gsd-pi 2.72.0-dev.3159350 → 2.72.0-dev.4f3264a

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 (189) hide show
  1. package/dist/resources/extensions/async-jobs/await-tool.js +4 -7
  2. package/dist/resources/extensions/async-jobs/job-manager.js +3 -28
  3. package/dist/resources/extensions/claude-code-cli/stream-adapter.js +26 -27
  4. package/dist/resources/extensions/gsd/auto/loop.js +1 -84
  5. package/dist/resources/extensions/gsd/auto-observability.js +54 -0
  6. package/dist/resources/extensions/gsd/auto-post-unit.js +0 -6
  7. package/dist/resources/extensions/gsd/auto.js +19 -25
  8. package/dist/resources/extensions/gsd/bootstrap/register-hooks.js +11 -9
  9. package/dist/resources/extensions/gsd/commands-handlers.js +1 -4
  10. package/dist/resources/extensions/gsd/context-injector.js +1 -1
  11. package/dist/resources/extensions/gsd/custom-workflow-engine.js +7 -3
  12. package/dist/resources/extensions/gsd/file-watcher.js +80 -0
  13. package/dist/resources/extensions/gsd/gsd-db.js +5 -47
  14. package/dist/resources/extensions/gsd/key-manager.js +0 -2
  15. package/dist/resources/extensions/gsd/preferences-skills.js +34 -2
  16. package/dist/resources/extensions/gsd/preferences-types.js +0 -15
  17. package/dist/resources/extensions/gsd/preferences.js +3 -16
  18. package/dist/resources/extensions/gsd/prompt-loader.js +1 -4
  19. package/dist/resources/extensions/gsd/rtk-status.js +43 -0
  20. package/dist/resources/extensions/gsd/state.js +1 -21
  21. package/dist/resources/extensions/gsd/write-intercept.js +1 -10
  22. package/dist/resources/extensions/ollama/index.js +5 -4
  23. package/dist/resources/extensions/ollama/ollama-client.js +6 -35
  24. package/dist/resources/extensions/ollama/ollama-discovery.js +6 -32
  25. package/dist/web/standalone/.next/BUILD_ID +1 -1
  26. package/dist/web/standalone/.next/app-path-routes-manifest.json +11 -11
  27. package/dist/web/standalone/.next/build-manifest.json +2 -2
  28. package/dist/web/standalone/.next/prerender-manifest.json +3 -3
  29. package/dist/web/standalone/.next/server/app/_global-error/page.js +3 -3
  30. package/dist/web/standalone/.next/server/app/_global-error/page_client-reference-manifest.js +1 -1
  31. package/dist/web/standalone/.next/server/app/_global-error.html +1 -1
  32. package/dist/web/standalone/.next/server/app/_global-error.rsc +1 -1
  33. package/dist/web/standalone/.next/server/app/_global-error.segments/_full.segment.rsc +1 -1
  34. package/dist/web/standalone/.next/server/app/_global-error.segments/_global-error/__PAGE__.segment.rsc +1 -1
  35. package/dist/web/standalone/.next/server/app/_global-error.segments/_global-error.segment.rsc +1 -1
  36. package/dist/web/standalone/.next/server/app/_global-error.segments/_head.segment.rsc +1 -1
  37. package/dist/web/standalone/.next/server/app/_global-error.segments/_index.segment.rsc +1 -1
  38. package/dist/web/standalone/.next/server/app/_global-error.segments/_tree.segment.rsc +1 -1
  39. package/dist/web/standalone/.next/server/app/_not-found/page.js +2 -2
  40. package/dist/web/standalone/.next/server/app/_not-found/page_client-reference-manifest.js +1 -1
  41. package/dist/web/standalone/.next/server/app/_not-found.html +1 -1
  42. package/dist/web/standalone/.next/server/app/_not-found.rsc +1 -1
  43. package/dist/web/standalone/.next/server/app/_not-found.segments/_full.segment.rsc +1 -1
  44. package/dist/web/standalone/.next/server/app/_not-found.segments/_head.segment.rsc +1 -1
  45. package/dist/web/standalone/.next/server/app/_not-found.segments/_index.segment.rsc +1 -1
  46. package/dist/web/standalone/.next/server/app/_not-found.segments/_not-found/__PAGE__.segment.rsc +1 -1
  47. package/dist/web/standalone/.next/server/app/_not-found.segments/_not-found.segment.rsc +1 -1
  48. package/dist/web/standalone/.next/server/app/_not-found.segments/_tree.segment.rsc +1 -1
  49. package/dist/web/standalone/.next/server/app/api/boot/route.js +1 -1
  50. package/dist/web/standalone/.next/server/app/api/bridge-terminal/input/route.js +1 -1
  51. package/dist/web/standalone/.next/server/app/api/bridge-terminal/resize/route.js +1 -1
  52. package/dist/web/standalone/.next/server/app/api/bridge-terminal/stream/route.js +2 -2
  53. package/dist/web/standalone/.next/server/app/api/browse-directories/route.js +1 -1
  54. package/dist/web/standalone/.next/server/app/api/captures/route.js +1 -1
  55. package/dist/web/standalone/.next/server/app/api/cleanup/route.js +1 -1
  56. package/dist/web/standalone/.next/server/app/api/dev-mode/route.js +1 -1
  57. package/dist/web/standalone/.next/server/app/api/doctor/route.js +1 -1
  58. package/dist/web/standalone/.next/server/app/api/experimental/route.js +2 -2
  59. package/dist/web/standalone/.next/server/app/api/export-data/route.js +1 -1
  60. package/dist/web/standalone/.next/server/app/api/files/route.js +1 -1
  61. package/dist/web/standalone/.next/server/app/api/forensics/route.js +1 -1
  62. package/dist/web/standalone/.next/server/app/api/git/route.js +1 -1
  63. package/dist/web/standalone/.next/server/app/api/history/route.js +1 -1
  64. package/dist/web/standalone/.next/server/app/api/hooks/route.js +1 -1
  65. package/dist/web/standalone/.next/server/app/api/inspect/route.js +1 -1
  66. package/dist/web/standalone/.next/server/app/api/knowledge/route.js +1 -1
  67. package/dist/web/standalone/.next/server/app/api/live-state/route.js +1 -1
  68. package/dist/web/standalone/.next/server/app/api/notifications/route.js +2 -2
  69. package/dist/web/standalone/.next/server/app/api/onboarding/route.js +1 -1
  70. package/dist/web/standalone/.next/server/app/api/preferences/route.js +1 -1
  71. package/dist/web/standalone/.next/server/app/api/projects/route.js +1 -1
  72. package/dist/web/standalone/.next/server/app/api/recovery/route.js +1 -1
  73. package/dist/web/standalone/.next/server/app/api/remote-questions/route.js +2 -2
  74. package/dist/web/standalone/.next/server/app/api/session/browser/route.js +1 -1
  75. package/dist/web/standalone/.next/server/app/api/session/command/route.js +1 -1
  76. package/dist/web/standalone/.next/server/app/api/session/events/route.js +2 -2
  77. package/dist/web/standalone/.next/server/app/api/session/manage/route.js +1 -1
  78. package/dist/web/standalone/.next/server/app/api/settings-data/route.js +1 -1
  79. package/dist/web/standalone/.next/server/app/api/shutdown/route.js +1 -1
  80. package/dist/web/standalone/.next/server/app/api/skill-health/route.js +1 -1
  81. package/dist/web/standalone/.next/server/app/api/steer/route.js +1 -1
  82. package/dist/web/standalone/.next/server/app/api/switch-root/route.js +1 -1
  83. package/dist/web/standalone/.next/server/app/api/terminal/input/route.js +2 -2
  84. package/dist/web/standalone/.next/server/app/api/terminal/resize/route.js +2 -2
  85. package/dist/web/standalone/.next/server/app/api/terminal/sessions/route.js +2 -2
  86. package/dist/web/standalone/.next/server/app/api/terminal/stream/route.js +3 -3
  87. package/dist/web/standalone/.next/server/app/api/terminal/upload/route.js +1 -1
  88. package/dist/web/standalone/.next/server/app/api/undo/route.js +1 -1
  89. package/dist/web/standalone/.next/server/app/api/update/route.js +1 -1
  90. package/dist/web/standalone/.next/server/app/api/visualizer/route.js +1 -1
  91. package/dist/web/standalone/.next/server/app/index.html +1 -1
  92. package/dist/web/standalone/.next/server/app/index.rsc +1 -1
  93. package/dist/web/standalone/.next/server/app/index.segments/__PAGE__.segment.rsc +1 -1
  94. package/dist/web/standalone/.next/server/app/index.segments/_full.segment.rsc +1 -1
  95. package/dist/web/standalone/.next/server/app/index.segments/_head.segment.rsc +1 -1
  96. package/dist/web/standalone/.next/server/app/index.segments/_index.segment.rsc +1 -1
  97. package/dist/web/standalone/.next/server/app/index.segments/_tree.segment.rsc +1 -1
  98. package/dist/web/standalone/.next/server/app/page.js +2 -2
  99. package/dist/web/standalone/.next/server/app/page_client-reference-manifest.js +1 -1
