui/dist/terminal-image.js.map +1 -1
  256. package/node_modules/@earendil-works/pi-tui/dist/terminal.d.ts.map +1 -1
  257. package/node_modules/@earendil-works/pi-tui/dist/terminal.js +0 -1
  258. package/node_modules/@earendil-works/pi-tui/dist/terminal.js.map +1 -1
  259. package/node_modules/@earendil-works/pi-tui/dist/tui.d.ts +2 -1
  260. package/node_modules/@earendil-works/pi-tui/dist/tui.d.ts.map +1 -1
  261. package/node_modules/@earendil-works/pi-tui/dist/tui.js +72 -16
  262. package/node_modules/@earendil-works/pi-tui/dist/tui.js.map +1 -1
  263. package/node_modules/@earendil-works/pi-tui/dist/utils.d.ts +1 -4
  264. package/node_modules/@earendil-works/pi-tui/dist/utils.d.ts.map +1 -1
  265. package/node_modules/@earendil-works/pi-tui/dist/utils.js +1 -7
  266. package/node_modules/@earendil-works/pi-tui/dist/utils.js.map +1 -1
  267. package/node_modules/@earendil-works/pi-tui/package.json +1 -1
  268. package/npm-shrinkwrap.json +12 -12
  269. package/package.json +5 -5
  270. package/dist/core/experimental.d.ts +0 -2
  271. package/dist/core/experimental.d.ts.map +0 -1
  272. package/dist/core/experimental.js +0 -4
  273. package/dist/core/experimental.js.map +0 -1
  274. package/dist/core/extensions/builtin/compaction/overflow-detection.d.ts +0 -11
  275. package/dist/core/extensions/builtin/compaction/overflow-detection.d.ts.map +0 -1
  276. package/dist/core/extensions/builtin/compaction/overflow-detection.js +0 -40
  277. package/dist/core/extensions/builtin/compaction/overflow-detection.js.map +0 -1
  278. package/dist/core/extensions/builtin/system-messages.d.ts +0 -47
  279. package/dist/core/extensions/builtin/system-messages.d.ts.map +0 -1
  280. package/dist/core/extensions/builtin/system-messages.js +0 -117
  281. package/dist/core/extensions/builtin/system-messages.js.map +0 -1
  282. package/dist/core/index.d.ts +0 -13
  283. package/dist/core/index.d.ts.map +0 -1
  284. package/dist/core/index.js +0 -13
  285. package/dist/core/index.js.map +0 -1
@@ -2988,30 +2988,13 @@ export const MODELS = {
2988
2988
  reasoning: true,
2989
2989
  input: ["text"],
2990
2990
  cost: {
2991
- input: 0.25,
2992
- output: 0.69,
2991
+ input: 0.35,
2992
+ output: 0.75,
2993
2993
  cacheRead: 0,
2994
2994
  cacheWrite: 0,
2995
2995
  },
2996
2996
  contextWindow: 131072,
2997
- maxTokens: 32768,
2998
- },
2999
- "llama3.1-8b": {
3000
- id: "llama3.1-8b",
3001
- name: "Llama 3.1 8B",
3002
- api: "openai-completions",
3003
- provider: "cerebras",
3004
- baseUrl: "https://api.cerebras.ai/v1",
3005
- reasoning: false,
3006
- input: ["text"],
3007
- cost: {
3008
- input: 0.1,
3009
- output: 0.1,
3010
- cacheRead: 0,
3011
- cacheWrite: 0,
3012
- },
3013
- contextWindow: 32000,
3014
- maxTokens: 8000,
2997
+ maxTokens: 40960,
3015
2998
  },
3016
2999
  "zai-glm-4.7": {
3017
3000
  id: "zai-glm-4.7",
@@ -3019,7 +3002,7 @@ export const MODELS = {
3019
3002
  api: "openai-completions",
3020
3003
  provider: "cerebras",
3021
3004
  baseUrl: "https://api.cerebras.ai/v1",
3022
- reasoning: false,
3005
+ reasoning: true,
3023
3006
  input: ["text"],
3024
3007
  cost: {
3025
3008
  input: 2.25,
@@ -3028,7 +3011,7 @@ export const MODELS = {
3028
3011
  cacheWrite: 0,
3029
3012
  },
3030
3013
  contextWindow: 131072,
3031
- maxTokens: 40000,
3014
+ maxTokens: 40960,
3032
3015
  },
3033
3016
  },
3034
3017
  "cloudflare-ai-gateway": {
@@ -3791,6 +3774,24 @@ export const MODELS = {
3791
3774
  contextWindow: 262144,
3792
3775
  maxTokens: 256000,
3793
3776
  },
3777
+ "@cf/moonshotai/kimi-k2.7-code": {
3778
+ id: "@cf/moonshotai/kimi-k2.7-code",
3779
+ name: "Kimi K2.7 Code",
3780
+ api: "openai-completions",
3781
+ provider: "cloudflare-workers-ai",
3782
+ baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
3783
+ compat: { "sendSessionAffinityHeaders": true },
3784
+ reasoning: true,
3785
+ input: ["text", "image"],
3786
+ cost: {
3787
+ input: 0.95,
3788
+ output: 4,
3789
+ cacheRead: 0.19,
3790
+ cacheWrite: 0,
3791
+ },
3792
+ contextWindow: 262144,
3793
+ maxTokens: 262144,
3794
+ },
3794
3795
  "@cf/nvidia/nemotron-3-120b-a12b": {
3795
3796
  id: "@cf/nvidia/nemotron-3-120b-a12b",
3796
3797
  name: "Nemotron 3 Super 120B",
@@ -4013,9 +4014,9 @@ export const MODELS = {
4013
4014
  contextWindow: 131072,
4014
4015
  maxTokens: 32768,
4015
4016
  },
4016
- "accounts/fireworks/models/kimi-k2p5": {
4017
- id: "accounts/fireworks/models/kimi-k2p5",
4018
- name: "Kimi K2.5",
4017
+ "accounts/fireworks/models/kimi-k2p6": {
4018
+ id: "accounts/fireworks/models/kimi-k2p6",
4019
+ name: "Kimi K2.6",
4019
4020
  api: "anthropic-messages",
4020
4021
  provider: "fireworks",
4021
4022
  baseUrl: "https://api.fireworks.ai/inference",
@@ -4023,17 +4024,17 @@ export const MODELS = {
4023
4024
  reasoning: true,
4024
4025
  input: ["text", "image"],
4025
4026
  cost: {
4026
- input: 0.6,
4027
- output: 3,
4028
- cacheRead: 0.1,
4027
+ input: 0.95,
4028
+ output: 4,
4029
+ cacheRead: 0.16,
4029
4030
  cacheWrite: 0,
4030
4031
  },
4031
- contextWindow: 256000,
4032
- maxTokens: 256000,
4032
+ contextWindow: 262000,
4033
+ maxTokens: 262000,
4033
4034
  },
4034
- "accounts/fireworks/models/kimi-k2p6": {
4035
- id: "accounts/fireworks/models/kimi-k2p6",
4036
- name: "Kimi K2.6",
4035
+ "accounts/fireworks/models/kimi-k2p7-code": {
4036
+ id: "accounts/fireworks/models/kimi-k2p7-code",
4037
+ name: "Kimi K2.7 Code",
4037
4038
  api: "anthropic-messages",
4038
4039
  provider: "fireworks",
4039
4040
  baseUrl: "https://api.fireworks.ai/inference",
@@ -4043,15 +4044,15 @@ export const MODELS = {
4043
4044
  cost: {
4044
4045
  input: 0.95,
4045
4046
  output: 4,
4046
- cacheRead: 0.16,
4047
+ cacheRead: 0.19,
4047
4048
  cacheWrite: 0,
4048
4049
  },
4049
4050
  contextWindow: 262000,
4050
4051
  maxTokens: 262000,
4051
4052
  },
4052
- "accounts/fireworks/models/minimax-m2p5": {
4053
- id: "accounts/fireworks/models/minimax-m2p5",
4054
- name: "MiniMax-M2.5",
4053
+ "accounts/fireworks/models/minimax-m2p7": {
4054
+ id: "accounts/fireworks/models/minimax-m2p7",
4055
+ name: "MiniMax-M2.7",
4055
4056
  api: "anthropic-messages",
4056
4057
  provider: "fireworks",
4057
4058
  baseUrl: "https://api.fireworks.ai/inference",
@@ -4061,15 +4062,15 @@ export const MODELS = {
4061
4062
  cost: {
4062
4063
  input: 0.3,
4063
4064
  output: 1.2,
4064
- cacheRead: 0.03,
4065
+ cacheRead: 0.06,
4065
4066
  cacheWrite: 0,
4066
4067
  },
4067
4068
  contextWindow: 196608,
4068
4069
  maxTokens: 196608,
4069
4070
  },
4070
- "accounts/fireworks/models/minimax-m2p7": {
4071
- id: "accounts/fireworks/models/minimax-m2p7",
4072
- name: "MiniMax-M2.7",
4071
+ "accounts/fireworks/models/minimax-m3": {
4072
+ id: "accounts/fireworks/models/minimax-m3",
4073
+ name: "MiniMax-M3",
4073
4074
  api: "anthropic-messages",
4074
4075
  provider: "fireworks",
4075
4076
  baseUrl: "https://api.fireworks.ai/inference",
@@ -4082,12 +4083,12 @@ export const MODELS = {
4082
4083
  cacheRead: 0.06,
4083
4084
  cacheWrite: 0,
4084
4085
  },
4085
- contextWindow: 196608,
4086
- maxTokens: 196608,
4086
+ contextWindow: 512000,
4087
+ maxTokens: 512000,
4087
4088
  },
4088
- "accounts/fireworks/models/qwen3p6-plus": {
4089
- id: "accounts/fireworks/models/qwen3p6-plus",
4090
- name: "Qwen 3.6 Plus",
4089
+ "accounts/fireworks/models/qwen3p7-plus": {
4090
+ id: "accounts/fireworks/models/qwen3p7-plus",
4091
+ name: "Qwen 3.7 Plus",
4091
4092
  api: "anthropic-messages",
4092
4093
  provider: "fireworks",
4093
4094
  baseUrl: "https://api.fireworks.ai/inference",
@@ -4095,9 +4096,9 @@ export const MODELS = {
4095
4096
  reasoning: true,
4096
4097
  input: ["text", "image"],
4097
4098
  cost: {
4098
- input: 0.5,
4099
- output: 3,
4100
- cacheRead: 0.1,
4099
+ input: 0.4,
4100
+ output: 1.6,
4101
+ cacheRead: 0.08,
4101
4102
  cacheWrite: 0,
4102
4103
  },
4103
4104
  contextWindow: 262144,
@@ -4157,8 +4158,45 @@ export const MODELS = {
4157
4158
  contextWindow: 262000,
4158
4159
  maxTokens: 262000,
4159
4160
  },
4161
+ "accounts/fireworks/routers/kimi-k2p7-code-fast": {
4162
+ id: "accounts/fireworks/routers/kimi-k2p7-code-fast",
4163
+ name: "Kimi K2.7 Code Fast",
4164
+ api: "anthropic-messages",
4165
+ provider: "fireworks",
4166
+ baseUrl: "https://api.fireworks.ai/inference",
4167
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
4168
+ reasoning: true,
4169
+ input: ["text", "image"],
4170
+ cost: {
4171
+ input: 2,
4172
+ output: 8,
4173
+ cacheRead: 0.38,
4174
+ cacheWrite: 0,
4175
+ },
4176
+ contextWindow: 262000,
4177
+ maxTokens: 262000,
4178
+ },
4160
4179
  },
4161
4180
  "github-copilot": {
4181
+ "claude-fable-5": {
4182
+ id: "claude-fable-5",
4183
+ name: "Claude Fable 5",
4184
+ api: "openai-completions",
4185
+ provider: "github-copilot",
4186
+ baseUrl: "https://api.individual.githubcopilot.com",
4187
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
4188
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4189
+ reasoning: true,
4190
+ input: ["text", "image"],
4191
+ cost: {
4192
+ input: 10,
4193
+ output: 50,
4194
+ cacheRead: 1,
4195
+ cacheWrite: 12.5,
4196
+ },
4197
+ contextWindow: 1000000,
4198
+ maxTokens: 128000,
4199
+ },
4162
4200
  "claude-haiku-4.5": {
4163
4201
  id: "claude-haiku-4.5",
4164
4202
  name: "Claude Haiku 4.5 (latest)",
@@ -5091,77 +5129,9 @@ export const MODELS = {
5091
5129
  },
5092
5130
  },
5093
5131
  "groq": {
5094
- "deepseek-r1-distill-llama-70b": {
5095
- id: "deepseek-r1-distill-llama-70b",
5096
- name: "DeepSeek R1 Distill Llama 70B",
5097
- api: "openai-completions",
5098
- provider: "groq",
5099
- baseUrl: "https://api.groq.com/openai/v1",
5100
- reasoning: true,
5101
- input: ["text"],
5102
- cost: {
5103
- input: 0.75,
5104
- output: 0.99,
5105
- cacheRead: 0,
5106
- cacheWrite: 0,
5107
- },
5108
- contextWindow: 131072,
5109
- maxTokens: 8192,
5110
- },
5111
- "gemma2-9b-it": {
5112
- id: "gemma2-9b-it",
5113
- name: "Gemma 2 9B",
5114
- api: "openai-completions",
5115
- provider: "groq",
5116
- baseUrl: "https://api.groq.com/openai/v1",
5117
- reasoning: false,
5118
- input: ["text"],
5119
- cost: {
5120
- input: 0.2,
5121
- output: 0.2,
5122
- cacheRead: 0,
5123
- cacheWrite: 0,
5124
- },
5125
- contextWindow: 8192,
5126
- maxTokens: 8192,
5127
- },
5128
- "groq/compound": {
5129
- id: "groq/compound",
5130
- name: "Compound",
5131
- api: "openai-completions",
5132
- provider: "groq",
5133
- baseUrl: "https://api.groq.com/openai/v1",
5134
- reasoning: true,
5135
- input: ["text"],
5136
- cost: {
5137
- input: 0,
5138
- output: 0,
5139
- cacheRead: 0,
5140
- cacheWrite: 0,
5141
- },
5142