  100. package/dist/web/standalone/.next/server/app-paths-manifest.json +11 -11
  101. package/dist/web/standalone/.next/server/chunks/2331.js +16 -16
  102. package/dist/web/standalone/.next/server/chunks/4741.js +12 -12
  103. package/dist/web/standalone/.next/server/chunks/5822.js +2 -2
  104. package/dist/web/standalone/.next/server/chunks/63.js +8 -8
  105. package/dist/web/standalone/.next/server/chunks/6897.js +3 -3
  106. package/dist/web/standalone/.next/server/functions-config-manifest.json +9 -0
  107. package/dist/web/standalone/.next/server/middleware-build-manifest.js +1 -1
  108. package/dist/web/standalone/.next/server/middleware-manifest.json +2 -29
  109. package/dist/web/standalone/.next/server/middleware.js +12 -4
  110. package/dist/web/standalone/.next/server/pages/404.html +1 -1
  111. package/dist/web/standalone/.next/server/pages/500.html +1 -1
  112. package/dist/web/standalone/.next/server/server-reference-manifest.json +1 -1
  113. package/dist/web/standalone/.next/server/webpack-runtime.js +1 -1
  114. package/package.json +1 -1
  115. package/packages/pi-ai/dist/env-api-keys.js +0 -1
  116. package/packages/pi-ai/dist/env-api-keys.js.map +1 -1
  117. package/packages/pi-ai/dist/models.custom.d.ts +0 -105
  118. package/packages/pi-ai/dist/models.custom.d.ts.map +1 -1
  119. package/packages/pi-ai/dist/models.custom.js +0 -97
  120. package/packages/pi-ai/dist/models.custom.js.map +1 -1
  121. package/packages/pi-ai/dist/models.generated.d.ts +140 -648
  122. package/packages/pi-ai/dist/models.generated.d.ts.map +1 -1
  123. package/packages/pi-ai/dist/models.generated.js +364 -861
  124. package/packages/pi-ai/dist/models.generated.js.map +1 -1
  125. package/packages/pi-ai/dist/models.test.js +0 -105
  126. package/packages/pi-ai/dist/models.test.js.map +1 -1
  127. package/packages/pi-ai/dist/types.d.ts +1 -1
  128. package/packages/pi-ai/dist/types.d.ts.map +1 -1
  129. package/packages/pi-ai/dist/types.js.map +1 -1
  130. package/packages/pi-ai/src/env-api-keys.ts +0 -1
  131. package/packages/pi-ai/src/models.custom.ts +0 -98
  132. package/packages/pi-ai/src/models.generated.ts +364 -861
  133. package/packages/pi-ai/src/models.test.ts +0 -135
  134. package/packages/pi-ai/src/types.ts +0 -1
  135. package/packages/pi-coding-agent/dist/core/model-resolver.d.ts.map +1 -1
  136. package/packages/pi-coding-agent/dist/core/model-resolver.js +0 -1
  137. package/packages/pi-coding-agent/dist/core/model-resolver.js.map +1 -1
  138. package/packages/pi-coding-agent/src/core/model-resolver.ts +0 -1
  139. package/src/resources/extensions/async-jobs/await-tool.test.ts +7 -40
  140. package/src/resources/extensions/async-jobs/await-tool.ts +4 -7
  141. package/src/resources/extensions/async-jobs/job-manager.ts +3 -33
  142. package/src/resources/extensions/claude-code-cli/stream-adapter.ts +26 -27
  143. package/src/resources/extensions/claude-code-cli/tests/stream-adapter.test.ts +2 -20
  144. package/src/resources/extensions/gsd/auto/loop.ts +1 -89
  145. package/src/resources/extensions/gsd/auto-observability.ts +72 -0
  146. package/src/resources/extensions/gsd/auto-post-unit.ts +0 -7
  147. package/src/resources/extensions/gsd/auto.ts +20 -25
  148. package/src/resources/extensions/gsd/bootstrap/register-hooks.ts +10 -8
  149. package/src/resources/extensions/gsd/commands-handlers.ts +1 -5
  150. package/src/resources/extensions/gsd/context-injector.ts +1 -1
  151. package/src/resources/extensions/gsd/custom-workflow-engine.ts +8 -4
  152. package/src/resources/extensions/gsd/file-watcher.ts +100 -0
  153. package/src/resources/extensions/gsd/gsd-db.ts +5 -52
  154. package/src/resources/extensions/gsd/key-manager.ts +0 -2
  155. package/src/resources/extensions/gsd/preferences-skills.ts +36 -2
  156. package/src/resources/extensions/gsd/preferences-types.ts +0 -16
  157. package/src/resources/extensions/gsd/preferences.ts +6 -19
  158. package/src/resources/extensions/gsd/prompt-loader.ts +1 -6
  159. package/src/resources/extensions/gsd/rtk-status.ts +53 -0
  160. package/src/resources/extensions/gsd/state.ts +0 -20
  161. package/src/resources/extensions/gsd/tests/gsd-db.test.ts +0 -74
  162. package/src/resources/extensions/gsd/tests/key-manager.test.ts +0 -63
  163. package/src/resources/extensions/gsd/tests/preferences.test.ts +0 -53
  164. package/src/resources/extensions/gsd/write-intercept.ts +1 -10
  165. package/src/resources/extensions/ollama/index.ts +5 -4
  166. package/src/resources/extensions/ollama/ollama-client.ts +6 -35
  167. package/src/resources/extensions/ollama/ollama-discovery.ts +6 -37
  168. package/src/resources/extensions/ollama/tests/ollama-discovery.test.ts +0 -54
  169. package/dist/resources/extensions/gsd/definition-io.js +0 -15
  170. package/dist/web/standalone/.next/server/edge-runtime-webpack.js +0 -2
  171. package/packages/pi-ai/dist/models.generated.test.d.ts +0 -2
  172. package/packages/pi-ai/dist/models.generated.test.d.ts.map +0 -1
  173. package/packages/pi-ai/dist/models.generated.test.js +0 -334
  174. package/packages/pi-ai/dist/models.generated.test.js.map +0 -1
  175. package/packages/pi-ai/src/models.generated.test.ts +0 -373
  176. package/src/resources/extensions/gsd/definition-io.ts +0 -18
  177. package/src/resources/extensions/gsd/tests/auto-paused-ui-cleanup.test.ts +0 -27
  178. package/src/resources/extensions/gsd/tests/block-db-writes.test.ts +0 -63
  179. package/src/resources/extensions/gsd/tests/definition-io.test.ts +0 -57
  180. package/src/resources/extensions/gsd/tests/doctor-heal-fixable-warnings.test.ts +0 -14
  181. package/src/resources/extensions/gsd/tests/false-degraded-mode-warning.test.ts +0 -104
  182. package/src/resources/extensions/gsd/tests/memory-pressure-stuck-state.test.ts +0 -54
  183. package/src/resources/extensions/gsd/tests/post-unit-state-rebuild.test.ts +0 -34
  184. package/src/resources/extensions/gsd/tests/preferences-formatting.test.ts +0 -87
  185. package/src/resources/extensions/gsd/tests/prompt-loader-working-directory.test.ts +0 -19
  186. package/src/resources/extensions/gsd/tests/register-hooks-depth-verification.test.ts +0 -97
  187. package/src/resources/extensions/gsd/tests/stale-slice-rows.test.ts +0 -41
  188. /package/dist/web/standalone/.next/static/{eR2tLKungpmiiOyUIhqjF → vr6Pbde48w4rMUplqDdh_}/_buildManifest.js +0 -0
  189. /package/dist/web/standalone/.next/static/{eR2tLKungpmiiOyUIhqjF → vr6Pbde48w4rMUplqDdh_}/_ssgManifest.js +0 -0
@@ -801,23 +801,6 @@ export const MODELS = {
801
801
  contextWindow: 204800,
802
802
  maxTokens: 131072,
803
803
  },
804
- "minimax.minimax-m2.5": {
805
- id: "minimax.minimax-m2.5",
806
- name: "MiniMax M2.5",
807
- api: "bedrock-converse-stream",
808
- provider: "amazon-bedrock",
809
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
810
- reasoning: true,
811
- input: ["text"],
812
- cost: {
813
- input: 0.3,
814
- output: 1.2,
815
- cacheRead: 0,
816
- cacheWrite: 0,
817
- },
818
- contextWindow: 196608,
819
- maxTokens: 98304,
820
- },
821
804
  "mistral.devstral-2-123b": {
822
805
  id: "mistral.devstral-2-123b",
823
806
  name: "Devstral 2 123B",
@@ -1056,23 +1039,6 @@ export const MODELS = {
1056
1039
  contextWindow: 128000,
1057
1040
  maxTokens: 4096,
1058
1041
  },
1059
- "nvidia.nemotron-super-3-120b": {
1060
- id: "nvidia.nemotron-super-3-120b",
1061
- name: "NVIDIA Nemotron 3 Super 120B A12B",
1062
- api: "bedrock-converse-stream",
1063
- provider: "amazon-bedrock",
1064
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1065
- reasoning: true,
1066
- input: ["text"],
1067
- cost: {
1068
- input: 0.15,
1069
- output: 0.65,
1070
- cacheRead: 0,
1071
- cacheWrite: 0,
1072
- },
1073
- contextWindow: 262144,
1074
- maxTokens: 131072,
1075
- },
1076
1042
  "openai.gpt-oss-120b-1:0": {
1077
1043
  id: "openai.gpt-oss-120b-1:0",
1078
1044
  name: "gpt-oss-120b",
@@ -1209,23 +1175,6 @@ export const MODELS = {
1209
1175
  contextWindow: 131072,
1210
1176
  maxTokens: 65536,
1211
1177
  },
1212
- "qwen.qwen3-coder-next": {
1213
- id: "qwen.qwen3-coder-next",
1214
- name: "Qwen3 Coder Next",
1215
- api: "bedrock-converse-stream",