- contextWindow: 131072,
5143
- maxTokens: 8192,
5144
- },
5145
- "groq/compound-mini": {
5146
- id: "groq/compound-mini",
5147
- name: "Compound Mini",
5148
- api: "openai-completions",
5149
- provider: "groq",
5150
- baseUrl: "https://api.groq.com/openai/v1",
5151
- reasoning: true,
5152
- input: ["text"],
5153
- cost: {
5154
- input: 0,
5155
- output: 0,
5156
- cacheRead: 0,
5157
- cacheWrite: 0,
5158
- },
5159
- contextWindow: 131072,
5160
- maxTokens: 8192,
5161
- },
5162
5132
  "llama-3.1-8b-instant": {
5163
5133
  id: "llama-3.1-8b-instant",
5164
- name: "Llama 3.1 8B Instant",
5134
+ name: "Llama 3.1 8B",
5165
5135
  api: "openai-completions",
5166
5136
  provider: "groq",
5167
5137
  baseUrl: "https://api.groq.com/openai/v1",
@@ -5178,7 +5148,7 @@ export const MODELS = {
5178
5148
  },
5179
5149
  "llama-3.3-70b-versatile": {
5180
5150
  id: "llama-3.3-70b-versatile",
5181
- name: "Llama 3.3 70B Versatile",
5151
+ name: "Llama 3.3 70B",
5182
5152
  api: "openai-completions",
5183
5153
  provider: "groq",
5184
5154
  baseUrl: "https://api.groq.com/openai/v1",
@@ -5193,60 +5163,9 @@ export const MODELS = {
5193
5163
  contextWindow: 131072,
5194
5164
  maxTokens: 32768,
5195
5165
  },
5196
- "llama3-70b-8192": {
5197
- id: "llama3-70b-8192",
5198
- name: "Llama 3 70B",
5199
- api: "openai-completions",
5200
- provider: "groq",
5201
- baseUrl: "https://api.groq.com/openai/v1",
5202
- reasoning: false,
5203
- input: ["text"],
5204
- cost: {
5205
- input: 0.59,
5206
- output: 0.79,
5207
- cacheRead: 0,
5208
- cacheWrite: 0,
5209
- },
5210
- contextWindow: 8192,
5211
- maxTokens: 8192,
5212
- },
5213
- "llama3-8b-8192": {
5214
- id: "llama3-8b-8192",
5215
- name: "Llama 3 8B",
5216
- api: "openai-completions",
5217
- provider: "groq",
5218
- baseUrl: "https://api.groq.com/openai/v1",
5219
- reasoning: false,
5220
- input: ["text"],
5221
- cost: {
5222
- input: 0.05,
5223
- output: 0.08,
5224
- cacheRead: 0,
5225
- cacheWrite: 0,
5226
- },
5227
- contextWindow: 8192,
5228
- maxTokens: 8192,
5229
- },
5230
- "meta-llama/llama-4-maverick-17b-128e-instruct": {
5231
- id: "meta-llama/llama-4-maverick-17b-128e-instruct",
5232
- name: "Llama 4 Maverick 17B",
5233
- api: "openai-completions",
5234
- provider: "groq",
5235
- baseUrl: "https://api.groq.com/openai/v1",
5236
- reasoning: false,
5237
- input: ["text", "image"],
5238
- cost: {
5239
- input: 0.2,
5240
- output: 0.6,
5241
- cacheRead: 0,
5242
- cacheWrite: 0,
5243
- },
5244
- contextWindow: 131072,
5245
- maxTokens: 8192,
5246
- },
5247
5166
  "meta-llama/llama-4-scout-17b-16e-instruct": {
5248
5167
  id: "meta-llama/llama-4-scout-17b-16e-instruct",
5249
- name: "Llama 4 Scout 17B",
5168
+ name: "Llama 4 Scout 17B 16E",
5250
5169
  api: "openai-completions",
5251
5170
  provider: "groq",
5252
5171
  baseUrl: "https://api.groq.com/openai/v1",
@@ -5261,57 +5180,6 @@ export const MODELS = {
5261
5180
  contextWindow: 131072,
5262
5181
  maxTokens: 8192,
5263
5182
  },
5264
- "mistral-saba-24b": {
5265
- id: "mistral-saba-24b",
5266
- name: "Mistral Saba 24B",
5267
- api: "openai-completions",
5268
- provider: "groq",
5269
- baseUrl: "https://api.groq.com/openai/v1",
5270
- reasoning: false,
5271
- input: ["text"],
5272
- cost: {
5273
- input: 0.79,
5274
- output: 0.79,
5275
- cacheRead: 0,
5276
- cacheWrite: 0,
5277
- },
5278
- contextWindow: 32768,
5279
- maxTokens: 32768,
5280
- },
5281
- "moonshotai/kimi-k2-instruct": {
5282
- id: "moonshotai/kimi-k2-instruct",
5283
- name: "Kimi K2 Instruct",
5284
- api: "openai-completions",
5285
- provider: "groq",
5286
- baseUrl: "https://api.groq.com/openai/v1",
5287
- reasoning: false,
5288
- input: ["text"],
5289
- cost: {
5290
- input: 1,
5291
- output: 3,
5292
- cacheRead: 0,
5293
- cacheWrite: 0,
5294
- },
5295
- contextWindow: 131072,
5296
- maxTokens: 16384,
5297
- },
5298
- "moonshotai/kimi-k2-instruct-0905": {
5299
- id: "moonshotai/kimi-k2-instruct-0905",
5300
- name: "Kimi K2 Instruct 0905",
5301
- api: "openai-completions",
5302
- provider: "groq",
5303
- baseUrl: "https://api.groq.com/openai/v1",
5304
- reasoning: false,
5305
- input: ["text"],
5306
- cost: {
5307
- input: 1,
5308
- output: 3,
5309
- cacheRead: 0.5,
5310
- cacheWrite: 0,
5311
- },
5312
- contextWindow: 262144,
5313
- maxTokens: 16384,
5314
- },
5315
5183
  "openai/gpt-oss-120b": {
5316
5184
  id: "openai/gpt-oss-120b",
5317
5185
  name: "GPT OSS 120B",
@@ -5363,26 +5231,9 @@ export const MODELS = {
5363
5231
  contextWindow: 131072,
5364
5232
  maxTokens: 65536,
5365
5233
  },
5366
- "qwen-qwq-32b": {
5367
- id: "qwen-qwq-32b",
5368
- name: "Qwen QwQ 32B",
5369
- api: "openai-completions",
5370
- provider: "groq",
5371
- baseUrl: "https://api.groq.com/openai/v1",
5372
- reasoning: true,
5373
- input: ["text"],
5374
- cost: {
5375
- input: 0.29,
5376
- output: 0.39,
5377
- cacheRead: 0,
5378
- cacheWrite: 0,
5379
- },
5380
- contextWindow: 131072,
5381
- maxTokens: 16384,
5382
- },
5383
5234
  "qwen/qwen3-32b": {
5384
5235
  id: "qwen/qwen3-32b",
5385
- name: "Qwen3 32B",
5236
+ name: "Qwen3-32B",
5386
5237
  api: "openai-completions",
5387
5238
  provider: "groq",
5388
5239
  baseUrl: "https://api.groq.com/openai/v1",
@@ -5798,6 +5649,24 @@ export const MODELS = {
5798
5649
  },
5799
5650
  },
5800
5651
  "kimi-coding": {
5652
+ "k2p7": {
5653
+ id: "k2p7",
5654
+ name: "Kimi K2.7 Code",
5655
+ api: "anthropic-messages",
5656
+ provider: "kimi-coding",
5657
+ baseUrl: "https://api.kimi.com/coding",
5658
+ headers: { "User-Agent": "KimiCLI/1.5" },
5659
+ reasoning: true,
5660
+ input: ["text", "image"],
5661
+ cost: {
5662
+ input: 0,
5663
+ output: 0,
5664
+ cacheRead: 0,
5665
+ cacheWrite: 0,
5666
+ },
5667
+ contextWindow: 262144,
5668
+ maxTokens: 32768,
5669
+ },
5801
5670
  "kimi-for-coding": {
5802
5671
  id: "kimi-for-coding",
5803
5672
  name: "Kimi For Coding",
@@ -6580,6 +6449,24 @@ export const MODELS = {
6580
6449
  contextWindow: 262144,
6581
6450
  maxTokens: 262144,
6582
6451
  },
6452
+ "kimi-k2.7-code": {
6453
+ id: "kimi-k2.7-code",
6454
+ name: "Kimi K2.7 Code",
6455
+ api: "openai-completions",
6456
+ provider: "moonshotai",
6457
+ baseUrl: "https://api.moonshot.ai/v1",
6458
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
6459
+ reasoning: true,
6460
+ input: ["text", "image"],
6461
+ cost: {
6462
+ input: 0.95,
6463
+ output: 4,
6464
+ cacheRead: 0.19,
6465
+ cacheWrite: 0,
6466
+ },
6467
+ contextWindow: 262144,
6468
+ maxTokens: 262144,
6469
+ },
6583
6470
  },
6584
6471
  "moonshotai-cn": {
6585
6472
  "kimi-k2-0711-preview": {
@@ -6832,8 +6719,8 @@ export const MODELS = {
6832
6719
  baseUrl: "https://integrate.api.nvidia.com/v1",
6833
6720
  headers: { "NVCF-POLL-SECONDS": "3600" },
6834
6721
  compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
6835
- reasoning: false,
6836
- input: ["text"],
6722
+ reasoning: true,
6723
+ input: ["text", "image"],
6837
6724
  cost: {
6838
6725
  input: 0,
6839
6726
  output: 0,
@@ -6862,44 +6749,6 @@ export const MODELS = {
6862
6749
  contextWindow: 262144,
6863
6750
  maxTokens: 262144,
6864
6751
  },
6865
- "nvidia/llama-3.3-nemotron-super-49b-v1": {
6866
- id: "nvidia/llama-3.3-nemotron-super-49b-v1",
6867
- name: "Llama 3.3 Nemotron Super 49B v1",
6868
- api: "openai-completions",
6869
- provider: "nvidia",
6870
- baseUrl: "https://integrate.api.nvidia.com/v1",
6871
- headers: { "NVCF-POLL-SECONDS": "3600" },
6872
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
6873
- reasoning: true,
6874
- input: ["text"],
6875
- cost: {
6876
- input: 0,
6877
- output: 0,
6878
- cacheRead: 0,
6879
- cacheWrite: 0,
6880
- },
6881
- contextWindow: 131072,
6882
- maxTokens: 131072,
6883
- },
6884
- "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
6885
- id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
6886
- name: "Llama 3.3 Nemotron Super 49B v1.5",
6887
- api: "openai-completions",
6888
- provider: "nvidia",
6889
- baseUrl: "https://integrate.api.nvidia.com/v1",
6890
- headers: { "NVCF-POLL-SECONDS": "3600" },
6891
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
6892
- reasoning: true,
6893
- input: ["text"],
6894
- cost: {
6895
- input: 0,
6896
- output: 0,
6897
- cacheRead: 0,
6898
- cacheWrite: 0,
6899
- },
6900
- contextWindow: 131072,
6901
- maxTokens: 131072,
6902
- },
6903
6752
  "nvidia/nemotron-3-nano-30b-a3b": {
6904
6753
  id: "nvidia/nemotron-3-nano-30b-a3b",
6905
6754
  name: "nemotron-3-nano-30b-a3b",
@@ -6995,9 +6844,9 @@ export const MODELS = {
6995
6844
  contextWindow: 131072,
6996
6845
  maxTokens: 131072,
6997
6846
  },
6998
- "openai/gpt-oss-20b": {
6999
- id: "openai/gpt-oss-20b",
7000
- name: "GPT OSS 20B",
6847
+ "openai/gpt-oss-120b": {
6848
+ id: "openai/gpt-oss-120b",
6849
+ name: "GPT-OSS-120B",
7001
6850
  api: "openai-completions",
7002
6851
  provider: "nvidia",
7003
6852
  baseUrl: "https://integrate.api.nvidia.com/v1",
@@ -7011,18 +6860,18 @@ export const MODELS = {
7011
6860
  cacheRead: 0,
7012
6861
  cacheWrite: 0,
7013
6862
  },
7014
- contextWindow: 131072,
7015
- maxTokens: 32768,
6863
+ contextWindow: 128000,
6864
+ maxTokens: 8192,
7016
6865
  },
7017
- "qwen/qwen3-coder-480b-a35b-instruct": {
7018
- id: "qwen/qwen3-coder-480b-a35b-instruct",
7019
- name: "Qwen3 Coder 480B A35B Instruct",
6866
+ "openai/gpt-oss-20b": {
6867
+ id: "openai/gpt-oss-20b",
6868
+ name: "GPT OSS 20B",
7020
6869
  api: "openai-completions",
7021
6870
  provider: "nvidia",
7022
6871
  baseUrl: "https://integrate.api.nvidia.com/v1",
7023
6872
  headers: { "NVCF-POLL-SECONDS": "3600" },
7024
6873
  compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
7025
- reasoning: false,
6874
+ reasoning: true,
7026
6875
  input: ["text"],
7027
6876
  cost: {
7028
6877
  input: 0,
@@ -7030,8 +6879,8 @@ export const MODELS = {
7030
6879
  cacheRead: 0,
7031
6880
  cacheWrite: 0,
7032
6881
  },
7033
- contextWindow: 262144,
7034
- maxTokens: 66536,
6882
+ contextWindow: 131072,
6883
+ maxTokens: 32768,
7035
6884
  },
7036
6885
  "qwen/qwen3.5-122b-a10b": {
7037
6886
  id: "qwen/qwen3.5-122b-a10b",
@@ -7943,25 +7792,6 @@ export const MODELS = {
7943
7792
  contextWindow: 200000,
7944
7793
  maxTokens: 32000,
7945
7794
  },
7946
- "claude-fable-5": {
7947
- id: "claude-fable-5",
7948
- name: "Claude Fable 5",
7949
- api: "anthropic-messages",
7950
- provider: "opencode",
7951
- baseUrl: "https://opencode.ai/zen",
7952
- compat: { "forceAdaptiveThinking": true },
7953
- reasoning: true,
7954
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
7955
- input: ["text", "image"],
7956
- cost: {
7957
- input: 10,
7958
- output: 50,
7959
- cacheRead: 1,
7960