1216
- provider: "amazon-bedrock",
1217
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1218
- reasoning: true,
1219
- input: ["text"],
1220
- cost: {
1221
- input: 0.22,
1222
- output: 1.8,
1223
- cacheRead: 0,
1224
- cacheWrite: 0,
1225
- },
1226
- contextWindow: 131072,
1227
- maxTokens: 65536,
1228
- },
1229
1178
  "qwen.qwen3-next-80b-a3b": {
1230
1179
  id: "qwen.qwen3-next-80b-a3b",
1231
1180
  name: "Qwen/Qwen3-Next-80B-A3B-Instruct",
@@ -1464,23 +1413,6 @@ export const MODELS = {
1464
1413
  contextWindow: 200000,
1465
1414
  maxTokens: 131072,
1466
1415
  },
1467
- "zai.glm-5": {
1468
- id: "zai.glm-5",
1469
- name: "GLM-5",
1470
- api: "bedrock-converse-stream",
1471
- provider: "amazon-bedrock",
1472
- baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1473
- reasoning: true,
1474
- input: ["text"],
1475
- cost: {
1476
- input: 1,
1477
- output: 3.2,
1478
- cacheRead: 0,
1479
- cacheWrite: 0,
1480
- },
1481
- contextWindow: 202752,
1482
- maxTokens: 101376,
1483
- },
1484
1416
  },
1485
1417
  "anthropic": {
1486
1418
  "claude-3-5-haiku-20241022": {
@@ -1568,6 +1500,23 @@ export const MODELS = {
1568
1500
  contextWindow: 200000,
1569
1501
  maxTokens: 64000,
1570
1502
  },
1503
+ "claude-3-7-sonnet-latest": {
1504
+ id: "claude-3-7-sonnet-latest",
1505
+ name: "Claude Sonnet 3.7 (latest)",
1506
+ api: "anthropic-messages",
1507
+ provider: "anthropic",
1508
+ baseUrl: "https://api.anthropic.com",
1509
+ reasoning: true,
1510
+ input: ["text", "image"],
1511
+ cost: {
1512
+ input: 3,
1513
+ output: 15,
1514
+ cacheRead: 0.3,
1515
+ cacheWrite: 3.75,
1516
+ },
1517
+ contextWindow: 200000,
1518
+ maxTokens: 64000,
1519
+ },
1571
1520
  "claude-3-haiku-20240307": {
1572
1521
  id: "claude-3-haiku-20240307",
1573
1522
  name: "Claude Haiku 3",
@@ -2301,23 +2250,6 @@ export const MODELS = {
2301
2250
  contextWindow: 400000,
2302
2251
  maxTokens: 128000,
2303
2252
  },
2304
- "gpt-5.3-chat-latest": {
2305
- id: "gpt-5.3-chat-latest",
2306
- name: "GPT-5.3 Chat (latest)",
2307
- api: "azure-openai-responses",
2308
- provider: "azure-openai-responses",
2309
- baseUrl: "",
2310
- reasoning: false,
2311
- input: ["text", "image"],
2312
- cost: {
2313
- input: 1.75,
2314
- output: 14,
2315
- cacheRead: 0.175,
2316
- cacheWrite: 0,
2317
- },
2318
- contextWindow: 128000,
2319
- maxTokens: 16384,
2320
- },
2321
2253
  "gpt-5.3-codex": {
2322
2254
  id: "gpt-5.3-codex",
2323
2255
  name: "GPT-5.3 Codex",
@@ -3032,7 +2964,7 @@ export const MODELS = {
3032
2964
  },
3033
2965
  "gpt-5.4-mini": {
3034
2966
  id: "gpt-5.4-mini",
3035
- name: "GPT-5.4 Mini",
2967
+ name: "GPT-5.4 mini",
3036
2968
  api: "openai-responses",
3037
2969
  provider: "github-copilot",
3038
2970
  baseUrl: "https://api.individual.githubcopilot.com",
@@ -3477,57 +3409,6 @@ export const MODELS = {
3477
3409
  contextWindow: 131072,
3478
3410
  maxTokens: 65536,
3479
3411
  },
3480
- "gemma-3-27b-it": {
3481
- id: "gemma-3-27b-it",
3482
- name: "Gemma 3 27B",
3483
- api: "google-generative-ai",
3484
- provider: "google",
3485
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3486
- reasoning: false,
3487
- input: ["text", "image"],
3488
- cost: {
3489
- input: 0,
3490
- output: 0,
3491
- cacheRead: 0,
3492
- cacheWrite: 0,
3493
- },
3494
- contextWindow: 131072,
3495
- maxTokens: 8192,
3496
- },
3497
- "gemma-4-26b-it": {
3498
- id: "gemma-4-26b-it",
3499
- name: "Gemma 4 26B",
3500
- api: "google-generative-ai",
3501
- provider: "google",
3502
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3503
- reasoning: true,
3504
- input: ["text", "image"],
3505
- cost: {
3506
- input: 0,
3507
- output: 0,
3508
- cacheRead: 0,
3509
- cacheWrite: 0,
3510
- },
3511
- contextWindow: 256000,
3512
- maxTokens: 8192,
3513
- },
3514
- "gemma-4-31b-it": {
3515
- id: "gemma-4-31b-it",
3516
- name: "Gemma 4 31B",
3517
- api: "google-generative-ai",
3518
- provider: "google",
3519
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3520
- reasoning: true,
3521
- input: ["text", "image"],
3522
- cost: {
3523
- input: 0,
3524
- output: 0,
3525
- cacheRead: 0,
3526
- cacheWrite: 0,
3527
- },
3528
- contextWindow: 256000,
3529
- maxTokens: 8192,
3530
- },
3531
3412
  },
3532
3413
  "google-antigravity": {
3533
3414
  "claude-opus-4-5-thinking": {
@@ -4029,40 +3910,6 @@ export const MODELS = {
4029
3910
  contextWindow: 8192,
4030
3911
  maxTokens: 8192,
4031
3912
  },
4032
- "groq/compound": {
4033
- id: "groq/compound",
4034
- name: "Compound",
4035
- api: "openai-completions",
4036
- provider: "groq",
4037
- baseUrl: "https://api.groq.com/openai/v1",
4038
- reasoning: true,
4039
- input: ["text"],
4040
- cost: {
4041
- input: 0,
4042
- output: 0,
4043
- cacheRead: 0,
4044
- cacheWrite: 0,
4045
- },
4046
- contextWindow: 131072,
4047
- maxTokens: 8192,
4048
- },
4049
- "groq/compound-mini": {
4050
- id: "groq/compound-mini",
4051
- name: "Compound Mini",
4052
- api: "openai-completions",
4053
- provider: "groq",
4054
- baseUrl: "https://api.groq.com/openai/v1",
4055
- reasoning: true,
4056
- input: ["text"],
4057
- cost: {
4058
- input: 0,
4059
- output: 0,
4060
- cacheRead: 0,
4061
- cacheWrite: 0,
4062
- },
4063
- contextWindow: 131072,
4064
- maxTokens: 8192,
4065
- },
4066
3913
  "llama-3.1-8b-instant": {
4067
3914
  id: "llama-3.1-8b-instant",
4068
3915
  name: "Llama 3.1 8B Instant",
@@ -4250,23 +4097,6 @@ export const MODELS = {
4250
4097
  contextWindow: 131072,
4251
4098
  maxTokens: 65536,
4252
4099
  },
4253
- "openai/gpt-oss-safeguard-20b": {
4254
- id: "openai/gpt-oss-safeguard-20b",
4255
- name: "Safety GPT OSS 20B",
4256
- api: "openai-completions",
4257
- provider: "groq",
4258
- baseUrl: "https://api.groq.com/openai/v1",
4259
- reasoning: true,
4260
- input: ["text"],
4261
- cost: {
4262
- input: 0.075,
4263
- output: 0.3,
4264
- cacheRead: 0.037,
4265
- cacheWrite: 0,
4266
- },
4267
- contextWindow: 131072,
4268
- maxTokens: 65536,
4269
- },
4270
4100
  "qwen-qwq-32b": {
4271
4101
  id: "qwen-qwq-32b",
4272
4102
  name: "Qwen QwQ 32B",
@@ -4299,7 +4129,7 @@ export const MODELS = {
4299
4129
  cacheWrite: 0,
4300
4130
  },
4301
4131
  contextWindow: 131072,
4302
- maxTokens: 40960,
4132
+ maxTokens: 16384,
4303
4133
  },
4304
4134
  },
4305
4135
  "huggingface": {
@@ -4627,24 +4457,6 @@ export const MODELS = {
4627
4457
  contextWindow: 202752,
4628
4458
  maxTokens: 131072,
4629
4459
  },
4630
- "zai-org/GLM-5.1": {
4631
- id: "zai-org/GLM-5.1",
4632
- name: "GLM-5.1",
4633
- api: "openai-completions",
4634
- provider: "huggingface",
4635
- baseUrl: "https://router.huggingface.co/v1",
4636
- compat: { "supportsDeveloperRole": false },
4637
- reasoning: true,
4638
- input: ["text"],
4639
- cost: {
4640
- input: 1,
4641
- output: 3.2,
4642
- cacheRead: 0.2,
4643
- cacheWrite: 0,
4644
- },
4645
- contextWindow: 202752,
4646
- maxTokens: 131072,
4647
- },
4648
4460
  },
4649
4461
  "kimi-coding": {
4650
4462
  "k2p5": {
@@ -5214,39 +5026,22 @@ export const MODELS = {
5214
5026
  contextWindow: 128000,
5215
5027
  maxTokens: 16384,
5216
5028
  },
5217
- "mistral-small-2603": {
5218
- id: "mistral-small-2603",
5219
- name: "Mistral Small 4",
5220
- api: "mistral-conversations",
5221
- provider: "mistral",
5222
- baseUrl: "https://api.mistral.ai",
5223
- reasoning: true,
5224
- input: ["text", "image"],
5225
- cost: {
5226
- input: 0.15,
5227
- output: 0.6,
5228
- cacheRead: 0,
5229
- cacheWrite: 0,
5230
- },
5231
- contextWindow: 256000,
5232
- maxTokens: 256000,
5233
- },
5234
5029
  "mistral-small-latest": {
5235
5030
  id: "mistral-small-latest",
5236
5031
  name: "Mistral Small (latest)",
5237
5032
  api: "mistral-conversations",
5238
5033
  provider: "mistral",
5239
5034
  baseUrl: "https://api.mistral.ai",
5240
- reasoning: true,
5035
+ reasoning: false,
5241
5036
  input: ["text", "image"],
5242
5037
  cost: {
5243
- input: 0.15,
5244
- output: 0.6,
5038
+ input: 0.1,
5039
+ output: 0.3,
5245
5040
  cacheRead: 0,
5246
5041
  cacheWrite: 0,
5247
5042
  },
5248
- contextWindow: 256000,
5249
- maxTokens: 256000,
5043
+ contextWindow: 128000,
5044
+ maxTokens: 16384,
5250
5045
  },
5251
5046
  "open-mistral-7b": {
5252
5047
  id: "open-mistral-7b",
@@ -5777,23 +5572,6 @@ export const MODELS = {
5777
5572
  contextWindow: 400000,
5778
5573
  maxTokens: 128000,
5779
5574
  },
5780
- "gpt-5.3-chat-latest": {
5781
- id: "gpt-5.3-chat-latest",
5782
- name: "GPT-5.3 Chat (latest)",
5783
- api: "openai-responses",
5784
- provider: "openai",
5785
- baseUrl: "https://api.openai.com/v1",
5786
- reasoning: false,
5787
- input: ["text", "image"],
5788
- cost: {
5789
- input: 1.75,
5790
- output: 14,
5791
- cacheRead: 0.175,
5792
- cacheWrite: 0,
5793
- },
5794
- contextWindow: 128000,
5795
- maxTokens: 16384,
5796
- },
5797
5575
  "gpt-5.3-codex": {
5798
5576
  id: "gpt-5.3-codex",
5799
5577
  name: "GPT-5.3 Codex",
@@ -6376,23 +6154,6 @@ export const MODELS = {
6376
6154
  contextWindow: 204800,
6377
6155
  maxTokens: 131072,
6378
6156
  },
6379
- "glm-5.1": {
6380
- id: "glm-5.1",
6381
- name: "GLM-5.1",
6382
- api: "openai-completions",
6383
- provider: "opencode",
6384
- baseUrl: "https://opencode.ai/zen/v1",
6385
- reasoning: true,
6386
- input: ["text"],
6387
- cost: {
6388
- input: 1.4,
6389
- output: 4.4,
6390
- cacheRead: 0.26,
6391
- cacheWrite: 0,
6392
- },
6393
- contextWindow: 204800,
6394
- maxTokens: 131072,
6395
- },
6396
6157
  "gpt-5": {
6397
6158
  id: "gpt-5",
6398
6159
  name: "GPT-5",
@@ -6648,24 +6409,58 @@ export const MODELS = {
6648
6409
  contextWindow: 262144,
6649
6410
  maxTokens: 65536,
6650
6411
  },
6651
- "minimax-m2.5": {
6652
- id: "minimax-m2.5",
6653
- name: "MiniMax M2.5",
6412
+ "mimo-v2-omni-free": {
6413
+ id: "mimo-v2-omni-free",
6414
+ name: "MiMo V2 Omni Free",
6654
6415
  api: "openai-completions",
6655
6416
  provider: "opencode",
6656
6417
  baseUrl: "https://opencode.ai/zen/v1",
6657
6418
  reasoning: true,
6658
- input: ["text"],
6419
+ input: ["text", "image"],
6659
6420
  cost: {
6660
- input: 0.3,
6661
- output: 1.2,
6662
- cacheRead: 0.06,
6421
+ input: 0,
6422
+ output: 0,
6423
+ cacheRead: 0,
6663
6424
  cacheWrite: 0,
6664
6425
  },
6665
- contextWindow: 204800,
6666
- maxTokens: 131072,
6426
+ contextWindow: 262144,
6427
+ maxTokens: 64000,
6667
6428
  },
6668
- "minimax-m2.5-free": {
6429
+ "mimo-v2-pro-free": {
6430
+ id: "mimo-v2-pro-free",
6431
+ name: "MiMo V2 Pro Free",
6432
+ api: "openai-completions",
6433
+ provider: "opencode",
6434
+ baseUrl: "https://opencode.ai/zen/v1",
6435
+ reasoning: true,
6436
+ input: ["text"],
6437
+ cost: {
6438
+ input: 0,
6439
+ output: 0,
6440
+ cacheRead: 0,
6441
+ cacheWrite: 0,
6442
+ },
6443
+ contextWindow: 1048576,
6444
+ maxTokens: 64000,
6445
+ },
6446
+ "minimax-m2.5": {
6447
+ id: "minimax-m2.5",
6448
+ name: "MiniMax M2.5",
6449
+ api: "openai-completions",
6450
+ provider: "opencode",
6451
+ baseUrl: "https://opencode.ai/zen/v1",
6452
+ reasoning: true,
6453
+ input: ["text"],
6454
+ cost: {
6455
+ input: 0.3,
6456
+ output: 1.2,
6457
+ cacheRead: 0.06,
6458
+ cacheWrite: 0,
6459
+ },
6460
+ contextWindow: 204800,
6461
+ maxTokens: 131072,
6462
+ },
6463
+ "minimax-m2.5-free": {
6669
6464
  id: "minimax-m2.5-free",
6670
6465
  name: "MiniMax M2.5 Free",
6671
6466
  api: "anthropic-messages",
@@ -6696,7 +6491,7 @@ export const MODELS = {
6696
6491
  cacheRead: 0,
6697
6492
  cacheWrite: 0,
6698
6493
  },
6699
- contextWindow: 204800,
6494
+ contextWindow: 1000000,
6700
6495
  maxTokens: 128000,
6701
6496
  },
6702
6497
  },
@@ -6718,23 +6513,6 @@ export const MODELS = {
6718
6513
  contextWindow: 204800,
6719
6514
  maxTokens: 131072,
6720
6515
  },
6721
- "glm-5.1": {
6722
- id: "glm-5.1",
6723
- name: "GLM-5.1",
6724
- api: "openai-completions",
6725
- provider: "opencode-go",
6726
- baseUrl: "https://opencode.ai/zen/go/v1",
6727
- reasoning: true,
6728
- input: ["text"],
6729
- cost: {
6730
- input: 1.4,
6731
- output: 4.4,
6732
- cacheRead: 0.26,
6733
- cacheWrite: 0,
6734
- },
6735
- contextWindow: 204800,
6736
- maxTokens: 131072,
6737
- },
6738
6516
  "kimi-k2.5": {
6739
6517
  id: "kimi-k2.5",
6740
6518
  name: "Kimi K2.5",
@@ -6752,40 +6530,6 @@ export const MODELS = {
6752
6530
  contextWindow: 262144,
6753
6531
  maxTokens: 65536,
6754
6532
  },
6755
- "mimo-v2-omni": {
6756
- id: "mimo-v2-omni",
6757
- name: "MiMo V2 Omni",
6758
- api: "openai-completions",
6759
- provider: "opencode-go",
6760
- baseUrl: "https://opencode.ai/zen/go/v1",
6761
- reasoning: true,
6762
- input: ["text", "image"],
6763
- cost: {
6764
- input: 0.4,
6765
- output: 2,
6766
- cacheRead: 0.08,
6767
- cacheWrite: 0,
6768
- },
6769
- contextWindow: 262144,
6770
- maxTokens: 64000,
6771
- },
6772
- "mimo-v2-pro": {
6773
- id: "mimo-v2-pro",
6774
- name: "MiMo V2 Pro",
6775
- api: "openai-completions",
6776
- provider: "opencode-go",
6777
- baseUrl: "https://opencode.ai/zen/go/v1",
6778
- reasoning: true,
6779
- input: ["text"],
6780
- cost: {
6781
- input: 1,
6782
- output: 3,
6783
- cacheRead: 0.2,
6784
- cacheWrite: 0,
6785
- },
6786
- contextWindow: 1048576,
6787
- maxTokens: 64000,
6788
- },
6789
6533
  "minimax-m2.5": {
6790
6534
  id: "minimax-m2.5",
6791
6535
  name: "MiniMax M2.5",
@@ -6992,6 +6736,23 @@ export const MODELS = {
6992
6736
  contextWindow: 200000,
6993
6737
  maxTokens: 8192,
6994
6738
  },
6739
+ "anthropic/claude-3.5-sonnet": {
6740
+ id: "anthropic/claude-3.5-sonnet",
6741
+ name: "Anthropic: Claude 3.5 Sonnet",
6742
+ api: "openai-completions",
6743
+ provider: "openrouter",
6744
+ baseUrl: "https://openrouter.ai/api/v1",
6745
+ reasoning: false,
6746
+ input: ["text", "image"],
6747
+ cost: {
6748
+ input: 6,
6749
+ output: 30,
6750
+ cacheRead: 0.6,
6751
+ cacheWrite: 7.5,
6752
+ },
6753
+ contextWindow: 200000,
6754
+ maxTokens: 8192,
6755
+ },
6995
6756
  "anthropic/claude-3.7-sonnet": {
6996
6757
  id: "anthropic/claude-3.7-sonnet",
6997
6758
  name: "Anthropic: Claude 3.7 Sonnet",
@@ -7007,7 +6768,7 @@ export const MODELS = {
7007
6768
  cacheWrite: 3.75,
7008
6769
  },
7009
6770
  contextWindow: 200000,
7010
- maxTokens: 128000,
6771
+ maxTokens: 64000,
7011
6772
  },
7012
6773
  "anthropic/claude-3.7-sonnet:thinking": {
7013
6774
  id: "anthropic/claude-3.7-sonnet:thinking",
@@ -7111,23 +6872,6 @@ export const MODELS = {
7111
6872
  contextWindow: 1000000,
7112
6873
  maxTokens: 128000,
7113
6874
  },
7114
- "anthropic/claude-opus-4.6-fast": {
7115
- id: "anthropic/claude-opus-4.6-fast",
7116
- name: "Anthropic: Claude Opus 4.6 (Fast)",
7117
- api: "openai-completions",
7118
- provider: "openrouter",
7119
- baseUrl: "https://openrouter.ai/api/v1",
7120
- reasoning: true,
7121
- input: ["text", "image"],
7122
- cost: {
7123
- input: 30,
7124
- output: 150,
7125
- cacheRead: 3,
7126
- cacheWrite: 37.5,
7127
- },
7128
- contextWindow: 1000000,
7129
- maxTokens: 128000,
7130
- },
7131
6875
  "anthropic/claude-sonnet-4": {
7132
6876
  id: "anthropic/claude-sonnet-4",
7133
6877
  name: "Anthropic: Claude Sonnet 4",
@@ -7142,7 +6886,7 @@ export const MODELS = {
7142
6886
  cacheRead: 0.3,
7143
6887
  cacheWrite: 3.75,
7144
6888
  },
7145
- contextWindow: 1000000,
6889
+ contextWindow: 200000,
7146
6890
  maxTokens: 64000,
7147
6891
  },
7148
6892
  "anthropic/claude-sonnet-4.5": {
@@ -7196,39 +6940,39 @@ export const MODELS = {
7196
6940
  contextWindow: 131000,
7197
6941
  maxTokens: 4096,
7198
6942
  },
7199
- "arcee-ai/trinity-large-thinking": {
7200
- id: "arcee-ai/trinity-large-thinking",
7201
- name: "Arcee AI: Trinity Large Thinking",
6943
+ "arcee-ai/trinity-mini": {
6944
+ id: "arcee-ai/trinity-mini",
6945
+ name: "Arcee AI: Trinity Mini",
7202
6946
  api: "openai-completions",
7203
6947
  provider: "openrouter",
7204
6948
  baseUrl: "https://openrouter.ai/api/v1",
7205
6949
  reasoning: true,
7206
6950
  input: ["text"],
7207
6951
  cost: {
7208
- input: 0.22,
7209
- output: 0.85,
6952
+ input: 0.045,
6953
+ output: 0.15,
7210
6954
  cacheRead: 0,
7211
6955
  cacheWrite: 0,
7212
6956
  },
7213
- contextWindow: 262144,
7214
- maxTokens: 262144,
6957
+ contextWindow: 131072,
6958
+ maxTokens: 131072,
7215
6959
  },
7216
- "arcee-ai/trinity-mini": {
7217
- id: "arcee-ai/trinity-mini",
7218
- name: "Arcee AI: Trinity Mini",
6960
+ "arcee-ai/trinity-mini:free": {