- cacheWrite: 12.5,
7961
- },
7962
- contextWindow: 1000000,
7963
- maxTokens: 128000,
7964
- },
7965
7795
  "claude-haiku-4-5": {
7966
7796
  id: "claude-haiku-4-5",
7967
7797
  name: "Claude Haiku 4.5",
@@ -8135,7 +7965,7 @@ export const MODELS = {
8135
7965
  cost: {
8136
7966
  input: 0.14,
8137
7967
  output: 0.28,
8138
- cacheRead: 0.03,
7968
+ cacheRead: 0.028,
8139
7969
  cacheWrite: 0,
8140
7970
  },
8141
7971
  contextWindow: 1000000,
@@ -8160,6 +7990,25 @@ export const MODELS = {
8160
7990
  contextWindow: 200000,
8161
7991
  maxTokens: 128000,
8162
7992
  },
7993
+ "deepseek-v4-pro": {
7994
+ id: "deepseek-v4-pro",
7995
+ name: "DeepSeek V4 Pro",
7996
+ api: "openai-completions",
7997
+ provider: "opencode",
7998
+ baseUrl: "https://opencode.ai/zen/v1",
7999
+ compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
8000
+ reasoning: true,
8001
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
8002
+ input: ["text"],
8003
+ cost: {
8004
+ input: 1.74,
8005
+ output: 3.84,
8006
+ cacheRead: 0.145,
8007
+ cacheWrite: 0,
8008
+ },
8009
+ contextWindow: 1000000,
8010
+ maxTokens: 384000,
8011
+ },
8163
8012
  "gemini-3-flash": {
8164
8013
  id: "gemini-3-flash",
8165
8014
  name: "Gemini 3 Flash",
@@ -8793,42 +8642,42 @@ export const MODELS = {
8793
8642
  contextWindow: 202752,
8794
8643
  maxTokens: 32768,
8795
8644
  },
8796
- "kimi-k2.5": {
8797
- id: "kimi-k2.5",
8798
- name: "Kimi K2.5",
8645
+ "kimi-k2.6": {
8646
+ id: "kimi-k2.6",
8647
+ name: "Kimi K2.6",
8799
8648
  api: "openai-completions",
8800
8649
  provider: "opencode-go",
8801
8650
  baseUrl: "https://opencode.ai/zen/go/v1",
8802
- compat: { "maxTokensField": "max_tokens" },
8651
+ compat: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false, "maxTokensField": "max_tokens" },
8803
8652
  reasoning: true,
8653
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
8804
8654
  input: ["text", "image"],
8805
- cost: {
8806
- input: 0.6,
8807
- output: 3,
8808
- cacheRead: 0.1,
8655
+ cost: {
8656
+ input: 0.95,
8657
+ output: 4,
8658
+ cacheRead: 0.16,
8809
8659
  cacheWrite: 0,
8810
8660
  },
8811
8661
  contextWindow: 262144,
8812
8662
  maxTokens: 65536,
8813
8663
  },
8814
- "kimi-k2.6": {
8815
- id: "kimi-k2.6",
8816
- name: "Kimi K2.6",
8664
+ "kimi-k2.7-code": {
8665
+ id: "kimi-k2.7-code",
8666
+ name: "Kimi K2.7 Code",
8817
8667
  api: "openai-completions",
8818
8668
  provider: "opencode-go",
8819
8669
  baseUrl: "https://opencode.ai/zen/go/v1",
8820
- compat: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false, "maxTokensField": "max_tokens" },
8670
+ compat: { "maxTokensField": "max_tokens" },
8821
8671
  reasoning: true,
8822
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
8823
8672
  input: ["text", "image"],
8824
8673
  cost: {
8825
8674
  input: 0.95,
8826
8675
  output: 4,
8827
- cacheRead: 0.16,
8676
+ cacheRead: 0.19,
8828
8677
  cacheWrite: 0,
8829
8678
  },
8830
8679
  contextWindow: 262144,
8831
- maxTokens: 65536,
8680
+ maxTokens: 262144,
8832
8681
  },
8833
8682
  "mimo-v2.5": {
8834
8683
  id: "mimo-v2.5",
@@ -8866,23 +8715,6 @@ export const MODELS = {
8866
8715
  contextWindow: 1048576,
8867
8716
  maxTokens: 128000,
8868
8717
  },
8869
- "minimax-m2.5": {
8870
- id: "minimax-m2.5",
8871
- name: "MiniMax M2.5",
8872
- api: "anthropic-messages",
8873
- provider: "opencode-go",
8874
- baseUrl: "https://opencode.ai/zen/go",
8875
- reasoning: true,
8876
- input: ["text"],
8877
- cost: {
8878
- input: 0.3,
8879
- output: 1.2,
8880
- cacheRead: 0.03,
8881
- cacheWrite: 0,
8882
- },
8883
- contextWindow: 204800,
8884
- maxTokens: 65536,
8885
- },
8886
8718
  "minimax-m2.7": {
8887
8719
  id: "minimax-m2.7",
8888
8720
  name: "MiniMax M2.7",
@@ -8903,16 +8735,16 @@ export const MODELS = {
8903
8735
  },
8904
8736
  "minimax-m3": {
8905
8737
  id: "minimax-m3",
8906
- name: "MiniMax M3",
8738
+ name: "MiniMax M3 (3x usage)",
8907
8739
  api: "anthropic-messages",
8908
8740
  provider: "opencode-go",
8909
8741
  baseUrl: "https://opencode.ai/zen/go",
8910
8742
  reasoning: true,
8911
8743
  input: ["text", "image"],
8912
8744
  cost: {
8913
- input: 0.3,
8914
- output: 1.2,
8915
- cacheRead: 0.06,
8745
+ input: 0.1,
8746
+ output: 0.4,
8747
+ cacheRead: 0.02,
8916
8748
  cacheWrite: 0,
8917
8749
  },
8918
8750
  contextWindow: 512000,
@@ -9066,8 +8898,8 @@ export const MODELS = {
9066
8898
  reasoning: false,
9067
8899
  input: ["text", "image"],
9068
8900
  cost: {
9069
- input: 0.7999999999999999,
9070
- output: 3.1999999999999997,
8901
+ input: 0.8,
8902
+ output: 3.2,
9071
8903
  cacheRead: 0,
9072
8904
  cacheWrite: 0,
9073
8905
  },
@@ -9100,7 +8932,7 @@ export const MODELS = {
9100
8932
  reasoning: false,
9101
8933
  input: ["text", "image"],
9102
8934
  cost: {
9103
- input: 0.7999999999999999,
8935
+ input: 0.8,
9104
8936
  output: 4,
9105
8937
  cacheRead: 0.08,
9106
8938
  cacheWrite: 1,
@@ -9136,7 +8968,7 @@ export const MODELS = {
9136
8968
  cost: {
9137
8969
  input: 1,
9138
8970
  output: 5,
9139
- cacheRead: 0.09999999999999999,
8971
+ cacheRead: 0.1,
9140
8972
  cacheWrite: 1.25,
9141
8973
  },
9142
8974
  contextWindow: 200000,
@@ -9480,8 +9312,8 @@ export const MODELS = {
9480
9312
  reasoning: true,
9481
9313
  input: ["text", "image"],
9482
9314
  cost: {
9483
- input: 0.09999999999999999,
9484
- output: 0.39999999999999997,
9315
+ input: 0.1,
9316
+ output: 0.4,
9485
9317
  cacheRead: 0,
9486
9318
  cacheWrite: 0,
9487
9319
  },
@@ -9531,8 +9363,8 @@ export const MODELS = {
9531
9363
  reasoning: false,
9532
9364
  input: ["text"],
9533
9365
  cost: {
9534
- input: 0.20020000000000002,
9535
- output: 0.8000999999999999,
9366
+ input: 0.2002,
9367
+ output: 0.8001,
9536
9368
  cacheRead: 0,
9537
9369
  cacheWrite: 0,
9538
9370
  },
@@ -9548,7 +9380,7 @@ export const MODELS = {
9548
9380
  reasoning: false,
9549
9381
  input: ["text"],
9550
9382
  cost: {
9551
- input: 0.19999999999999998,
9383
+ input: 0.2,
9552
9384
  output: 0.77,
9553
9385
  cacheRead: 0.135,
9554
9386
  cacheWrite: 0,
@@ -9566,7 +9398,7 @@ export const MODELS = {
9566
9398
  input: ["text"],
9567
9399
  cost: {
9568
9400
  input: 0.21,
9569
- output: 0.7899999999999999,
9401
+ output: 0.79,
9570
9402
  cacheRead: 0.13,
9571
9403
  cacheWrite: 0,
9572
9404
  },
@@ -9600,7 +9432,7 @@ export const MODELS = {
9600
9432
  input: ["text"],
9601
9433
  cost: {
9602
9434
  input: 0.5,
9603
- output: 2.1500000000000004,
9435
+ output: 2.15,
9604
9436
  cacheRead: 0.35,
9605
9437
  cacheWrite: 0,
9606
9438
  },
@@ -9669,13 +9501,13 @@ export const MODELS = {
9669
9501
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
9670
9502
  input: ["text"],
9671
9503
  cost: {
9672
- input: 0.0983,
9673
- output: 0.1966,
9674
- cacheRead: 0.019700000000000002,
9504
+ input: 0.098,
9505
+ output: 0.196,
9506
+ cacheRead: 0.02,
9675
9507
  cacheWrite: 0,
9676
9508
  },
9677
9509
  contextWindow: 1048576,
9678
- maxTokens: 131072,
9510
+ maxTokens: 4096,
9679
9511
  },
9680
9512
  "deepseek/deepseek-v4-pro": {
9681
9513
  id: "deepseek/deepseek-v4-pro",
@@ -9725,7 +9557,7 @@ export const MODELS = {
9725
9557
  input: 0.3,
9726
9558
  output: 2.5,
9727
9559
  cacheRead: 0.03,
9728
- cacheWrite: 0.08333333333333334,
9560
+ cacheWrite: 0.083333,
9729
9561
  },
9730
9562
  contextWindow: 1048576,
9731
9563
  maxTokens: 65535,
@@ -9739,10 +9571,10 @@ export const MODELS = {
9739
9571
  reasoning: true,
9740
9572
  input: ["text", "image"],
9741
9573
  cost: {
9742
- input: 0.09999999999999999,
9743
- output: 0.39999999999999997,
9574
+ input: 0.1,
9575
+ output: 0.4,
9744
9576
  cacheRead: 0.01,
9745
- cacheWrite: 0.08333333333333334,
9577
+ cacheWrite: 0.083333,
9746
9578
  },
9747
9579
  contextWindow: 1048576,
9748
9580
  maxTokens: 65535,
@@ -9756,10 +9588,10 @@ export const MODELS = {
9756
9588
  reasoning: true,
9757
9589
  input: ["text", "image"],
9758
9590
  cost: {
9759
- input: 0.09999999999999999,
9760
- output: 0.39999999999999997,
9591
+ input: 0.1,
9592
+ output: 0.4,
9761
9593
  cacheRead: 0.01,
9762
- cacheWrite: 0.08333333333333334,
9594
+ cacheWrite: 0.083333,
9763
9595
  },
9764
9596
  contextWindow: 1048576,
9765
9597
  maxTokens: 65535,
@@ -9826,8 +9658,8 @@ export const MODELS = {
9826
9658
  cost: {
9827
9659
  input: 0.5,
9828
9660
  output: 3,
9829
- cacheRead: 0.049999999999999996,
9830
- cacheWrite: 0.08333333333333334,
9661
+ cacheRead: 0.05,
9662
+ cacheWrite: 0.083333,
9831
9663
  },
9832
9664
  contextWindow: 1048576,
9833
9665
  maxTokens: 65536,
@@ -9843,8 +9675,8 @@ export const MODELS = {
9843
9675
  cost: {
9844
9676
  input: 0.25,
9845
9677
  output: 1.5,
9846
- cacheRead: 0.024999999999999998,
9847
- cacheWrite: 0.08333333333333334,
9678
+ cacheRead: 0.025,
9679
+ cacheWrite: 0.083333,
9848
9680
  },
9849
9681
  contextWindow: 1048576,
9850
9682
  maxTokens: 65536,
@@ -9860,8 +9692,8 @@ export const MODELS = {
9860
9692
  cost: {
9861
9693
  input: 0.25,
9862
9694
  output: 1.5,
9863
- cacheRead: 0.024999999999999998,
9864
- cacheWrite: 0.08333333333333334,
9695
+ cacheRead: 0.025,
9696
+ cacheWrite: 0.083333,
9865
9697
  },
9866
9698
  contextWindow: 1048576,
9867
9699
  maxTokens: 65536,
@@ -9877,7 +9709,7 @@ export const MODELS = {
9877
9709
  cost: {
9878
9710
  input: 2,
9879
9711
  output: 12,
9880
- cacheRead: 0.19999999999999998,
9712
+ cacheRead: 0.2,
9881
9713
  cacheWrite: 0.375,
9882
9714
  },
9883
9715
  contextWindow: 1048576,
@@ -9894,7 +9726,7 @@ export const MODELS = {
9894
9726
  cost: {
9895
9727
  input: 2,
9896
9728
  output: 12,
9897
- cacheRead: 0.19999999999999998,
9729
+ cacheRead: 0.2,
9898
9730
  cacheWrite: 0.375,
9899
9731
  },
9900
9732
  contextWindow: 1048756,
@@ -9912,7 +9744,7 @@ export const MODELS = {
9912
9744
  input: 1.5,
9913
9745
  output: 9,
9914
9746
  cacheRead: 0.15,
9915
- cacheWrite: 0.08333333333333334,
9747
+ cacheWrite: 0.083333,
9916
9748
  },
9917
9749
  contextWindow: 1048576,
9918
9750
  maxTokens: 65536,
@@ -9926,7 +9758,7 @@ export const MODELS = {
9926
9758
  reasoning: false,
9927
9759
  input: ["text", "image"],
9928
9760
  cost: {
9929
- input: 0.049999999999999996,
9761
+ input: 0.05,
9930
9762
  output: 0.15,
9931
9763
  cacheRead: 0,
9932
9764
  cacheWrite: 0,
@@ -9995,12 +9827,12 @@ export const MODELS = {
9995
9827
  input: ["text", "image"],
9996
9828
  cost: {
9997
9829
  input: 0.12,
9998
- output: 0.36,
9830
+ output: 0.35,
9999
9831
  cacheRead: 0.09,
10000
9832
  cacheWrite: 0,
10001
9833
  },
10002
9834
  contextWindow: 262144,
10003
- maxTokens: 8192,
9835
+ maxTokens: 262144,
10004
9836
  },
10005
9837
  "google/gemma-4-31b-it:free": {