6961
+ id: "arcee-ai/trinity-mini:free",
6962
+ name: "Arcee AI: Trinity Mini (free)",
7219
6963
  api: "openai-completions",
7220
6964
  provider: "openrouter",
7221
6965
  baseUrl: "https://openrouter.ai/api/v1",
7222
6966
  reasoning: true,
7223
6967
  input: ["text"],
7224
6968
  cost: {
7225
- input: 0.045,
7226
- output: 0.15,
6969
+ input: 0,
6970
+ output: 0,
7227
6971
  cacheRead: 0,
7228
6972
  cacheWrite: 0,
7229
6973
  },
7230
6974
  contextWindow: 131072,
7231
- maxTokens: 131072,
6975
+ maxTokens: 4096,
7232
6976
  },
7233
6977
  "arcee-ai/virtuoso-large": {
7234
6978
  id: "arcee-ai/virtuoso-large",
@@ -7477,13 +7221,13 @@ export const MODELS = {
7477
7221
  reasoning: true,
7478
7222
  input: ["text"],
7479
7223
  cost: {
7480
- input: 0.5,
7224
+ input: 0.44999999999999996,
7481
7225
  output: 2.1500000000000004,
7482
- cacheRead: 0.35,
7226
+ cacheRead: 0.22499999999999998,
7483
7227
  cacheWrite: 0,
7484
7228
  },
7485
7229
  contextWindow: 163840,
7486
- maxTokens: 4096,
7230
+ maxTokens: 65536,
7487
7231
  },
7488
7232
  "deepseek/deepseek-v3.1-terminus": {
7489
7233
  id: "deepseek/deepseek-v3.1-terminus",
@@ -7636,7 +7380,7 @@ export const MODELS = {
7636
7380
  cacheWrite: 0.08333333333333334,
7637
7381
  },
7638
7382
  contextWindow: 1048576,
7639
- maxTokens: 65535,
7383
+ maxTokens: 65536,
7640
7384
  },
7641
7385
  "google/gemini-2.5-pro": {
7642
7386
  id: "google/gemini-2.5-pro",
@@ -7706,6 +7450,23 @@ export const MODELS = {
7706
7450
  contextWindow: 1048576,
7707
7451
  maxTokens: 65536,
7708
7452
  },
7453
+ "google/gemini-3-pro-preview": {
7454
+ id: "google/gemini-3-pro-preview",
7455
+ name: "Google: Gemini 3 Pro Preview",
7456
+ api: "openai-completions",
7457
+ provider: "openrouter",
7458
+ baseUrl: "https://openrouter.ai/api/v1",
7459
+ reasoning: true,
7460
+ input: ["text", "image"],
7461
+ cost: {
7462
+ input: 2,
7463
+ output: 12,
7464
+ cacheRead: 0.19999999999999998,
7465
+ cacheWrite: 0.375,
7466
+ },
7467
+ contextWindow: 1048576,
7468
+ maxTokens: 65536,
7469
+ },
7709
7470
  "google/gemini-3.1-flash-lite-preview": {
7710
7471
  id: "google/gemini-3.1-flash-lite-preview",
7711
7472
  name: "Google: Gemini 3.1 Flash Lite Preview",
@@ -7757,74 +7518,6 @@ export const MODELS = {
7757
7518
  contextWindow: 1048576,
7758
7519
  maxTokens: 65536,
7759
7520
  },
7760
- "google/gemma-4-26b-a4b-it": {
7761
- id: "google/gemma-4-26b-a4b-it",
7762
- name: "Google: Gemma 4 26B A4B ",
7763
- api: "openai-completions",
7764
- provider: "openrouter",
7765
- baseUrl: "https://openrouter.ai/api/v1",
7766
- reasoning: true,
7767
- input: ["text", "image"],
7768
- cost: {
7769
- input: 0.12,
7770
- output: 0.39999999999999997,
7771
- cacheRead: 0,
7772
- cacheWrite: 0,
7773
- },
7774
- contextWindow: 262144,
7775
- maxTokens: 262144,
7776
- },
7777
- "google/gemma-4-26b-a4b-it:free": {
7778
- id: "google/gemma-4-26b-a4b-it:free",
7779
- name: "Google: Gemma 4 26B A4B (free)",
7780
- api: "openai-completions",
7781
- provider: "openrouter",
7782
- baseUrl: "https://openrouter.ai/api/v1",
7783
- reasoning: true,
7784
- input: ["text", "image"],
7785
- cost: {
7786
- input: 0,
7787
- output: 0,
7788
- cacheRead: 0,
7789
- cacheWrite: 0,
7790
- },
7791
- contextWindow: 262144,
7792
- maxTokens: 32768,
7793
- },
7794
- "google/gemma-4-31b-it": {
7795
- id: "google/gemma-4-31b-it",
7796
- name: "Google: Gemma 4 31B",
7797
- api: "openai-completions",
7798
- provider: "openrouter",
7799
- baseUrl: "https://openrouter.ai/api/v1",
7800
- reasoning: true,
7801
- input: ["text", "image"],
7802
- cost: {
7803
- input: 0.14,
7804
- output: 0.39999999999999997,
7805
- cacheRead: 0,
7806
- cacheWrite: 0,
7807
- },
7808
- contextWindow: 262144,
7809
- maxTokens: 131072,
7810
- },
7811
- "google/gemma-4-31b-it:free": {
7812
- id: "google/gemma-4-31b-it:free",
7813
- name: "Google: Gemma 4 31B (free)",
7814
- api: "openai-completions",
7815
- provider: "openrouter",
7816
- baseUrl: "https://openrouter.ai/api/v1",
7817
- reasoning: true,
7818
- input: ["text", "image"],
7819
- cost: {
7820
- input: 0,
7821
- output: 0,
7822
- cacheRead: 0,
7823
- cacheWrite: 0,
7824
- },
7825
- contextWindow: 262144,
7826
- maxTokens: 32768,
7827
- },
7828
7521
  "inception/mercury": {
7829
7522
  id: "inception/mercury",
7830
7523
  name: "Inception: Mercury",
@@ -7876,22 +7569,22 @@ export const MODELS = {
7876
7569
  contextWindow: 128000,
7877
7570
  maxTokens: 32000,
7878
7571
  },
7879
- "kwaipilot/kat-coder-pro-v2": {
7880
- id: "kwaipilot/kat-coder-pro-v2",
7881
- name: "Kwaipilot: KAT-Coder-Pro V2",
7572
+ "kwaipilot/kat-coder-pro": {
7573
+ id: "kwaipilot/kat-coder-pro",
7574
+ name: "Kwaipilot: KAT-Coder-Pro V1",
7882
7575
  api: "openai-completions",
7883
7576
  provider: "openrouter",
7884
7577
  baseUrl: "https://openrouter.ai/api/v1",
7885
7578
  reasoning: false,
7886
7579
  input: ["text"],
7887
7580
  cost: {
7888
- input: 0.3,
7889
- output: 1.2,
7890
- cacheRead: 0.06,
7581
+ input: 0.207,
7582
+ output: 0.828,
7583
+ cacheRead: 0.0414,
7891
7584
  cacheWrite: 0,
7892
7585
  },
7893
7586
  contextWindow: 256000,
7894
- maxTokens: 80000,
7587
+ maxTokens: 128000,
7895
7588
  },
7896
7589
  "meituan/longcat-flash-chat": {
7897
7590
  id: "meituan/longcat-flash-chat",
@@ -8072,13 +7765,13 @@ export const MODELS = {
8072
7765
  reasoning: true,
8073
7766
  input: ["text"],
8074
7767
  cost: {
8075
- input: 0.29,
7768
+ input: 0.27,
8076
7769
  output: 0.95,
8077
- cacheRead: 0.03,
7770
+ cacheRead: 0.0290000007,
8078
7771
  cacheWrite: 0,
8079
7772
  },
8080
7773
  contextWindow: 196608,
8081
- maxTokens: 196608,
7774
+ maxTokens: 4096,
8082
7775
  },
8083
7776
  "minimax/minimax-m2.5": {
8084
7777
  id: "minimax/minimax-m2.5",
@@ -8089,9 +7782,9 @@ export const MODELS = {
8089
7782
  reasoning: true,
8090
7783
  input: ["text"],
8091
7784
  cost: {
8092
- input: 0.118,
8093
- output: 0.9900000000000001,
8094
- cacheRead: 0.059,
7785
+ input: 0.19999999999999998,
7786
+ output: 1.17,
7787
+ cacheRead: 0.09999999999999999,
8095
7788
  cacheWrite: 0,
8096
7789
  },
8097
7790
  contextWindow: 196608,
@@ -8112,7 +7805,7 @@ export const MODELS = {
8112
7805
  cacheWrite: 0,
8113
7806
  },
8114
7807
  contextWindow: 196608,
8115
- maxTokens: 8192,
7808
+ maxTokens: 196608,
8116
7809
  },
8117
7810
  "minimax/minimax-m2.7": {
8118
7811
  id: "minimax/minimax-m2.7",
@@ -8125,11 +7818,11 @@ export const MODELS = {
8125
7818
  cost: {
8126
7819
  input: 0.3,
8127
7820
  output: 1.2,
8128
- cacheRead: 0.059,
7821
+ cacheRead: 0.06,
8129
7822
  cacheWrite: 0,
8130
7823
  },
8131
- contextWindow: 196608,
8132
- maxTokens: 4096,
7824
+ contextWindow: 204800,
7825
+ maxTokens: 131072,
8133
7826
  },
8134
7827
  "mistralai/codestral-2508": {
8135
7828
  id: "mistralai/codestral-2508",
@@ -8386,6 +8079,23 @@ export const MODELS = {
8386
8079
  contextWindow: 32768,
8387
8080
  maxTokens: 4096,
8388
8081
  },
8082
+ "mistralai/mistral-small-24b-instruct-2501": {
8083
+ id: "mistralai/mistral-small-24b-instruct-2501",
8084
+ name: "Mistral: Mistral Small 3",
8085
+ api: "openai-completions",
8086
+ provider: "openrouter",
8087
+ baseUrl: "https://openrouter.ai/api/v1",
8088
+ reasoning: false,
8089
+ input: ["text"],
8090
+ cost: {
8091
+ input: 0.049999999999999996,
8092
+ output: 0.08,
8093
+ cacheRead: 0,
8094
+ cacheWrite: 0,
8095
+ },
8096
+ contextWindow: 32768,
8097
+ maxTokens: 16384,
8098
+ },
8389
8099
  "mistralai/mistral-small-2603": {
8390
8100
  id: "mistralai/mistral-small-2603",
8391
8101
  name: "Mistral: Mistral Small 4",
@@ -8403,6 +8113,23 @@ export const MODELS = {
8403
8113
  contextWindow: 262144,
8404
8114
  maxTokens: 4096,
8405
8115
  },
8116
+ "mistralai/mistral-small-3.1-24b-instruct:free": {
8117
+ id: "mistralai/mistral-small-3.1-24b-instruct:free",
8118
+ name: "Mistral: Mistral Small 3.1 24B (free)",
8119
+ api: "openai-completions",
8120
+ provider: "openrouter",
8121
+ baseUrl: "https://openrouter.ai/api/v1",
8122
+ reasoning: false,
8123
+ input: ["text", "image"],
8124
+ cost: {
8125
+ input: 0,
8126
+ output: 0,
8127
+ cacheRead: 0,