10006
9838
  id: "google/gemma-4-31b-it:free",
@@ -10028,9 +9860,9 @@ export const MODELS = {
10028
9860
  reasoning: false,
10029
9861
  input: ["text"],
10030
9862
  cost: {
10031
- input: 0.049999999999999996,
10032
- output: 0.09999999999999999,
10033
- cacheRead: 0.049999999999999996,
9863
+ input: 0.05,
9864
+ output: 0.1,
9865
+ cacheRead: 0.05,
10034
9866
  cacheWrite: 0,
10035
9867
  },
10036
9868
  contextWindow: 131072,
@@ -10048,7 +9880,7 @@ export const MODELS = {
10048
9880
  cost: {
10049
9881
  input: 0.25,
10050
9882
  output: 0.75,
10051
- cacheRead: 0.024999999999999998,
9883
+ cacheRead: 0.025,
10052
9884
  cacheWrite: 0,
10053
9885
  },
10054
9886
  contextWindow: 128000,
@@ -10131,8 +9963,8 @@ export const MODELS = {
10131
9963
  reasoning: false,
10132
9964
  input: ["text"],
10133
9965
  cost: {
10134
- input: 0.39999999999999997,
10135
- output: 0.39999999999999997,
9966
+ input: 0.4,
9967
+ output: 0.4,
10136
9968
  cacheRead: 0,
10137
9969
  cacheWrite: 0,
10138
9970
  },
@@ -10165,7 +9997,7 @@ export const MODELS = {
10165
9997
  reasoning: false,
10166
9998
  input: ["text"],
10167
9999
  cost: {
10168
- input: 0.09999999999999999,
10000
+ input: 0.1,
10169
10001
  output: 0.32,
10170
10002
  cacheRead: 0,
10171
10003
  cacheWrite: 0,
@@ -10216,7 +10048,7 @@ export const MODELS = {
10216
10048
  reasoning: false,
10217
10049
  input: ["text", "image"],
10218
10050
  cost: {
10219
- input: 0.09999999999999999,
10051
+ input: 0.1,
10220
10052
  output: 0.3,
10221
10053
  cacheRead: 0,
10222
10054
  cacheWrite: 0,
@@ -10233,7 +10065,7 @@ export const MODELS = {
10233
10065
  reasoning: true,
10234
10066
  input: ["text"],
10235
10067
  cost: {
10236
- input: 0.39999999999999997,
10068
+ input: 0.4,
10237
10069
  output: 2.2,
10238
10070
  cacheRead: 0,
10239
10071
  cacheWrite: 0,
@@ -10285,8 +10117,8 @@ export const MODELS = {
10285
10117
  input: ["text"],
10286
10118
  cost: {
10287
10119
  input: 0.15,
10288
- output: 0.8999999999999999,
10289
- cacheRead: 0.049999999999999996,
10120
+ output: 0.9,
10121
+ cacheRead: 0.05,
10290
10122
  cacheWrite: 0,
10291
10123
  },
10292
10124
  contextWindow: 204800,
@@ -10301,9 +10133,9 @@ export const MODELS = {
10301
10133
  reasoning: true,
10302
10134
  input: ["text"],
10303
10135
  cost: {
10304
- input: 0.27,
10305
- output: 1.08,
10306
- cacheRead: 0.054,
10136
+ input: 0.25,
10137
+ output: 1,
10138
+ cacheRead: 0.05,
10307
10139
  cacheWrite: 0,
10308
10140
  },
10309
10141
  contextWindow: 204800,
@@ -10336,7 +10168,7 @@ export const MODELS = {
10336
10168
  input: ["text"],
10337
10169
  cost: {
10338
10170
  input: 0.3,
10339
- output: 0.8999999999999999,
10171
+ output: 0.9,
10340
10172
  cacheRead: 0.03,
10341
10173
  cacheWrite: 0,
10342
10174
  },
@@ -10352,7 +10184,7 @@ export const MODELS = {
10352
10184
  reasoning: false,
10353
10185
  input: ["text"],
10354
10186
  cost: {
10355
- input: 0.39999999999999997,
10187
+ input: 0.4,
10356
10188
  output: 2,
10357
10189
  cacheRead: 0.04,
10358
10190
  cacheWrite: 0,
@@ -10369,8 +10201,8 @@ export const MODELS = {
10369
10201
  reasoning: false,
10370
10202
  input: ["text", "image"],
10371
10203
  cost: {
10372
- input: 0.19999999999999998,
10373
- output: 0.19999999999999998,
10204
+ input: 0.2,
10205
+ output: 0.2,
10374
10206
  cacheRead: 0.02,
10375
10207
  cacheWrite: 0,
10376
10208
  },
@@ -10386,8 +10218,8 @@ export const MODELS = {
10386
10218
  reasoning: false,
10387
10219
  input: ["text", "image"],
10388
10220
  cost: {
10389
- input: 0.09999999999999999,
10390
- output: 0.09999999999999999,
10221
+ input: 0.1,
10222
+ output: 0.1,
10391
10223
  cacheRead: 0.01,
10392
10224
  cacheWrite: 0,
10393
10225
  },
@@ -10422,7 +10254,7 @@ export const MODELS = {
10422
10254
  cost: {
10423
10255
  input: 2,
10424
10256
  output: 6,
10425
- cacheRead: 0.19999999999999998,
10257
+ cacheRead: 0.2,
10426
10258
  cacheWrite: 0,
10427
10259
  },
10428
10260
  contextWindow: 128000,
@@ -10439,7 +10271,7 @@ export const MODELS = {
10439
10271
  cost: {
10440
10272
  input: 2,
10441
10273
  output: 6,
10442
- cacheRead: 0.19999999999999998,
10274
+ cacheRead: 0.2,
10443
10275
  cacheWrite: 0,
10444
10276
  },
10445
10277
  contextWindow: 131072,
@@ -10456,7 +10288,7 @@ export const MODELS = {
10456
10288
  cost: {
10457
10289
  input: 0.5,
10458
10290
  output: 1.5,
10459
- cacheRead: 0.049999999999999996,
10291
+ cacheRead: 0.05,
10460
10292
  cacheWrite: 0,
10461
10293
  },
10462
10294
  contextWindow: 262144,
@@ -10471,7 +10303,7 @@ export const MODELS = {
10471
10303
  reasoning: false,
10472
10304
  input: ["text", "image"],
10473
10305
  cost: {
10474
- input: 0.39999999999999997,
10306
+ input: 0.4,
10475
10307
  output: 2,
10476
10308
  cacheRead: 0.04,
10477
10309
  cacheWrite: 0,
@@ -10505,7 +10337,7 @@ export const MODELS = {
10505
10337
  reasoning: false,
10506
10338
  input: ["text", "image"],
10507
10339
  cost: {
10508
- input: 0.39999999999999997,
10340
+ input: 0.4,
10509
10341
  output: 2,
10510
10342
  cacheRead: 0.04,
10511
10343
  cacheWrite: 0,
@@ -10539,7 +10371,7 @@ export const MODELS = {
10539
10371
  reasoning: false,
10540
10372
  input: ["text"],
10541
10373
  cost: {
10542
- input: 0.19999999999999998,
10374
+ input: 0.2,
10543
10375
  output: 0.6,
10544
10376
  cacheRead: 0.02,
10545
10377
  cacheWrite: 0,
@@ -10574,7 +10406,7 @@ export const MODELS = {
10574
10406
  input: ["text", "image"],
10575
10407
  cost: {
10576
10408
  input: 0.075,
10577
- output: 0.19999999999999998,
10409
+ output: 0.2,
10578
10410
  cacheRead: 0,
10579
10411
  cacheWrite: 0,
10580
10412
  },
@@ -10592,7 +10424,7 @@ export const MODELS = {
10592
10424
  cost: {
10593
10425
  input: 2,
10594
10426
  output: 6,
10595
- cacheRead: 0.19999999999999998,
10427
+ cacheRead: 0.2,
10596
10428
  cacheWrite: 0,
10597
10429
  },
10598
10430
  contextWindow: 65536,
@@ -10607,7 +10439,7 @@ export const MODELS = {
10607
10439
  reasoning: false,
10608
10440
  input: ["text"],
10609
10441
  cost: {
10610
- input: 0.09999999999999999,
10442
+ input: 0.1,
10611
10443
  output: 0.3,
10612
10444
  cacheRead: 0.01,
10613
10445
  cacheWrite: 0,
@@ -10624,7 +10456,7 @@ export const MODELS = {
10624
10456
  reasoning: false,
10625
10457
  input: ["text"],
10626
10458
  cost: {
10627
- input: 0.5700000000000001,
10459
+ input: 0.57,
10628
10460
  output: 2.3,
10629
10461
  cacheRead: 0,
10630
10462
  cacheWrite: 0,
@@ -10693,31 +10525,30 @@ export const MODELS = {
10693
10525
  reasoning: true,
10694
10526
  input: ["text", "image"],
10695
10527
  cost: {
10696
- input: 0.6799999999999999,
10528
+ input: 0.68,
10697
10529
  output: 3.41,
10698
- cacheRead: 0.33999999999999997,
10530
+ cacheRead: 0.34,
10699
10531
  cacheWrite: 0,
10700
10532
  },
10701
10533
  contextWindow: 262144,
10702
10534
  maxTokens: 262142,
10703
10535
  },
10704
- "moonshotai/kimi-k2.6:free": {
10705
- id: "moonshotai/kimi-k2.6:free",
10706
- name: "MoonshotAI: Kimi K2.6 (free)",
10536
+ "moonshotai/kimi-k2.7-code": {
10537
+ id: "moonshotai/kimi-k2.7-code",
10538
+ name: "MoonshotAI: Kimi K2.7 Code",
10707
10539
  api: "openai-completions",
10708
10540
  provider: "openrouter",
10709
10541
  baseUrl: "https://openrouter.ai/api/v1",
10710
- compat: { "supportsDeveloperRole": false, "requiresReasoningContentOnAssistantMessages": true },
10711
10542
  reasoning: true,
10712
10543
  input: ["text", "image"],
10713
10544
  cost: {
10714
- input: 0,
10715
- output: 0,
10716
- cacheRead: 0,
10545
+ input: 0.75,
10546
+ output: 3.5,
10547
+ cacheRead: 0.16,
10717
10548
  cacheWrite: 0,
10718
10549
  },
10719
10550
  contextWindow: 262144,
10720
- maxTokens: 4096,
10551
+ maxTokens: 262144,
10721
10552
  },
10722
10553
  "nex-agi/nex-n2-pro:free": {
10723
10554
  id: "nex-agi/nex-n2-pro:free",
@@ -10745,8 +10576,8 @@ export const MODELS = {
10745
10576
  reasoning: true,
10746
10577
  input: ["text"],
10747
10578
  cost: {
10748
- input: 0.39999999999999997,
10749
- output: 0.39999999999999997,
10579
+ input: 0.4,
10580
+ output: 0.4,
10750
10581
  cacheRead: 0,
10751
10582
  cacheWrite: 0,
10752
10583
  },
@@ -10762,8 +10593,8 @@ export const MODELS = {
10762
10593
  reasoning: true,
10763
10594
  input: ["text"],
10764
10595
  cost: {
10765
- input: 0.049999999999999996,
10766
- output: 0.19999999999999998,
10596
+ input: 0.05,
10597
+ output: 0.2,
10767
10598
  cacheRead: 0,
10768
10599
  cacheWrite: 0,
10769
10600
  },
@@ -10814,7 +10645,7 @@ export const MODELS = {
10814
10645
  input: ["text"],
10815
10646
  cost: {
10816
10647
  input: 0.09,
10817
- output: 0.44999999999999996,
10648
+ output: 0.45,
10818
10649
  cacheRead: 0,
10819
10650
  cacheWrite: 0,
10820
10651
  },
@@ -10889,23 +10720,6 @@ export const MODELS = {
10889
10720
  contextWindow: 128000,
10890
10721
  maxTokens: 128000,
10891
10722
  },
10892
- "nvidia/nemotron-nano-9b-v2": {
10893
- id: "nvidia/nemotron-nano-9b-v2",
10894
- name: "NVIDIA: Nemotron Nano 9B V2",
10895
- api: "openai-completions",
10896
- provider: "openrouter",
10897
- baseUrl: "https://openrouter.ai/api/v1",
10898
- reasoning: true,
10899
- input: ["text"],
10900
- cost: {
10901
- input: 0.04,
10902
- output: 0.16,
10903
- cacheRead: 0,
10904
- cacheWrite: 0,
10905
- },
10906
- contextWindow: 131072,
10907
- maxTokens: 16384,
10908
- },
10909
10723
  "nvidia/nemotron-nano-9b-v2:free": {
10910
10724
  id: "nvidia/nemotron-nano-9b-v2:free",
10911
10725
  name: "NVIDIA: Nemotron Nano 9B V2 (free)",
@@ -11051,9 +10865,9 @@ export const MODELS = {
11051
10865
  reasoning: false,
11052
10866
  input: ["text", "image"],
11053
10867
  cost: {
11054
- input: 0.39999999999999997,
11055
- output: 1.5999999999999999,
11056
- cacheRead: 0.09999999999999999,
10868
+ input: 0.4,
10869
+ output: 1.6,
10870
+ cacheRead: 0.1,
11057
10871
  cacheWrite: 0,
11058
10872
  },
11059
10873
  contextWindow: 1047576,
@@ -11068,9 +10882,9 @@ export const MODELS = {
11068
10882
  reasoning: false,
11069
10883
  input: ["text", "image"],
11070
10884
  cost: {
11071
- input: 0.09999999999999999,
11072
- output: 0.39999999999999997,
11073
- cacheRead: 0.024999999999999998,
10885
+ input: 0.1,
10886
+ output: 0.4,
10887
+ cacheRead: 0.025,
11074
10888
  cacheWrite: 0,
11075
10889
  },
11076
10890
  contextWindow: 1047576,
@@ -11223,7 +11037,7 @@ export const MODELS = {
11223
11037
  cost: {
11224
11038
  input: 0.25,
11225
11039
  output: 2,
11226
- cacheRead: 0.024999999999999998,
11040
+ cacheRead: 0.025,
11227
11041
  cacheWrite: 0,
11228
11042
  },
11229
11043
  contextWindow: 400000,