8128
+ cacheWrite: 0,
8129
+ },
8130
+ contextWindow: 128000,
8131
+ maxTokens: 4096,
8132
+ },
8406
8133
  "mistralai/mistral-small-3.2-24b-instruct": {
8407
8134
  id: "mistralai/mistral-small-3.2-24b-instruct",
8408
8135
  name: "Mistral: Mistral Small 3.2 24B",
@@ -8514,13 +8241,13 @@ export const MODELS = {
8514
8241
  reasoning: false,
8515
8242
  input: ["text"],
8516
8243
  cost: {
8517
- input: 0.5700000000000001,
8518
- output: 2.3,
8244
+ input: 0.55,
8245
+ output: 2.2,
8519
8246
  cacheRead: 0,
8520
8247
  cacheWrite: 0,
8521
8248
  },
8522
- contextWindow: 131072,
8523
- maxTokens: 131072,
8249
+ contextWindow: 131000,
8250
+ maxTokens: 4096,
8524
8251
  },
8525
8252
  "moonshotai/kimi-k2-0905": {
8526
8253
  id: "moonshotai/kimi-k2-0905",
@@ -8533,11 +8260,11 @@ export const MODELS = {
8533
8260
  cost: {
8534
8261
  input: 0.39999999999999997,
8535
8262
  output: 2,
8536
- cacheRead: 0,
8263
+ cacheRead: 0.15,
8537
8264
  cacheWrite: 0,
8538
8265
  },
8539
- contextWindow: 262144,
8540
- maxTokens: 262144,
8266
+ contextWindow: 131072,
8267
+ maxTokens: 4096,
8541
8268
  },
8542
8269
  "moonshotai/kimi-k2-thinking": {
8543
8270
  id: "moonshotai/kimi-k2-thinking",
@@ -8548,12 +8275,12 @@ export const MODELS = {
8548
8275
  reasoning: true,
8549
8276
  input: ["text"],
8550
8277
  cost: {
8551
- input: 0.6,
8552
- output: 2.5,
8553
- cacheRead: 0,
8278
+ input: 0.47,
8279
+ output: 2,
8280
+ cacheRead: 0.14100000000000001,
8554
8281
  cacheWrite: 0,
8555
8282
  },
8556
- contextWindow: 262144,
8283
+ contextWindow: 131072,
8557
8284
  maxTokens: 4096,
8558
8285
  },
8559
8286
  "moonshotai/kimi-k2.5": {
@@ -8582,8 +8309,8 @@ export const MODELS = {
8582
8309
  reasoning: false,
8583
8310
  input: ["text"],
8584
8311
  cost: {
8585
- input: 0.135,
8586
- output: 0.5,
8312
+ input: 0.27,
8313
+ output: 1,
8587
8314
  cacheRead: 0,
8588
8315
  cacheWrite: 0,
8589
8316
  },
@@ -8669,7 +8396,7 @@ export const MODELS = {
8669
8396
  cost: {
8670
8397
  input: 0.09999999999999999,
8671
8398
  output: 0.5,
8672
- cacheRead: 0.09999999999999999,
8399
+ cacheRead: 0.04,
8673
8400
  cacheWrite: 0,
8674
8401
  },
8675
8402
  contextWindow: 262144,
@@ -8894,7 +8621,7 @@ export const MODELS = {
8894
8621
  cacheWrite: 0,
8895
8622
  },
8896
8623
  contextWindow: 1047576,
8897
- maxTokens: 4096,
8624
+ maxTokens: 32768,
8898
8625
  },
8899
8626
  "openai/gpt-4.1-mini": {
8900
8627
  id: "openai/gpt-4.1-mini",
@@ -8941,7 +8668,7 @@ export const MODELS = {
8941
8668
  cost: {
8942
8669
  input: 2.5,
8943
8670
  output: 10,
8944
- cacheRead: 0,
8671
+ cacheRead: 1.25,
8945
8672
  cacheWrite: 0,
8946
8673
  },
8947
8674
  contextWindow: 128000,
@@ -9162,11 +8889,11 @@ export const MODELS = {
9162
8889
  cost: {
9163
8890
  input: 0.049999999999999996,
9164
8891
  output: 0.39999999999999997,
9165
- cacheRead: 0.01,
8892
+ cacheRead: 0.005,
9166
8893
  cacheWrite: 0,
9167
8894
  },
9168
8895
  contextWindow: 400000,
9169
- maxTokens: 4096,
8896
+ maxTokens: 128000,
9170
8897
  },
9171
8898
  "openai/gpt-5-pro": {
9172
8899
  id: "openai/gpt-5-pro",
@@ -9196,7 +8923,7 @@ export const MODELS = {
9196
8923
  cost: {
9197
8924
  input: 1.25,
9198
8925
  output: 10,
9199
- cacheRead: 0.13,
8926
+ cacheRead: 0.125,
9200
8927
  cacheWrite: 0,
9201
8928
  },
9202
8929
  contextWindow: 400000,
@@ -9264,11 +8991,11 @@ export const MODELS = {
9264
8991
  cost: {
9265
8992
  input: 0.25,
9266
8993
  output: 2,
9267
- cacheRead: 0.03,
8994
+ cacheRead: 0.024999999999999998,
9268
8995
  cacheWrite: 0,
9269
8996
  },
9270
8997
  contextWindow: 400000,
9271
- maxTokens: 128000,
8998
+ maxTokens: 100000,
9272
8999
  },
9273
9000
  "openai/gpt-5.2": {
9274
9001
  id: "openai/gpt-5.2",
@@ -9302,7 +9029,7 @@ export const MODELS = {
9302
9029
  cacheWrite: 0,
9303
9030
  },
9304
9031
  contextWindow: 128000,
9305
- maxTokens: 32000,
9032
+ maxTokens: 16384,
9306
9033
  },
9307
9034
  "openai/gpt-5.2-codex": {
9308
9035
  id: "openai/gpt-5.2-codex",
@@ -9440,40 +9167,6 @@ export const MODELS = {
9440
9167
  contextWindow: 1050000,
9441
9168
  maxTokens: 128000,
9442
9169
  },
9443
- "openai/gpt-audio": {
9444
- id: "openai/gpt-audio",
9445
- name: "OpenAI: GPT Audio",
9446
- api: "openai-completions",
9447
- provider: "openrouter",
9448
- baseUrl: "https://openrouter.ai/api/v1",
9449
- reasoning: false,
9450
- input: ["text"],
9451
- cost: {
9452
- input: 2.5,
9453
- output: 10,
9454
- cacheRead: 0,
9455
- cacheWrite: 0,
9456
- },
9457
- contextWindow: 128000,
9458
- maxTokens: 16384,
9459
- },
9460
- "openai/gpt-audio-mini": {
9461
- id: "openai/gpt-audio-mini",
9462
- name: "OpenAI: GPT Audio Mini",
9463
- api: "openai-completions",
9464
- provider: "openrouter",
9465
- baseUrl: "https://openrouter.ai/api/v1",
9466
- reasoning: false,
9467
- input: ["text"],
9468
- cost: {
9469
- input: 0.6,
9470
- output: 2.4,
9471
- cacheRead: 0,
9472
- cacheWrite: 0,
9473
- },
9474
- contextWindow: 128000,
9475
- maxTokens: 16384,
9476
- },
9477
9170
  "openai/gpt-oss-120b": {
9478
9171
  id: "openai/gpt-oss-120b",
9479
9172
  name: "OpenAI: gpt-oss-120b",
@@ -9518,12 +9211,12 @@ export const MODELS = {
9518
9211
  input: ["text"],
9519
9212
  cost: {
9520
9213
  input: 0.03,
9521
- output: 0.14,
9522
- cacheRead: 0,
9214
+ output: 0.11,
9215
+ cacheRead: 0.015,
9523
9216
  cacheWrite: 0,
9524
9217
  },
9525
9218
  contextWindow: 131072,
9526
- maxTokens: 4096,
9219
+ maxTokens: 131072,
9527
9220
  },
9528
9221
  "openai/gpt-oss-20b:free": {
9529
9222
  id: "openai/gpt-oss-20b:free",
@@ -9540,7 +9233,7 @@ export const MODELS = {
9540
9233
  cacheWrite: 0,
9541
9234
  },
9542
9235
  contextWindow: 131072,
9543
- maxTokens: 8192,
9236
+ maxTokens: 131072,
9544
9237
  },
9545
9238
  "openai/gpt-oss-safeguard-20b": {
9546
9239
  id: "openai/gpt-oss-safeguard-20b",
@@ -9795,7 +9488,7 @@ export const MODELS = {
9795
9488
  cacheWrite: 0,
9796
9489
  },
9797
9490
  contextWindow: 32768,
9798
- maxTokens: 32768,
9491
+ maxTokens: 4096,
9799
9492
  },
9800
9493
  "qwen/qwen-max": {
9801
9494
  id: "qwen/qwen-max",
@@ -10035,6 +9728,23 @@ export const MODELS = {
10035
9728
  contextWindow: 40960,
10036
9729
  maxTokens: 40960,
10037
9730
  },
9731
+ "qwen/qwen3-4b:free": {
9732
+ id: "qwen/qwen3-4b:free",
9733
+ name: "Qwen: Qwen3 4B (free)",
9734
+ api: "openai-completions",
9735
+ provider: "openrouter",
9736
+ baseUrl: "https://openrouter.ai/api/v1",
9737
+ reasoning: true,
9738
+ input: ["text"],
9739
+ cost: {
9740
+ input: 0,
9741
+ output: 0,
9742
+ cacheRead: 0,
9743
+ cacheWrite: 0,
9744
+ },
9745
+ contextWindow: 40960,
9746
+ maxTokens: 4096,
9747
+ },
10038
9748
  "qwen/qwen3-8b": {
10039
9749
  id: "qwen/qwen3-8b",
10040
9750
  name: "Qwen: Qwen3 8B",
@@ -10112,13 +9822,13 @@ export const MODELS = {
10112
9822
  reasoning: false,
10113
9823
  input: ["text"],
10114
9824
  cost: {
10115
- input: 0.15,
10116
- output: 0.7999999999999999,
10117
- cacheRead: 0.12,
9825
+ input: 0.12,
9826
+ output: 0.75,
9827
+ cacheRead: 0.06,
10118
9828
  cacheWrite: 0,
10119
9829
  },
10120
9830
  contextWindow: 262144,
10121
- maxTokens: 262144,
9831
+ maxTokens: 65536,
10122
9832
  },
10123
9833
  "qwen/qwen3-coder-plus": {
10124
9834
  id: "qwen/qwen3-coder-plus",
@@ -10441,7 +10151,7 @@ export const MODELS = {
10441
10151
  cacheWrite: 0,
10442
10152
  },
10443
10153
  contextWindow: 256000,
10444
- maxTokens: 32768,
10154
+ maxTokens: 4096,
10445
10155
  },
10446
10156
  "qwen/qwen3.5-flash-02-23": {
10447
10157
  id: "qwen/qwen3.5-flash-02-23",
@@ -10477,23 +10187,6 @@ export const MODELS = {
10477
10187
  contextWindow: 1000000,
10478
10188
  maxTokens: 65536,
10479
10189
  },
10480
- "qwen/qwen3.6-plus": {
10481
- id: "qwen/qwen3.6-plus",
10482
- name: "Qwen: Qwen3.6 Plus",
10483
- api: "openai-completions",
10484
- provider: "openrouter",
10485
- baseUrl: "https://openrouter.ai/api/v1",
10486
- reasoning: true,
10487
- input: ["text", "image"],
10488
- cost: {
10489
- input: 0.325,
10490
- output: 1.95,
10491
- cacheRead: 0,
10492
- cacheWrite: 0,
10493
- },
10494
- contextWindow: 1000000,
10495
- maxTokens: 65536,