@@ -11238,8 +11052,8 @@ export const MODELS = {
11238
11052
  reasoning: true,
11239
11053
  input: ["text", "image"],
11240
11054
  cost: {
11241
- input: 0.049999999999999996,
11242
- output: 0.39999999999999997,
11055
+ input: 0.05,
11056
+ output: 0.4,
11243
11057
  cacheRead: 0.01,
11244
11058
  cacheWrite: 0,
11245
11059
  },
@@ -11342,7 +11156,7 @@ export const MODELS = {
11342
11156
  cost: {
11343
11157
  input: 0.25,
11344
11158
  output: 2,
11345
- cacheRead: 0.024999999999999998,
11159
+ cacheRead: 0.025,
11346
11160
  cacheWrite: 0,
11347
11161
  },
11348
11162
  contextWindow: 400000,
@@ -11502,7 +11316,7 @@ export const MODELS = {
11502
11316
  thinkingLevelMap: { "xhigh": "xhigh" },
11503
11317
  input: ["text", "image"],
11504
11318
  cost: {
11505
- input: 0.19999999999999998,
11319
+ input: 0.2,
11506
11320
  output: 1.25,
11507
11321
  cacheRead: 0.02,
11508
11322
  cacheWrite: 0,
@@ -11947,7 +11761,7 @@ export const MODELS = {
11947
11761
  reasoning: true,
11948
11762
  input: ["text"],
11949
11763
  cost: {
11950
- input: 0.19999999999999998,
11764
+ input: 0.2,
11951
11765
  output: 1.1,
11952
11766
  cacheRead: 0,
11953
11767
  cacheWrite: 0,
@@ -11965,7 +11779,7 @@ export const MODELS = {
11965
11779
  input: ["text"],
11966
11780
  cost: {
11967
11781
  input: 0.36,
11968
- output: 0.39999999999999997,
11782
+ output: 0.4,
11969
11783
  cacheRead: 0,
11970
11784
  cacheWrite: 0,
11971
11785
  },
@@ -11983,7 +11797,7 @@ export const MODELS = {
11983
11797
  cost: {
11984
11798
  input: 0.26,
11985
11799
  output: 0.78,
11986
- cacheRead: 0.052000000000000005,
11800
+ cacheRead: 0.052,
11987
11801
  cacheWrite: 0.325,
11988
11802
  },
11989
11803
  contextWindow: 1000000,
@@ -12032,7 +11846,7 @@ export const MODELS = {
12032
11846
  reasoning: true,
12033
11847
  input: ["text"],
12034
11848
  cost: {
12035
- input: 0.09999999999999999,
11849
+ input: 0.1,
12036
11850
  output: 0.24,
12037
11851
  cacheRead: 0,
12038
11852
  cacheWrite: 0,
@@ -12049,8 +11863,8 @@ export const MODELS = {
12049
11863
  reasoning: true,
12050
11864
  input: ["text"],
12051
11865
  cost: {
12052
- input: 0.45499999999999996,
12053
- output: 1.8199999999999998,
11866
+ input: 0.455,
11867
+ output: 1.82,
12054
11868
  cacheRead: 0,
12055
11869
  cacheWrite: 0,
12056
11870
  },
@@ -12067,7 +11881,7 @@ export const MODELS = {
12067
11881
  input: ["text"],
12068
11882
  cost: {
12069
11883
  input: 0.09,
12070
- output: 0.09999999999999999,
11884
+ output: 0.1,
12071
11885
  cacheRead: 0,
12072
11886
  cacheWrite: 0,
12073
11887
  },
@@ -12083,9 +11897,9 @@ export const MODELS = {
12083
11897
  reasoning: true,
12084
11898
  input: ["text"],
12085
11899
  cost: {
12086
- input: 0.09999999999999999,
12087
- output: 0.09999999999999999,
12088
- cacheRead: 0.09999999999999999,
11900
+ input: 0.1,
11901
+ output: 0.1,
11902
+ cacheRead: 0.1,
12089
11903
  cacheWrite: 0,
12090
11904
  },
12091
11905
  contextWindow: 262144,
@@ -12135,7 +11949,7 @@ export const MODELS = {
12135
11949
  input: ["text"],
12136
11950
  cost: {
12137
11951
  input: 0.08,
12138
- output: 0.39999999999999997,
11952
+ output: 0.4,
12139
11953
  cacheRead: 0.08,
12140
11954
  cacheWrite: 0,
12141
11955
  },
@@ -12168,9 +11982,9 @@ export const MODELS = {
12168
11982
  reasoning: true,
12169
11983
  input: ["text"],
12170
11984
  cost: {
12171
- input: 0.049999999999999996,
12172
- output: 0.39999999999999997,
12173
- cacheRead: 0.049999999999999996,
11985
+ input: 0.05,
11986
+ output: 0.4,
11987
+ cacheRead: 0.05,
12174
11988
  cacheWrite: 0,
12175
11989
  },
12176
11990
  contextWindow: 131072,
@@ -12186,7 +12000,7 @@ export const MODELS = {
12186
12000
  input: ["text"],
12187
12001
  cost: {
12188
12002
  input: 0.22,
12189
- output: 1.7999999999999998,
12003
+ output: 1.8,
12190
12004
  cacheRead: 0,
12191
12005
  cacheWrite: 0,
12192
12006
  },
@@ -12237,7 +12051,7 @@ export const MODELS = {
12237
12051
  input: ["text"],
12238
12052
  cost: {
12239
12053
  input: 0.11,
12240
- output: 0.7999999999999999,
12054
+ output: 0.8,
12241
12055
  cacheRead: 0.07,
12242
12056
  cacheWrite: 0,
12243
12057
  },
@@ -12372,7 +12186,7 @@ export const MODELS = {
12372
12186
  reasoning: false,
12373
12187
  input: ["text", "image"],
12374
12188
  cost: {
12375
- input: 0.19999999999999998,
12189
+ input: 0.2,
12376
12190
  output: 0.88,
12377
12191
  cacheRead: 0.11,
12378
12192
  cacheWrite: 0,
@@ -12440,8 +12254,8 @@ export const MODELS = {
12440
12254
  reasoning: false,
12441
12255
  input: ["text", "image"],
12442
12256
  cost: {
12443
- input: 0.10400000000000001,
12444
- output: 0.41600000000000004,
12257
+ input: 0.104,
12258
+ output: 0.416,
12445
12259
  cacheRead: 0,
12446
12260
  cacheWrite: 0,
12447
12261
  },
@@ -12527,7 +12341,7 @@ export const MODELS = {
12527
12341
  cost: {
12528
12342
  input: 0.14,
12529
12343
  output: 1,
12530
- cacheRead: 0.049999999999999996,
12344
+ cacheRead: 0.05,
12531
12345
  cacheWrite: 0,
12532
12346
  },
12533
12347
  contextWindow: 262144,
@@ -12559,7 +12373,7 @@ export const MODELS = {
12559
12373
  reasoning: true,
12560
12374
  input: ["text", "image"],
12561
12375
  cost: {
12562
- input: 0.09999999999999999,
12376
+ input: 0.1,
12563
12377
  output: 0.15,
12564
12378
  cacheRead: 0,
12565
12379
  cacheWrite: 0,
@@ -12611,7 +12425,7 @@ export const MODELS = {
12611
12425
  input: ["text", "image"],
12612
12426
  cost: {
12613
12427
  input: 0.3,
12614
- output: 1.7999999999999998,
12428
+ output: 1.8,
12615
12429
  cacheRead: 0,
12616
12430
  cacheWrite: 0.375,
12617
12431
  },
@@ -12627,13 +12441,13 @@ export const MODELS = {
12627
12441
  reasoning: true,
12628
12442
  input: ["text", "image"],
12629
12443
  cost: {
12630
- input: 0.28900000000000003,
12631
- output: 2.4,
12444
+ input: 0.2885,
12445
+ output: 3.17,
12632
12446
  cacheRead: 0,
12633
12447
  cacheWrite: 0,
12634
12448
  },
12635
12449
  contextWindow: 262144,
12636
- maxTokens: 131072,
12450
+ maxTokens: 262140,
12637
12451
  },
12638
12452
  "qwen/qwen3.6-35b-a3b": {
12639
12453
  id: "qwen/qwen3.6-35b-a3b",
@@ -12644,13 +12458,13 @@ export const MODELS = {
12644
12458
  reasoning: true,
12645
12459
  input: ["text", "image"],
12646
12460
  cost: {
12647
- input: 0.14,
12461
+ input: 0.15,
12648
12462
  output: 1,
12649
- cacheRead: 0,
12463
+ cacheRead: 0.05,
12650
12464
  cacheWrite: 0,
12651
12465
  },
12652
12466
  contextWindow: 262144,
12653
- maxTokens: 262140,
12467
+ maxTokens: 262144,
12654
12468
  },
12655
12469
  "qwen/qwen3.6-flash": {
12656
12470
  id: "qwen/qwen3.6-flash",
@@ -12729,10 +12543,10 @@ export const MODELS = {
12729
12543
  reasoning: true,
12730
12544
  input: ["text", "image"],
12731
12545
  cost: {
12732
- input: 0.39999999999999997,
12733
- output: 1.5999999999999999,
12734
- cacheRead: 0.08,
12735
- cacheWrite: 0.5,
12546
+ input: 0.32,
12547
+ output: 1.28,
12548
+ cacheRead: 0.064,
12549
+ cacheWrite: 0.4,
12736
12550
  },
12737
12551
  contextWindow: 1000000,
12738
12552
  maxTokens: 65536,
@@ -12746,8 +12560,8 @@ export const MODELS = {
12746
12560
  reasoning: false,
12747
12561
  input: ["text", "image"],
12748
12562
  cost: {
12749
- input: 0.09999999999999999,
12750
- output: 0.09999999999999999,
12563
+ input: 0.1,
12564
+ output: 0.1,
12751
12565
  cacheRead: 0,
12752
12566
  cacheWrite: 0,
12753
12567
  },
@@ -12814,7 +12628,7 @@ export const MODELS = {
12814
12628
  reasoning: true,
12815
12629
  input: ["text", "image"],
12816
12630
  cost: {
12817
- input: 0.19999999999999998,
12631
+ input: 0.2,
12818
12632
  output: 1.15,
12819
12633
  cacheRead: 0.04,
12820
12634
  cacheWrite: 0,
@@ -12833,7 +12647,7 @@ export const MODELS = {
12833
12647
  cost: {
12834
12648
  input: 0.063,
12835
12649
  output: 0.21,
12836
- cacheRead: 0.020999999999999998,
12650
+ cacheRead: 0.021,
12837
12651
  cacheWrite: 0,
12838
12652
  },
12839
12653
  contextWindow: 262144,
@@ -12848,7 +12662,7 @@ export const MODELS = {
12848
12662
  reasoning: false,
12849
12663
  input: ["text"],
12850
12664
  cost: {
12851
- input: 0.16999999999999998,
12665
+ input: 0.17,
12852
12666
  output: 0.43,
12853
12667
  cacheRead: 0,
12854
12668
  cacheWrite: 0,
@@ -12865,8 +12679,8 @@ export const MODELS = {
12865
12679
  reasoning: false,
12866
12680
  input: ["text"],
12867
12681
  cost: {
12868
- input: 0.39999999999999997,
12869
- output: 0.39999999999999997,
12682
+ input: 0.4,
12683
+ output: 0.4,
12870
12684
  cacheRead: 0,
12871
12685
  cacheWrite: 0,
12872
12686
  },
@@ -12901,7 +12715,7 @@ export const MODELS = {
12901
12715
  cost: {
12902
12716
  input: 1.25,
12903
12717
  output: 2.5,
12904
- cacheRead: 0.19999999999999998,
12718
+ cacheRead: 0.2,
12905
12719
  cacheWrite: 0,
12906
12720
  },
12907
12721
  contextWindow: 2000000,
@@ -12918,7 +12732,7 @@ export const MODELS = {
12918
12732
  cost: {
12919
12733
  input: 1.25,
12920
12734
  output: 2.5,
12921
- cacheRead: 0.19999999999999998,
12735
+ cacheRead: 0.2,
12922
12736
  cacheWrite: 0,
12923
12737
  },
12924
12738
  contextWindow: 1000000,
@@ -12935,7 +12749,7 @@ export const MODELS = {
12935
12749
  cost: {
12936
12750
  input: 1,
12937
12751
  output: 2,
12938
- cacheRead: 0.19999999999999998,
12752
+ cacheRead: 0.2,
12939
12753
  cacheWrite: 0,
12940
12754
  },
12941
12755
  contextWindow: 256000,
@@ -12950,7 +12764,7 @@ export const MODELS = {
12950
12764
  reasoning: true,
12951
12765
  input: ["text"],
12952
12766
  cost: {
12953
- input: 0.09999999999999999,
12767
+ input: 0.1,
12954
12768
  output: 0.3,
12955
12769
  cacheRead: 0.01,
12956
12770
  cacheWrite: 0,
@@ -13036,7 +12850,7 @@ export const MODELS = {
13036
12850
  input: ["text", "image"],
13037
12851
  cost: {
13038
12852
  input: 0.6,
13039
- output: 1.7999999999999998,
12853
+ output: 1.8,
13040
12854
  cacheRead: 0.11,
13041
12855
  cacheWrite: 0,
13042
12856
  },
@@ -13070,7 +12884,7 @@ export const MODELS = {
13070
12884
  input: ["text", "image"],
13071
12885
  cost: {
13072
12886
  input: 0.3,
13073
- output: 0.8999999999999999,
12887
+ output: 0.9,
13074
12888
  cacheRead: 0.055,
13075
12889
  cacheWrite: 0,
13076
12890
  },
@@ -13086,7 +12900,7 @@ export const MODELS = {
13086
12900
  reasoning: true,
13087
12901
  input: ["text"],
13088
12902
  cost: {
13089
- input: 0.39999999999999997,
12903
+ input: 0.4,
13090
12904
  output: 1.75,
13091
12905
  cacheRead: 0.08,
13092
12906
  cacheWrite: 0,
@@ -13104,7 +12918,7 @@ export const MODELS = {
13104
12918
  input: ["text"],
13105
12919
  cost: {
13106
12920
  input: 0.06,
13107
- output: 0.39999999999999997,
12921
+ output: 0.4,
13108
12922
  cacheRead: 0.01,
13109
12923
  cacheWrite: 0,
13110
12924
  },
@@ -13190,7 +13004,7 @@ export const MODELS = {
13190
13004
  cost: {
13191
13005
  input: 1,
13192
13006
  output: 5,
13193
- cacheRead: 0.09999999999999999,
13007
+ cacheRead: 0.1,
13194
13008
  cacheWrite: 1.25,
13195
13009
  },
13196
13010
  contextWindow: 200000,
@@ -13242,7 +13056,7 @@ export const MODELS = {
13242
13056
  input: 1.5,
13243
13057
  output: 9,
13244
13058
  cacheRead: 0.15,
13245
- cacheWrite: 0.08333333333333334,
13059
+ cacheWrite: 0.083333,
13246
13060
  },
13247
13061
  contextWindow: 1048576,
13248
13062
  maxTokens: 65536,
@@ -13258,7 +13072,7 @@ export const MODELS = {
13258
13072
  cost: {
13259
13073
  input: 2,
13260
13074
  output: 12,
13261
- cacheRead: 0.19999999999999998,
13075
+ cacheRead: 0.2,
13262
13076
  cacheWrite: 0.375,
13263
13077
  },
13264
13078
  contextWindow: 1048576,
@@ -13273,9 +13087,9 @@ export const MODELS = {
13273
13087
  reasoning: true,
13274
13088
  input: ["text", "image"],
13275
13089
  cost: {
13276
- input: 0.6799999999999999,
13090
+ input: 0.68,
13277
13091
  output: 3.41,
13278
- cacheRead: 0.33999999999999997,
13092
+ cacheRead: 0.34,
13279
13093
  cacheWrite: 0,
13280
13094
  },
13281
13095
  contextWindow: 262144,
@@ -13317,25 +13131,6 @@ export const MODELS = {
13317
13131
  },
13318
13132
  },
13319
13133
  "together": {
13320
- "MiniMaxAI/MiniMax-M2.5": {
13321
- id: "MiniMaxAI/MiniMax-M2.5",
13322
- name: "MiniMax-M2.5",
13323
- api: "openai-completions",
13324
- provider: "together",
13325
- baseUrl: "https://api.together.ai/v1",
13326
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
13327
- reasoning: true,
13328
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
13329
- input: ["text"],
13330
- cost: {
13331
- input: 0.3,
13332
- output: 1.2,
13333
- cacheRead: 0.06,
13334
- cacheWrite: 0,
13335
- },
13336
- contextWindow: 204800,
13337
- maxTokens: 131072,
13338
- },
13339
13134
  "MiniMaxAI/MiniMax-M2.7": {
13340
13135
  id: "MiniMaxAI/MiniMax-M2.7",
13341
13136
  name: "MiniMax-M2.7",
@@ -13355,28 +13150,28 @@ export const MODELS = {
13355
13150
  contextWindow: 202752,
13356
13151
  maxTokens: 131072,
13357
13152
  },
13358
- "Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
13359
- id: "Qwen/Qwen3-235B-A22B-Instruct-2507-tput",
13360
- name: "Qwen3 235B A22B Instruct 2507 FP8",
13153
+ "MiniMaxAI/MiniMax-M3": {
13154
+ id: "MiniMaxAI/MiniMax-M3",
13155
+ name: "MiniMax-M3",
13361
13156
  api: "openai-completions",
13362
13157
  provider: "together",
13363
13158
  baseUrl: "https://api.together.ai/v1",
13364
13159
  compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
13365
13160
  reasoning: true,
13366
13161
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
13367
- input: ["text"],
13162
+ input: ["text", "image"],
13368
13163
  cost: {
13369
- input: 0.2,
13370
- output: 0.6,
13371
- cacheRead: 0,
13164
+ input: 0.3,
13165
+ output: 1.2,
13166
+ cacheRead: 0.06,
13372
13167
  cacheWrite: 0,
13373
13168
  },
13374
- contextWindow: 262144,
13375
- maxTokens: 262144,
13169
+ contextWindow: 524288,
13170
+ maxTokens: 250000,
13376
13171
  },
13377
- "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {
13378
- id: "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
13379
- name: "Qwen3 Coder 480B A35B Instruct",
13172
+ "Qwen/Qwen2.5-7B-Instruct-Turbo": {
13173
+ id: "Qwen/Qwen2.5-7B-Instruct-Turbo",
13174
+ name: "Qwen 2.5 7B Instruct Turbo",
13380
13175
  api: "openai-completions",
13381
13176
  provider: "together",
13382
13177
  baseUrl: "https://api.together.ai/v1",
@@ -13384,27 +13179,26 @@ export const MODELS = {
13384
13179
  reasoning: false,
13385
13180
  input: ["text"],
13386
13181
  cost: {
13387
- input: 2,
13388
- output: 2,
13182
+ input: 0.3,
13183
+ output: 0.3,
13389
13184
  cacheRead: 0,
13390
13185
  cacheWrite: 0,
13391
13186
  },
13392
- contextWindow: 262144,
13393
- maxTokens: 262144,
13187
+ contextWindow: 32768,
13188
+ maxTokens: 32768,
13394
13189
  },
13395
- "Qwen/Qwen3-Coder-Next-FP8": {
13396
- id: "Qwen/Qwen3-Coder-Next-FP8",
13397
- name: "Qwen3 Coder Next FP8",
13190
+ "Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
13191
+ id: "Qwen/Qwen3-235B-A22B-Instruct-2507-tput",
13192
+ name: "Qwen3 235B A22B Instruct 2507 FP8",
13398
13193
  api: "openai-completions",
13399
13194
  provider: "together",
13400
13195
  baseUrl: "https://api.together.ai/v1",
13401
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
13402
- reasoning: true,
13403
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
13196
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
13197
+ reasoning: false,
13404
13198
  input: ["text"],
13405
13199
  cost: {
13406
- input: 0.5,
13407
- output: 1.2,
13200
+ input: 0.2,
13201
+ output: 0.6,
13408
13202
  cacheRead: 0,
13409
13203
  cacheWrite: 0,
13410
13204
  },
@@ -13430,47 +13224,28 @@ export const MODELS = {
13430
13224
  contextWindow: 262144,
13431
13225
  maxTokens: 130000,
13432
13226
  },
13433
- "Qwen/Qwen3.6-Plus": {
13434
- id: "Qwen/Qwen3.6-Plus",
13435
- name: "Qwen3.6 Plus",
13436
- api: "openai-completions",
13437
- provider: "together",
13438
- baseUrl: "https://api.together.ai/v1",
13439
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
13440
- reasoning: true,
13441
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
13442
- input: ["text"],
13443
- cost: {
13444
- input: 0.5,
13445
- output: 3,
13446
- cacheRead: 0,
13447
- cacheWrite: 0,
13448
- },
13449
- contextWindow: 1000000,
13450
- maxTokens: 500000,
13451
- },
13452
- "Qwen/Qwen3.7-Max": {
13453
- id: "Qwen/Qwen3.7-Max",
13454
- name: "Qwen3.7 Max",
13227
+ "Qwen/Qwen3.5-9B": {
13228
+ id: "Qwen/Qwen3.5-9B",
13229
+ name: "Qwen3.5 9B",
13455
13230
  api: "openai-completions",
13456
13231
  provider: "together",
13457
13232
  baseUrl: "https://api.together.ai/v1",
13458
13233
  compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
13459
13234
  reasoning: true,
13460
13235
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
13461
- input: ["text"],
13236
+ input: ["text", "image"],
13462
13237
  cost: {
13463
- input: 2.5,
13464
- output: 7.5,
13238
+ input: 0.17,
13239
+ output: 0.25,
13465
13240
  cacheRead: 0,
13466
13241
  cacheWrite: 0,
13467
13242
  },
13468
- contextWindow: 1000000,
13469
- maxTokens: 500000,
13243
+ contextWindow: 262144,
13244
+ maxTokens: 65536,
13470
13245
  },
13471
- "deepseek-ai/DeepSeek-V3": {
13472
- id: "deepseek-ai/DeepSeek-V3",
13473
- name: "DeepSeek-V3",
13246
+ "Qwen/Qwen3.6-Plus": {
13247
+ id: "Qwen/Qwen3.6-Plus",
13248
+ name: "Qwen3.6 Plus",
13474
13249
  api: "openai-completions",
13475
13250
  provider: "together",
13476
13251
  baseUrl: "https://api.together.ai/v1",
@@ -13479,32 +13254,31 @@ export const MODELS = {
13479
13254
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
13480
13255
  input: ["text"],
13481
13256
  cost: {
13482
- input: 1.25,
13483
- output: 1.25,
13257
+ input: 0.5,
13258
+ output: 3,
13484
13259
  cacheRead: 0,
13485
13260
  cacheWrite: 0,
13486
13261
  },
13487
- contextWindow: 131072,
13488
- maxTokens: 131072,
13262
+ contextWindow: 1000000,
13263
+ maxTokens: 500000,
13489
13264
  },
13490
- "deepseek-ai/DeepSeek-V3-1": {
13491
- id: "deepseek-ai/DeepSeek-V3-1",
13492
- name: "DeepSeek V3.1",
13265
+ "Qwen/Qwen3.7-Max": {
13266
+ id: "Qwen/Qwen3.7-Max",
13267
+ name: "Qwen3.7 Max",
13493
13268
  api: "openai-completions",
13494
13269
  provider: "together",
13495
13270
  baseUrl: "https://api.together.ai/v1",
13496
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
13497
- reasoning: true,
13498
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
13271
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
13272
+ reasoning: false,
13499
13273
  input: ["text"],
13500
13274
  cost: {
13501
- input: 0.6,
13502
- output: 1.7,
13275
+ input: 2.5,
13276
+ output: 7.5,
13503
13277
  cacheRead: 0,
13504
13278
  cacheWrite: 0,
13505
13279
  },
13506
- contextWindow: 131072,
13507
- maxTokens: 131072,
13280
+ contextWindow: 1000000,
13281
+ maxTokens: 500000,
13508
13282
  },
13509
13283
  "deepseek-ai/DeepSeek-V4-Pro": {
13510
13284
  id: "deepseek-ai/DeepSeek-V4-Pro",
@@ -13517,8 +13291,8 @@ export const MODELS = {
13517
13291
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null },
13518
13292
  input: ["text"],
13519
13293
  cost: {
13520
- input: 2.1,
13521
- output: 4.4,
13294
+ input: 1.74,
13295
+ output: 3.48,
13522
13296
  cacheRead: 0.2,
13523
13297
  cacheWrite: 0,
13524
13298
  },
@@ -13554,8 +13328,8 @@ export const MODELS = {
13554
13328
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
13555
13329
  input: ["text", "image"],
13556
13330
  cost: {
13557
- input: 0.2,
13558
- output: 0.5,
13331
+ input: 0.39,
13332
+ output: 0.97,
13559
13333
  cacheRead: 0,
13560
13334
  cacheWrite: 0,
13561
13335
  },
@@ -13580,25 +13354,6 @@ export const MODELS = {
13580
13354
  contextWindow: 131072,
13581
13355
  maxTokens: 131072,
13582
13356
  },
13583
- "moonshotai/Kimi-K2.5": {
13584
- id: "moonshotai/Kimi-K2.5",
13585
- name: "Kimi K2.5",
13586
- api: "openai-completions",
13587
- provider: "together",
13588
- baseUrl: "https://api.together.ai/v1",
13589
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
13590
- reasoning: true,
13591
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
13592
- input: ["text", "image"],
13593
- cost: {
13594
- input: 0.5,
13595
- output: 2.8,
13596
- cacheRead: 0,
13597
- cacheWrite: 0,
13598
- },
13599
- contextWindow: 262144,
13600
- maxTokens: 262144,
13601
- },
13602
13357
  "moonshotai/Kimi-K2.6": {
13603
13358
  id: "moonshotai/Kimi-K2.6",
13604
13359
  name: "Kimi K2.6",
@@ -13656,6 +13411,44 @@ export const MODELS = {
13656
13411
  contextWindow: 131072,
13657
13412
  maxTokens: 131072,
13658
13413
  },
13414
+ "openai/gpt-oss-20b": {
13415
+ id: "openai/gpt-oss-20b",
13416
+ name: "GPT OSS 20B",
13417
+ api: "openai-completions",
13418
+ provider: "together",
13419
+ baseUrl: "https://api.together.ai/v1",
13420
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "openai" },
13421
+ reasoning: true,
13422
+ thinkingLevelMap: { "off": null, "minimal": null },
13423
+ input: ["text"],
13424
+ cost: {
13425
+ input: 0.05,
13426
+ output: 0.2,
13427
+ cacheRead: 0,
13428
+ cacheWrite: 0,
13429
+ },
13430
+ contextWindow: 131072,
13431
+ maxTokens: 131072,
13432
+ },
13433
+ "zai-org/GLM-5": {
13434
+ id: "zai-org/GLM-5",
13435
+ name: "GLM-5",
13436
+ api: "openai-completions",
13437
+ provider: "together",
13438
+ baseUrl: "https://api.together.ai/v1",
13439