10496
- },
10497
10190
  "qwen/qwq-32b": {
10498
10191
  id: "qwen/qwq-32b",
10499
10192
  name: "Qwen: QwQ 32B",
@@ -10511,23 +10204,6 @@ export const MODELS = {
10511
10204
  contextWindow: 131072,
10512
10205
  maxTokens: 131072,
10513
10206
  },
10514
- "rekaai/reka-edge": {
10515
- id: "rekaai/reka-edge",
10516
- name: "Reka Edge",
10517
- api: "openai-completions",
10518
- provider: "openrouter",
10519
- baseUrl: "https://openrouter.ai/api/v1",
10520
- reasoning: false,
10521
- input: ["text", "image"],
10522
- cost: {
10523
- input: 0.09999999999999999,
10524
- output: 0.09999999999999999,
10525
- cacheRead: 0,
10526
- cacheWrite: 0,
10527
- },
10528
- contextWindow: 16384,
10529
- maxTokens: 16384,
10530
- },
10531
10207
  "relace/relace-search": {
10532
10208
  id: "relace/relace-search",
10533
10209
  name: "Relace: Relace Search",
@@ -10590,11 +10266,28 @@ export const MODELS = {
10590
10266
  cost: {
10591
10267
  input: 0.09999999999999999,
10592
10268
  output: 0.3,
10269
+ cacheRead: 0.02,
10270
+ cacheWrite: 0,
10271
+ },
10272
+ contextWindow: 256000,
10273
+ maxTokens: 256000,
10274
+ },
10275
+ "stepfun/step-3.5-flash:free": {
10276
+ id: "stepfun/step-3.5-flash:free",
10277
+ name: "StepFun: Step 3.5 Flash (free)",
10278
+ api: "openai-completions",
10279
+ provider: "openrouter",
10280
+ baseUrl: "https://openrouter.ai/api/v1",
10281
+ reasoning: true,
10282
+ input: ["text"],
10283
+ cost: {
10284
+ input: 0,
10285
+ output: 0,
10593
10286
  cacheRead: 0,
10594
10287
  cacheWrite: 0,
10595
10288
  },
10596
- contextWindow: 262144,
10597
- maxTokens: 65536,
10289
+ contextWindow: 256000,
10290
+ maxTokens: 256000,
10598
10291
  },
10599
10292
  "thedrummer/rocinante-12b": {
10600
10293
  id: "thedrummer/rocinante-12b",
@@ -10783,9 +10476,9 @@ export const MODELS = {
10783
10476
  contextWindow: 2000000,
10784
10477
  maxTokens: 30000,
10785
10478
  },
10786
- "x-ai/grok-4.20": {
10787
- id: "x-ai/grok-4.20",
10788
- name: "xAI: Grok 4.20",
10479
+ "x-ai/grok-4.20-beta": {
10480
+ id: "x-ai/grok-4.20-beta",
10481
+ name: "xAI: Grok 4.20 Beta",
10789
10482
  api: "openai-completions",
10790
10483
  provider: "openrouter",
10791
10484
  baseUrl: "https://openrouter.ai/api/v1",
@@ -11047,43 +10740,9 @@ export const MODELS = {
11047
10740
  reasoning: true,
11048
10741
  input: ["text"],
11049
10742
  cost: {
11050
- input: 1.2,
11051
- output: 4,
11052
- cacheRead: 0.24,
11053
- cacheWrite: 0,
11054
- },
11055
- contextWindow: 202752,
11056
- maxTokens: 131072,
11057
- },
11058
- "z-ai/glm-5.1": {
11059
- id: "z-ai/glm-5.1",
11060
- name: "Z.ai: GLM 5.1",
11061
- api: "openai-completions",
11062
- provider: "openrouter",
11063
- baseUrl: "https://openrouter.ai/api/v1",
11064
- reasoning: true,
11065
- input: ["text"],
11066
- cost: {
11067
- input: 0.95,
11068
- output: 3.15,
11069
- cacheRead: 0.475,
11070
- cacheWrite: 0,
11071
- },
11072
- contextWindow: 202752,
11073
- maxTokens: 65535,
11074
- },
11075
- "z-ai/glm-5v-turbo": {
11076
- id: "z-ai/glm-5v-turbo",
11077
- name: "Z.ai: GLM 5V Turbo",
11078
- api: "openai-completions",
11079
- provider: "openrouter",
11080
- baseUrl: "https://openrouter.ai/api/v1",
11081
- reasoning: true,
11082
- input: ["text", "image"],
11083
- cost: {
11084
- input: 1.2,
11085
- output: 4,
11086
- cacheRead: 0.24,
10743
+ input: 0.96,
10744
+ output: 3.1999999999999997,
10745
+ cacheRead: 0.192,
11087
10746
  cacheWrite: 0,
11088
10747
  },
11089
10748
  contextWindow: 202752,
@@ -11110,20 +10769,20 @@ export const MODELS = {
11110
10769
  },
11111
10770
  "alibaba/qwen-3-235b": {
11112
10771
  id: "alibaba/qwen-3-235b",
11113
- name: "Qwen3 235B A22b Instruct 2507",
10772
+ name: "Qwen3-235B-A22B",
11114
10773
  api: "anthropic-messages",
11115
10774
  provider: "vercel-ai-gateway",
11116
10775
  baseUrl: "https://ai-gateway.vercel.sh",
11117
10776
  reasoning: false,
11118
10777
  input: ["text"],
11119
10778
  cost: {
11120
- input: 0.6,
11121
- output: 1.2,
11122
- cacheRead: 0.6,
10779
+ input: 0.071,
10780
+ output: 0.463,
10781
+ cacheRead: 0,
11123
10782
  cacheWrite: 0,
11124
10783
  },
11125
- contextWindow: 131000,
11126
- maxTokens: 40000,
10784
+ contextWindow: 40960,
10785
+ maxTokens: 16384,
11127
10786
  },
11128
10787
  "alibaba/qwen-3-30b": {
11129
10788
  id: "alibaba/qwen-3-30b",
@@ -11151,13 +10810,13 @@ export const MODELS = {
11151
10810
  reasoning: true,
11152
10811
  input: ["text"],
11153
10812
  cost: {
11154
- input: 0.16,
11155
- output: 0.64,
11156
- cacheRead: 0,
10813
+ input: 0.29,
10814
+ output: 0.59,
10815
+ cacheRead: 0.145,
11157
10816
  cacheWrite: 0,
11158
10817
  },
11159
- contextWindow: 128000,
11160
- maxTokens: 8192,
10818
+ contextWindow: 131072,
10819
+ maxTokens: 40960,
11161
10820
  },
11162
10821
  "alibaba/qwen3-235b-a22b-thinking": {
11163
10822
  id: "alibaba/qwen3-235b-a22b-thinking",
@@ -11185,13 +10844,13 @@ export const MODELS = {
11185
10844
  reasoning: false,
11186
10845
  input: ["text"],
11187
10846
  cost: {
11188
- input: 1.5,
11189
- output: 7.5,
11190
- cacheRead: 0.3,
10847
+ input: 0.39999999999999997,
10848
+ output: 1.5999999999999999,
10849
+ cacheRead: 0.022,
11191
10850
  cacheWrite: 0,
11192
10851
  },
11193
10852
  contextWindow: 262144,
11194
- maxTokens: 65536,
10853
+ maxTokens: 66536,
11195
10854
  },
11196
10855
  "alibaba/qwen3-coder-30b-a3b": {
11197
10856
  id: "alibaba/qwen3-coder-30b-a3b",
@@ -11304,13 +10963,13 @@ export const MODELS = {
11304
10963
  reasoning: true,
11305
10964
  input: ["text", "image"],
11306
10965
  cost: {
11307
- input: 0.39999999999999997,
11308
- output: 4,
10966
+ input: 0.22,
10967
+ output: 0.88,
11309
10968
  cacheRead: 0,
11310
10969
  cacheWrite: 0,
11311
10970
  },
11312
- contextWindow: 131072,
11313
- maxTokens: 32768,
10971
+ contextWindow: 256000,
10972
+ maxTokens: 256000,
11314
10973
  },
11315
10974
  "alibaba/qwen3.5-flash": {
11316
10975
  id: "alibaba/qwen3.5-flash",
@@ -11346,23 +11005,6 @@ export const MODELS = {
11346
11005
  contextWindow: 1000000,
11347
11006
  maxTokens: 64000,
11348
11007
  },
11349
- "alibaba/qwen3.6-plus": {
11350
- id: "alibaba/qwen3.6-plus",
11351
- name: "Qwen 3.6 Plus",
11352
- api: "anthropic-messages",
11353
- provider: "vercel-ai-gateway",
11354
- baseUrl: "https://ai-gateway.vercel.sh",
11355
- reasoning: true,
11356
- input: ["text", "image"],
11357
- cost: {
11358
- input: 0.5,
11359
- output: 3,
11360
- cacheRead: 0.09999999999999999,
11361
- cacheWrite: 0,
11362
- },
11363
- contextWindow: 1000000,
11364
- maxTokens: 64000,
11365
- },
11366
11008
  "anthropic/claude-3-haiku": {
11367
11009
  id: "anthropic/claude-3-haiku",
11368
11010
  name: "Claude 3 Haiku",
@@ -11397,6 +11039,40 @@ export const MODELS = {
11397
11039
  contextWindow: 200000,
11398
11040
  maxTokens: 8192,
11399
11041
  },
11042
+ "anthropic/claude-3.5-sonnet": {
11043
+ id: "anthropic/claude-3.5-sonnet",
11044
+ name: "Claude 3.5 Sonnet",
11045
+ api: "anthropic-messages",
11046
+ provider: "vercel-ai-gateway",
11047
+ baseUrl: "https://ai-gateway.vercel.sh",
11048
+ reasoning: false,
11049
+ input: ["text", "image"],
11050
+ cost: {
11051
+ input: 3,
11052
+ output: 15,
11053
+ cacheRead: 0.3,
11054
+ cacheWrite: 3.75,
11055
+ },
11056
+ contextWindow: 200000,
11057
+ maxTokens: 8192,
11058
+ },
11059
+ "anthropic/claude-3.5-sonnet-20240620": {
11060
+ id: "anthropic/claude-3.5-sonnet-20240620",
11061
+ name: "Claude 3.5 Sonnet (2024-06-20)",
11062
+ api: "anthropic-messages",
11063
+ provider: "vercel-ai-gateway",
11064
+ baseUrl: "https://ai-gateway.vercel.sh",
11065
+ reasoning: false,
11066
+ input: ["text", "image"],
11067
+ cost: {
11068
+ input: 3,
11069
+ output: 15,
11070
+ cacheRead: 0.3,
11071
+ cacheWrite: 3.75,
11072
+ },
11073
+ contextWindow: 200000,
11074
+ maxTokens: 8192,
11075
+ },
11400
11076
  "anthropic/claude-3.7-sonnet": {
11401
11077
  id: "anthropic/claude-3.7-sonnet",
11402
11078
  name: "Claude 3.7 Sonnet",
@@ -11567,23 +11243,6 @@ export const MODELS = {
11567
11243
  contextWindow: 131000,
11568
11244
  maxTokens: 131000,
11569
11245
  },
11570