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
13440
+ reasoning: true,
13441
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
13442
+ input: ["text"],
13443
+ cost: {
13444
+ input: 1,
13445
+ output: 3.2,
13446
+ cacheRead: 0,
13447
+ cacheWrite: 0,
13448
+ },
13449
+ contextWindow: 202752,
13450
+ maxTokens: 131072,
13451
+ },
13659
13452
  "zai-org/GLM-5.1": {
13660
13453
  id: "zai-org/GLM-5.1",
13661
13454
  name: "GLM-5.1",
@@ -13771,7 +13564,7 @@ export const MODELS = {
13771
13564
  reasoning: true,
13772
13565
  input: ["text", "image"],
13773
13566
  cost: {
13774
- input: 0.39999999999999997,
13567
+ input: 0.4,
13775
13568
  output: 4,
13776
13569
  cacheRead: 0,
13777
13570
  cacheWrite: 0,
@@ -13841,7 +13634,7 @@ export const MODELS = {
13841
13634
  cost: {
13842
13635
  input: 1,
13843
13636
  output: 5,
13844
- cacheRead: 0.19999999999999998,
13637
+ cacheRead: 0.2,
13845
13638
  cacheWrite: 0,
13846
13639
  },
13847
13640
  contextWindow: 1000000,
@@ -13941,7 +13734,7 @@ export const MODELS = {
13941
13734
  reasoning: true,
13942
13735
  input: ["text", "image"],
13943
13736
  cost: {
13944
- input: 0.39999999999999997,
13737
+ input: 0.4,
13945
13738
  output: 4,
13946
13739
  cacheRead: 0,
13947
13740
  cacheWrite: 0,
@@ -13958,8 +13751,8 @@ export const MODELS = {
13958
13751
  reasoning: true,
13959
13752
  input: ["text", "image"],
13960
13753
  cost: {
13961
- input: 0.09999999999999999,
13962
- output: 0.39999999999999997,
13754
+ input: 0.1,
13755
+ output: 0.4,
13963
13756
  cacheRead: 0.001,
13964
13757
  cacheWrite: 0.125,
13965
13758
  },
@@ -13975,7 +13768,7 @@ export const MODELS = {
13975
13768
  reasoning: true,
13976
13769
  input: ["text", "image"],
13977
13770
  cost: {
13978
- input: 0.39999999999999997,
13771
+ input: 0.4,
13979
13772
  output: 2.4,
13980
13773
  cacheRead: 0.04,
13981
13774
  cacheWrite: 0.5,
@@ -13993,7 +13786,7 @@ export const MODELS = {
13993
13786
  input: ["text", "image"],
13994
13787
  cost: {
13995
13788
  input: 0.6,
13996
- output: 3.5999999999999996,
13789
+ output: 3.6,
13997
13790
  cacheRead: 0,
13998
13791
  cacheWrite: 0,
13999
13792
  },
@@ -14011,7 +13804,7 @@ export const MODELS = {
14011
13804
  cost: {
14012
13805
  input: 0.5,
14013
13806
  output: 3,
14014
- cacheRead: 0.09999999999999999,
13807
+ cacheRead: 0.1,
14015
13808
  cacheWrite: 0.625,
14016
13809
  },
14017
13810
  contextWindow: 1000000,
@@ -14043,8 +13836,8 @@ export const MODELS = {
14043
13836
  reasoning: true,
14044
13837
  input: ["text", "image"],
14045
13838
  cost: {
14046
- input: 0.39999999999999997,
14047
- output: 1.5999999999999999,
13839
+ input: 0.4,
13840
+ output: 1.6,
14048
13841
  cacheRead: 0.08,
14049
13842
  cacheWrite: 0.5,
14050
13843
  },
@@ -14077,7 +13870,7 @@ export const MODELS = {
14077
13870
  reasoning: false,
14078
13871
  input: ["text", "image"],
14079
13872
  cost: {
14080
- input: 0.7999999999999999,
13873
+ input: 0.8,
14081
13874
  output: 4,
14082
13875
  cacheRead: 0.08,
14083
13876
  cacheWrite: 1,
@@ -14085,25 +13878,6 @@ export const MODELS = {
14085
13878
  contextWindow: 200000,
14086
13879
  maxTokens: 8192,
14087
13880
  },
14088
- "anthropic/claude-fable-5": {
14089
- id: "anthropic/claude-fable-5",
14090
- name: "Claude Fable 5",
14091
- api: "anthropic-messages",
14092
- provider: "vercel-ai-gateway",
14093
- baseUrl: "https://ai-gateway.vercel.sh",
14094
- compat: { "forceAdaptiveThinking": true },
14095
- reasoning: true,
14096
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
14097
- input: ["text", "image"],
14098
- cost: {
14099
- input: 10,
14100
- output: 50,
14101
- cacheRead: 1,
14102
- cacheWrite: 12.5,
14103
- },
14104
- contextWindow: 1000000,
14105
- maxTokens: 128000,
14106
- },
14107
13881
  "anthropic/claude-haiku-4.5": {
14108
13882
  id: "anthropic/claude-haiku-4.5",
14109
13883
  name: "Claude Haiku 4.5",
@@ -14115,7 +13889,7 @@ export const MODELS = {
14115
13889
  cost: {
14116
13890
  input: 1,
14117
13891
  output: 5,
14118
- cacheRead: 0.09999999999999999,
13892
+ cacheRead: 0.1,
14119
13893
  cacheWrite: 1.25,
14120
13894
  },
14121
13895
  contextWindow: 200000,
@@ -14308,7 +14082,7 @@ export const MODELS = {
14308
14082
  input: ["text"],
14309
14083
  cost: {
14310
14084
  input: 0.25,
14311
- output: 0.8999999999999999,
14085
+ output: 0.9,
14312
14086
  cacheRead: 0,
14313
14087
  cacheWrite: 0,
14314
14088
  },
@@ -14326,7 +14100,7 @@ export const MODELS = {
14326
14100
  cost: {
14327
14101
  input: 0.25,
14328
14102
  output: 2,
14329
- cacheRead: 0.049999999999999996,
14103
+ cacheRead: 0.05,
14330
14104
  cacheWrite: 0,
14331
14105
  },
14332
14106
  contextWindow: 256000,
@@ -14511,8 +14285,8 @@ export const MODELS = {
14511
14285
  reasoning: true,
14512
14286
  input: ["text", "image"],
14513
14287
  cost: {
14514
- input: 0.09999999999999999,
14515
- output: 0.39999999999999997,
14288
+ input: 0.1,
14289
+ output: 0.4,
14516
14290
  cacheRead: 0.01,
14517
14291
  cacheWrite: 0,
14518
14292
  },
@@ -14547,7 +14321,7 @@ export const MODELS = {
14547
14321
  cost: {
14548
14322
  input: 0.5,
14549
14323
  output: 3,
14550
- cacheRead: 0.049999999999999996,
14324
+ cacheRead: 0.05,
14551
14325
  cacheWrite: 0,
14552
14326
  },
14553
14327
  contextWindow: 1000000,
@@ -14564,7 +14338,7 @@ export const MODELS = {
14564
14338
  cost: {
14565
14339
  input: 2,
14566
14340
  output: 12,
14567
- cacheRead: 0.19999999999999998,
14341
+ cacheRead: 0.2,
14568
14342
  cacheWrite: 0,
14569
14343
  },
14570
14344
  contextWindow: 1000000,
@@ -14615,7 +14389,7 @@ export const MODELS = {
14615
14389
  cost: {
14616
14390
  input: 2,
14617
14391
  output: 12,
14618
- cacheRead: 0.19999999999999998,
14392
+ cacheRead: 0.2,
14619
14393
  cacheWrite: 0,
14620
14394
  },
14621
14395
  contextWindow: 1000000,
@@ -14665,7 +14439,7 @@ export const MODELS = {
14665
14439
  input: ["text", "image"],
14666
14440
  cost: {
14667
14441
  input: 0.14,
14668
- output: 0.39999999999999997,
14442
+ output: 0.4,
14669
14443
  cacheRead: 0,
14670
14444
  cacheWrite: 0,
14671
14445
  },
@@ -14683,7 +14457,7 @@ export const MODELS = {
14683
14457
  cost: {
14684
14458
  input: 0.25,
14685
14459
  output: 0.75,
14686
- cacheRead: 0.024999999999999998,
14460
+ cacheRead: 0.025,
14687
14461
  cacheWrite: 0,
14688
14462
  },
14689
14463
  contextWindow: 128000,
@@ -14835,7 +14609,7 @@ export const MODELS = {
14835
14609
  input: ["text", "image"],
14836
14610
  cost: {
14837
14611
  input: 0.24,
14838
- output: 0.9700000000000001,
14612
+ output: 0.97,
14839
14613
  cacheRead: 0,
14840
14614
  cacheWrite: 0,
14841
14615
  },
@@ -14851,7 +14625,7 @@ export const MODELS = {
14851
14625
  reasoning: false,
14852
14626
  input: ["text", "image"],
14853
14627
  cost: {
14854
- input: 0.16999999999999998,
14628
+ input: 0.17,
14855
14629
  output: 0.66,
14856
14630
  cacheRead: 0,
14857
14631
  cacheWrite: 0,
@@ -15005,7 +14779,7 @@ export const MODELS = {
15005
14779
  input: ["text"],
15006
14780
  cost: {
15007
14781
  input: 0.3,
15008
- output: 0.8999999999999999,
14782
+ output: 0.9,
15009
14783
  cacheRead: 0,
15010
14784
  cacheWrite: 0,
15011
14785
  },
@@ -15021,7 +14795,7 @@ export const MODELS = {
15021
14795
  reasoning: false,
15022
14796
  input: ["text"],
15023
14797
  cost: {
15024
- input: 0.39999999999999997,
14798
+ input: 0.4,
15025
14799
  output: 2,
15026
14800
  cacheRead: 0,
15027
14801
  cacheWrite: 0,
@@ -15038,7 +14812,7 @@ export const MODELS = {
15038
14812
  reasoning: false,
15039
14813
  input: ["text"],
15040
14814
  cost: {
15041
- input: 0.09999999999999999,
14815
+ input: 0.1,
15042
14816
  output: 0.3,
15043
14817
  cacheRead: 0,
15044
14818
  cacheWrite: 0,
@@ -15055,7 +14829,7 @@ export const MODELS = {
15055
14829
  reasoning: false,
15056
14830
  input: ["text"],
15057
14831
  cost: {
15058
- input: 0.09999999999999999,
14832
+ input: 0.1,
15059
14833
  output: 0.3,
15060
14834
  cacheRead: 0,
15061
14835
  cacheWrite: 0,
@@ -15072,8 +14846,8 @@ export const MODELS = {
15072
14846
  reasoning: false,
15073
14847
  input: ["text"],
15074
14848
  cost: {
15075
- input: 0.09999999999999999,
15076
- output: 0.09999999999999999,
14849
+ input: 0.1,
14850
+ output: 0.1,
15077
14851
  cacheRead: 0,
15078
14852
  cacheWrite: 0,
15079
14853
  },
@@ -15106,7 +14880,7 @@ export const MODELS = {
15106
14880
  reasoning: false,
15107
14881
  input: ["text", "image"],
15108
14882
  cost: {
15109
- input: 0.39999999999999997,
14883
+ input: 0.4,
15110
14884
  output: 2,
15111
14885
  cacheRead: 0,
15112
14886
  cacheWrite: 0,
@@ -15157,7 +14931,7 @@ export const MODELS = {
15157
14931
  reasoning: false,
15158
14932
  input: ["text", "image"],
15159
14933
  cost: {
15160
- input: 0.09999999999999999,
14934
+ input: 0.1,
15161
14935
  output: 0.3,
15162
14936
  cacheRead: 0,
15163
14937
  cacheWrite: 0,
@@ -15208,7 +14982,7 @@ export const MODELS = {
15208
14982
  reasoning: false,
15209
14983
  input: ["text"],
15210
14984
  cost: {
15211
- input: 0.5700000000000001,
14985
+ input: 0.57,
15212
14986
  output: 2.3,
15213
14987
  cacheRead: 0,
15214
14988
  cacheWrite: 0,
@@ -15233,40 +15007,6 @@ export const MODELS = {
15233
15007
  contextWindow: 262114,
15234
15008
  maxTokens: 262114,
15235
15009
  },
15236
- "moonshotai/kimi-k2-thinking-turbo": {
15237
- id: "moonshotai/kimi-k2-thinking-turbo",
15238
- name: "Kimi K2 Thinking Turbo",
15239
- api: "anthropic-messages",
15240
- provider: "vercel-ai-gateway",
15241
- baseUrl: "https://ai-gateway.vercel.sh",
15242
- reasoning: true,
15243
- input: ["text"],
15244
- cost: {
15245
- input: 1.15,
15246
- output: 8,
15247
- cacheRead: 0.15,
15248
- cacheWrite: 0,
15249
- },
15250
- contextWindow: 262114,
15251
- maxTokens: 262114,
15252
- },
15253
- "moonshotai/kimi-k2-turbo": {
15254
- id: "moonshotai/kimi-k2-turbo",
15255
- name: "Kimi K2 Turbo",
15256
- api: "anthropic-messages",
15257
- provider: "vercel-ai-gateway",
15258
- baseUrl: "https://ai-gateway.vercel.sh",
15259
- reasoning: false,
15260
- input: ["text"],
15261
- cost: {
15262
- input: 1.15,
15263
- output: 8,
15264
- cacheRead: 0.15,
15265
- cacheWrite: 0,
15266
- },
15267
- contextWindow: 256000,
15268
- maxTokens: 16384,
15269
- },
15270
15010
  "moonshotai/kimi-k2.5": {
15271
15011
  id: "moonshotai/kimi-k2.5",
15272
15012
  name: "Kimi K2.5",
@@ -15278,7 +15018,7 @@ export const MODELS = {
15278
15018
  cost: {
15279
15019
  input: 0.6,
15280
15020
  output: 3,
15281
- cacheRead: 0.09999999999999999,
15021
+ cacheRead: 0.1,
15282
15022
  cacheWrite: 0,
15283
15023
  },
15284
15024
  contextWindow: 262114,
@@ -15301,6 +15041,23 @@ export const MODELS = {
15301
15041
  contextWindow: 262000,
15302
15042
  maxTokens: 262000,
15303
15043
  },
15044
+ "moonshotai/kimi-k2.7-code": {
15045
+ id: "moonshotai/kimi-k2.7-code",
15046
+ name: "Kimi K2.7 Code",
15047
+ api: "anthropic-messages",
15048
+ provider: "vercel-ai-gateway",
15049
+ baseUrl: "https://ai-gateway.vercel.sh",
15050
+ reasoning: true,
15051
+ input: ["text", "image"],
15052
+ cost: {
15053
+ input: 0.95,
15054
+ output: 4,
15055
+ cacheRead: 0.19,
15056
+ cacheWrite: 0,
15057
+ },
15058
+ contextWindow: 256000,
15059
+ maxTokens: 32768,
15060
+ },
15304
15061
  "nvidia/nemotron-3-super-120b-a12b": {
15305
15062
  id: "nvidia/nemotron-3-super-120b-a12b",
15306
15063
  name: "NVIDIA Nemotron 3 Super 120B A12B",
@@ -15344,7 +15101,7 @@ export const MODELS = {
15344
15101
  reasoning: true,
15345
15102
  input: ["text", "image"],
15346
15103
  cost: {
15347
- input: 0.19999999999999998,
15104
+ input: 0.2,
15348
15105
  output: 0.6,
15349
15106
  cacheRead: 0,
15350
15107
  cacheWrite: 0,
@@ -15362,7 +15119,7 @@ export const MODELS = {
15362
15119
  input: ["text"],
15363
15120
  cost: {
15364
15121
  input: 0.06,
15365
- output: 0.22999999999999998,
15122
+ output: 0.23,
15366
15123
  cacheRead: 0,
15367
15124
  cacheWrite: 0,
15368
15125
  },
@@ -15412,9 +15169,9 @@ export const MODELS = {
15412
15169
  reasoning: false,
15413
15170
  input: ["text", "image"],
15414
15171
  cost: {
15415
- input: 0.39999999999999997,
15416
- output: 1.5999999999999999,
15417
- cacheRead: 0.09999999999999999,
15172
+ input: 0.4,
15173
+ output: 1.6,
15174
+ cacheRead: 0.1,
15418
15175
  cacheWrite: 0,
15419
15176
  },
15420
15177
  contextWindow: 1047576,
@@ -15429,9 +15186,9 @@ export const MODELS = {
15429
15186
  reasoning: false,
15430
15187
  input: ["text", "image"],
15431
15188
  cost: {
15432
- input: 0.09999999999999999,
15433
- output: 0.39999999999999997,
15434
- cacheRead: 0.024999999999999998,
15189
+ input: 0.1,
15190
+ output: 0.4,
15191
+ cacheRead: 0.025,
15435
15192
  cacheWrite: 0,
15436
15193
  },
15437
15194
  contextWindow: 1047576,
@@ -15533,7 +15290,7 @@ export const MODELS = {
15533
15290
  cost: {
15534
15291
  input: 0.25,
15535
15292
  output: 2,
15536
- cacheRead: 0.024999999999999998,
15293
+ cacheRead: 0.025,
15537
15294
  cacheWrite: 0,
15538
15295
  },
15539
15296
  contextWindow: 400000,
@@ -15548,8 +15305,8 @@ export const MODELS = {
15548
15305
  reasoning: true,
15549
15306
  input: ["text", "image"],
15550
15307
  cost: {
15551
- input: 0.049999999999999996,
15552
- output: 0.39999999999999997,
15308
+ input: 0.05,
15309
+ output: 0.4,
15553
15310
  cacheRead: 0.005,
15554
15311
  cacheWrite: 0,
15555
15312
  },
@@ -15618,7 +15375,7 @@ export const MODELS = {
15618
15375
  cost: {
15619
15376
  input: 0.25,
15620
15377
  output: 2,
15621
- cacheRead: 0.024999999999999998,
15378
+ cacheRead: 0.025,
15622
15379
  cacheWrite: 0,
15623
15380
  },
15624
15381
  contextWindow: 400000,
@@ -15812,7 +15569,7 @@ export const MODELS = {
15812
15569
  thinkingLevelMap: { "xhigh": "xhigh" },
15813
15570
  input: ["text", "image"],
15814
15571
  cost: {
15815
- input: 0.19999999999999998,
15572
+ input: 0.2,
15816
15573
  output: 1.25,
15817
15574
  cacheRead: 0.02,
15818
15575
  cacheWrite: 0,
@@ -15900,8 +15657,8 @@ export const MODELS = {
15900
15657
  reasoning: true,
15901
15658
  input: ["text"],
15902
15659
  cost: {
15903
- input: 0.049999999999999996,
15904
- output: 0.19999999999999998,
15660
+ input: 0.05,
15661
+ output: 0.2,
15905
15662
  cacheRead: 0,
15906
15663
  cacheWrite: 0,
15907
15664
  },
@@ -16087,7 +15844,7 @@ export const MODELS = {
16087
15844
  reasoning: true,
16088
15845
  input: ["text", "image"],
16089
15846
  cost: {
16090
- input: 0.19999999999999998,
15847
+ input: 0.2,
16091
15848
  output: 1.15,
16092
15849
  cacheRead: 0.04,
16093
15850
  cacheWrite: 0,
@@ -16104,9 +15861,9 @@ export const MODELS = {
16104
15861
  reasoning: false,
16105
15862
  input: ["text", "image"],
16106
15863
  cost: {
16107
- input: 0.19999999999999998,
15864
+ input: 0.2,
16108
15865
  output: 0.5,
16109
- cacheRead: 0.049999999999999996,
15866
+ cacheRead: 0.05,
16110
15867
  cacheWrite: 0,
16111
15868
  },
16112
15869
  contextWindow: 1000000,
@@ -16121,9 +15878,9 @@ export const MODELS = {
16121
15878
  reasoning: true,
16122
15879
  input: ["text", "image"],
16123
15880
  cost: {
16124
- input: 0.19999999999999998,
15881
+ input: 0.2,
16125
15882
  output: 0.5,
16126
- cacheRead: 0.049999999999999996,
15883
+ cacheRead: 0.05,
16127
15884
  cacheWrite: 0,
16128
15885
  },
16129
15886
  contextWindow: 1000000,
@@ -16140,7 +15897,7 @@ export const MODELS = {
16140
15897
  cost: {
16141
15898
  input: 1.25,
16142
15899
  output: 2.5,
16143
- cacheRead: 0.19999999999999998,
15900
+ cacheRead: 0.2,
16144
15901
  cacheWrite: 0,
16145
15902
  },
16146
15903
  contextWindow: 2000000,
@@ -16157,7 +15914,7 @@ export const MODELS = {
16157
15914
  cost: {
16158
15915
  input: 1.25,
16159
15916
  output: 2.5,
16160
- cacheRead: 0.19999999999999998,
15917
+ cacheRead: 0.2,
16161
15918
  cacheWrite: 0,
16162
15919
  },
16163
15920
  contextWindow: 2000000,
@@ -16174,7 +15931,7 @@ export const MODELS = {
16174
15931
  cost: {
16175
15932
  input: 1.25,
16176
15933
  output: 2.5,
16177
- cacheRead: 0.19999999999999998,
15934
+ cacheRead: 0.2,
16178
15935
  cacheWrite: 0,
16179
15936
  },
16180
15937
  contextWindow: 2000000,
@@ -16191,7 +15948,7 @@ export const MODELS = {
16191
15948
  cost: {
16192
15949
  input: 1.25,
16193
15950
  output: 2.5,
16194
- cacheRead: 0.19999999999999998,
15951
+ cacheRead: 0.2,
16195
15952
  cacheWrite: 0,
16196
15953
  },
16197
15954
  contextWindow: 2000000,
@@ -16208,7 +15965,7 @@ export const MODELS = {
16208
15965
  cost: {
16209
15966
  input: 1.25,
16210
15967
  output: 2.5,
16211
- cacheRead: 0.19999999999999998,
15968
+ cacheRead: 0.2,
16212
15969
  cacheWrite: 0,
16213
15970
  },
16214
15971
  contextWindow: 2000000,
@@ -16225,7 +15982,7 @@ export const MODELS = {
16225
15982
  cost: {
16226
15983
  input: 1.25,
16227
15984
  output: 2.5,
16228
- cacheRead: 0.19999999999999998,
15985
+ cacheRead: 0.2,
16229
15986
  cacheWrite: 0,
16230
15987
  },
16231
15988
  contextWindow: 2000000,
@@ -16242,7 +15999,7 @@ export const MODELS = {
16242
15999
  cost: {
16243
16000
  input: 1.25,
16244
16001
  output: 2.5,
16245
- cacheRead: 0.19999999999999998,
16002
+ cacheRead: 0.2,
16246
16003
  cacheWrite: 0,
16247
16004
  },
16248
16005
  contextWindow: 1000000,
@@ -16259,7 +16016,7 @@ export const MODELS = {
16259
16016
  cost: {
16260
16017
  input: 1,
16261
16018
  output: 2,
16262
- cacheRead: 0.19999999999999998,
16019
+ cacheRead: 0.2,
16263
16020
  cacheWrite: 0,
16264
16021
  },
16265
16022
  contextWindow: 256000,
@@ -16274,7 +16031,7 @@ export const MODELS = {
16274
16031
  reasoning: true,
16275
16032
  input: ["text"],
16276
16033
  cost: {
16277
- input: 0.09999999999999999,
16034
+ input: 0.1,
16278
16035
  output: 0.3,
16279
16036
  cacheRead: 0.01,
16280
16037
  cacheWrite: 0,
@@ -16293,7 +16050,7 @@ export const MODELS = {
16293
16050
  cost: {
16294
16051
  input: 1,
16295
16052
  output: 3,
16296
- cacheRead: 0.19999999999999998,
16053
+ cacheRead: 0.2,
16297
16054
  cacheWrite: 0,
16298
16055
  },
16299
16056
  contextWindow: 1000000,
@@ -16359,7 +16116,7 @@ export const MODELS = {
16359
16116
  reasoning: true,
16360
16117
  input: ["text"],
16361
16118
  cost: {
16362
- input: 0.19999999999999998,
16119
+ input: 0.2,
16363
16120
  output: 1.1,
16364
16121
  cacheRead: 0.03,
16365
16122
  cacheWrite: 0,
@@ -16377,7 +16134,7 @@ export const MODELS = {
16377
16134
  input: ["text", "image"],
16378
16135
  cost: {
16379
16136
  input: 0.6,
16380
- output: 1.7999999999999998,
16137
+ output: 1.8,
16381
16138
  cacheRead: 0.11,
16382
16139
  cacheWrite: 0,
16383
16140
  },
@@ -16411,8 +16168,8 @@ export const MODELS = {
16411
16168
  input: ["text", "image"],
16412
16169
  cost: {
16413
16170
  input: 0.3,
16414
- output: 0.8999999999999999,
16415
- cacheRead: 0.049999999999999996,
16171
+ output: 0.9,
16172
+ cacheRead: 0.05,
16416
16173
  cacheWrite: 0,
16417
16174
  },
16418
16175
  contextWindow: 128000,
@@ -16462,7 +16219,7 @@ export const MODELS = {
16462
16219
  input: ["text"],
16463
16220
  cost: {
16464
16221
  input: 0.07,
16465
- output: 0.39999999999999997,
16222
+ output: 0.4,
16466
16223
  cacheRead: 0,
16467
16224
  cacheWrite: 0,
16468
16225
  },
@@ -16479,7 +16236,7 @@ export const MODELS = {
16479
16236
  input: ["text"],
16480
16237
  cost: {
16481
16238
  input: 0.06,
16482
- output: 0.39999999999999997,
16239
+ output: 0.4,
16483
16240
  cacheRead: 0.01,
16484
16241
  cacheWrite: 0,
16485
16242
  },
@@ -16496,8 +16253,8 @@ export const MODELS = {
16496
16253
  input: ["text"],
16497
16254
  cost: {
16498
16255
  input: 1,
16499
- output: 3.1999999999999997,
16500
- cacheRead: 0.19999999999999998,
16256
+ output: 3.2,
16257
+ cacheRead: 0.2,
16501
16258
  cacheWrite: 0,
16502
16259
  },
16503
16260
  contextWindow: 202800,
@@ -17135,6 +16892,24 @@ export const MODELS = {
17135
16892
  contextWindow: 200000,
17136
16893
  maxTokens: 131072,
17137
16894
  },
16895
+ "glm-5.2": {
16896
+ id: "glm-5.2",
16897
+ name: "GLM-5.2",
16898
+ api: "openai-completions",
16899
+ provider: "zai",
16900
+ baseUrl: "https://api.z.ai/api/coding/paas/v4",
16901
+ compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
16902
+ reasoning: true,
16903
+ input: ["text"],
16904
+ cost: {
16905
+ input: 0,
16906
+ output: 0,
16907
+ cacheRead: 0,
16908
+ cacheWrite: 0,
16909
+ },
16910
+ contextWindow: 1000000,
16911
+ maxTokens: 131072,
16912
+ },
17138
16913
  "glm-5v-turbo": {
17139
16914
  id: "glm-5v-turbo",
17140
16915
  name: "GLM-5V-Turbo",
@@ -17227,6 +17002,24 @@ export const MODELS = {
17227
17002
  contextWindow: 200000,
17228
17003
  maxTokens: 131072,
17229
17004
  },
17005
+ "glm-5.2": {
17006
+ id: "glm-5.2",
17007
+ name: "GLM-5.2",
17008
+ api: "openai-completions",
17009
+ provider: "zai-coding-cn",
17010
+ baseUrl: "https://open.bigmodel.cn/api/coding/paas/v4",
17011
+ compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
17012
+ reasoning: true,
17013
+ input: ["text"],
17014
+ cost: {
17015
+ input: 0,
17016
+ output: 0,
17017
+ cacheRead: 0,
17018
+ cacheWrite: 0,
17019
+ },
17020
+ contextWindow: 1000000,
17021
+ maxTokens: 131072,
17022
+ },
17230
17023
  "glm-5v-turbo": {
17231
17024
  id: "glm-5v-turbo",
17232
17025
  name: "GLM-5V-Turbo",