- "arcee-ai/trinity-large-thinking": {
11571
- id: "arcee-ai/trinity-large-thinking",
11572
- name: "Trinity Large Thinking",
11573
- api: "anthropic-messages",
11574
- provider: "vercel-ai-gateway",
11575
- baseUrl: "https://ai-gateway.vercel.sh",
11576
- reasoning: true,
11577
- input: ["text"],
11578
- cost: {
11579
- input: 0.25,
11580
- output: 0.8999999999999999,
11581
- cacheRead: 0,
11582
- cacheWrite: 0,
11583
- },
11584
- contextWindow: 262100,
11585
- maxTokens: 80000,
11586
- },
11587
11246
  "bytedance/seed-1.6": {
11588
11247
  id: "bytedance/seed-1.6",
11589
11248
  name: "Seed 1.6",
@@ -11661,13 +11320,13 @@ export const MODELS = {
11661
11320
  reasoning: true,
11662
11321
  input: ["text"],
11663
11322
  cost: {
11664
- input: 0.56,
11665
- output: 1.68,
11666
- cacheRead: 0.28,
11323
+ input: 0.5,
11324
+ output: 1.5,
11325
+ cacheRead: 0,
11667
11326
  cacheWrite: 0,
11668
11327
  },
11669
11328
  contextWindow: 163840,
11670
- maxTokens: 8192,
11329
+ maxTokens: 16384,
11671
11330
  },
11672
11331
  "deepseek/deepseek-v3.1-terminus": {
11673
11332
  id: "deepseek/deepseek-v3.1-terminus",
@@ -11850,7 +11509,7 @@ export const MODELS = {
11850
11509
  cost: {
11851
11510
  input: 0.25,
11852
11511
  output: 1.5,
11853
- cacheRead: 0.03,
11512
+ cacheRead: 0,
11854
11513
  cacheWrite: 0,
11855
11514
  },
11856
11515
  contextWindow: 1000000,
@@ -11873,40 +11532,6 @@ export const MODELS = {
11873
11532
  contextWindow: 1000000,
11874
11533
  maxTokens: 64000,
11875
11534
  },
11876
- "google/gemma-4-26b-a4b-it": {
11877
- id: "google/gemma-4-26b-a4b-it",
11878
- name: "Gemma 4 26B A4B IT",
11879
- api: "anthropic-messages",
11880
- provider: "vercel-ai-gateway",
11881
- baseUrl: "https://ai-gateway.vercel.sh",
11882
- reasoning: false,
11883
- input: ["text", "image"],
11884
- cost: {
11885
- input: 0.13,
11886
- output: 0.39999999999999997,
11887
- cacheRead: 0,
11888
- cacheWrite: 0,
11889
- },
11890
- contextWindow: 262144,
11891
- maxTokens: 131072,
11892
- },
11893
- "google/gemma-4-31b-it": {
11894
- id: "google/gemma-4-31b-it",
11895
- name: "Gemma 4 31B IT",
11896
- api: "anthropic-messages",
11897
- provider: "vercel-ai-gateway",
11898
- baseUrl: "https://ai-gateway.vercel.sh",
11899
- reasoning: false,
11900
- input: ["text", "image"],
11901
- cost: {
11902
- input: 0.14,
11903
- output: 0.39999999999999997,
11904
- cacheRead: 0,
11905
- cacheWrite: 0,
11906
- },
11907
- contextWindow: 262144,
11908
- maxTokens: 131072,
11909
- },
11910
11535
  "inception/mercury-2": {
11911
11536
  id: "inception/mercury-2",
11912
11537
  name: "Mercury 2",
@@ -11941,39 +11566,39 @@ export const MODELS = {
11941
11566
  contextWindow: 32000,
11942
11567
  maxTokens: 16384,
11943
11568
  },
11944
- "kwaipilot/kat-coder-pro-v2": {
11945
- id: "kwaipilot/kat-coder-pro-v2",
11946
- name: "Kat Coder Pro V2",
11569
+ "meituan/longcat-flash-chat": {
11570
+ id: "meituan/longcat-flash-chat",
11571
+ name: "LongCat Flash Chat",
11947
11572
  api: "anthropic-messages",
11948
11573
  provider: "vercel-ai-gateway",
11949
11574
  baseUrl: "https://ai-gateway.vercel.sh",
11950
- reasoning: true,
11575
+ reasoning: false,
11951
11576
  input: ["text"],
11952
11577
  cost: {
11953
- input: 0.3,
11954
- output: 1.2,
11955
- cacheRead: 0.06,
11578
+ input: 0,
11579
+ output: 0,
11580
+ cacheRead: 0,
11956
11581
  cacheWrite: 0,
11957
11582
  },
11958
- contextWindow: 256000,
11959
- maxTokens: 256000,
11583
+ contextWindow: 128000,
11584
+ maxTokens: 100000,
11960
11585
  },
11961
- "meituan/longcat-flash-chat": {
11962
- id: "meituan/longcat-flash-chat",
11963
- name: "LongCat Flash Chat",
11586
+ "meituan/longcat-flash-thinking": {
11587
+ id: "meituan/longcat-flash-thinking",
11588
+ name: "LongCat Flash Thinking",
11964
11589
  api: "anthropic-messages",
11965
11590
  provider: "vercel-ai-gateway",
11966
11591
  baseUrl: "https://ai-gateway.vercel.sh",
11967
- reasoning: false,
11592
+ reasoning: true,
11968
11593
  input: ["text"],
11969
11594
  cost: {
11970
- input: 0,
11971
- output: 0,
11595
+ input: 0.15,
11596
+ output: 1.5,
11972
11597
  cacheRead: 0,
11973
11598
  cacheWrite: 0,
11974
11599
  },
11975
11600
  contextWindow: 128000,
11976
- maxTokens: 100000,
11601
+ maxTokens: 8192,
11977
11602
  },
11978
11603
  "meta/llama-3.1-70b": {
11979
11604
  id: "meta/llama-3.1-70b",
@@ -12001,13 +11626,13 @@ export const MODELS = {
12001
11626
  reasoning: false,
12002
11627
  input: ["text"],
12003
11628
  cost: {
12004
- input: 0.22,
12005
- output: 0.22,
12006
- cacheRead: 0,
11629
+ input: 0.09999999999999999,
11630
+ output: 0.09999999999999999,
11631
+ cacheRead: 0.09999999999999999,
12007
11632
  cacheWrite: 0,
12008
11633
  },
12009
11634
  contextWindow: 128000,
12010
- maxTokens: 8192,
11635
+ maxTokens: 16384,
12011
11636
  },
12012
11637
  "meta/llama-3.2-11b": {
12013
11638
  id: "meta/llama-3.2-11b",
@@ -12385,20 +12010,20 @@ export const MODELS = {
12385
12010
  },
12386
12011
  "moonshotai/kimi-k2": {
12387
12012
  id: "moonshotai/kimi-k2",
12388
- name: "Kimi K2 Instruct",
12013
+ name: "Kimi K2",
12389
12014
  api: "anthropic-messages",
12390
12015
  provider: "vercel-ai-gateway",
12391
12016
  baseUrl: "https://ai-gateway.vercel.sh",
12392
12017
  reasoning: false,
12393
12018
  input: ["text"],
12394
12019
  cost: {
12395
- input: 0.5700000000000001,
12396
- output: 2.3,
12397
- cacheRead: 0,
12020
+ input: 0.6,
12021
+ output: 2.5,
12022
+ cacheRead: 0.15,
12398
12023
  cacheWrite: 0,
12399
12024
  },
12400
12025
  contextWindow: 131072,
12401
- maxTokens: 131072,
12026
+ maxTokens: 16384,
12402
12027
  },
12403
12028
  "moonshotai/kimi-k2-0905": {
12404
12029
  id: "moonshotai/kimi-k2-0905",
@@ -12411,11 +12036,11 @@ export const MODELS = {
12411
12036
  cost: {
12412
12037
  input: 0.6,
12413
12038
  output: 2.5,
12414
- cacheRead: 0.3,
12039
+ cacheRead: 0.15,
12415
12040
  cacheWrite: 0,
12416
12041
  },
12417
12042
  contextWindow: 256000,
12418
- maxTokens: 128000,
12043
+ maxTokens: 16384,
12419
12044
  },
12420
12045
  "moonshotai/kimi-k2-thinking": {
12421
12046
  id: "moonshotai/kimi-k2-thinking",
@@ -12987,12 +12612,12 @@ export const MODELS = {
12987
12612
  reasoning: true,
12988
12613
  input: ["text"],
12989
12614
  cost: {
12990
- input: 0.049999999999999996,
12991
- output: 0.19999999999999998,
12615
+ input: 0.07,
12616
+ output: 0.3,
12992
12617
  cacheRead: 0,
12993
12618
  cacheWrite: 0,
12994
12619
  },
12995
- contextWindow: 131072,
12620
+ contextWindow: 128000,
12996
12621
  maxTokens: 8192,
12997
12622
  },
12998
12623
  "openai/gpt-oss-safeguard-20b": {
@@ -13123,8 +12748,8 @@ export const MODELS = {
13123
12748
  reasoning: false,
13124
12749
  input: ["text", "image"],
13125
12750
  cost: {
13126
- input: 0,
13127
- output: 0,
12751
+ input: 1,
12752
+ output: 1,
13128
12753
  cacheRead: 0,
13129
12754
  cacheWrite: 0,
13130
12755
  },
@@ -13140,8 +12765,8 @@ export const MODELS = {
13140
12765
  reasoning: false,
13141
12766
  input: ["text", "image"],
13142
12767
  cost: {
13143
- input: 0,
13144
- output: 0,
12768
+ input: 3,
12769
+ output: 15,
13145
12770
  cacheRead: 0,
13146
12771
  cacheWrite: 0,
13147
12772
  },
@@ -13165,6 +12790,23 @@ export const MODELS = {
13165
12790
  contextWindow: 131072,
13166
12791
  maxTokens: 131072,
13167
12792
  },
12793
+ "xai/grok-2-vision": {
12794
+ id: "xai/grok-2-vision",
12795
+ name: "Grok 2 Vision",
12796
+ api: "anthropic-messages",
12797
+ provider: "vercel-ai-gateway",
12798
+ baseUrl: "https://ai-gateway.vercel.sh",
12799
+ reasoning: false,
12800
+ input: ["text", "image"],
12801
+ cost: {
12802
+ input: 2,
12803
+ output: 10,
12804
+ cacheRead: 0,
12805
+ cacheWrite: 0,
12806
+ },
12807
+ contextWindow: 32768,
12808
+ maxTokens: 32768,
12809
+ },
13168
12810
  "xai/grok-3": {
13169
12811
  id: "xai/grok-3",
13170
12812
  name: "Grok 3 Beta",
@@ -13318,23 +12960,6 @@ export const MODELS = {
13318
12960
  contextWindow: 2000000,
13319
12961
  maxTokens: 30000,
13320
12962
  },
13321
- "xai/grok-4.20-multi-agent": {
13322
- id: "xai/grok-4.20-multi-agent",
13323
- name: "Grok 4.20 Multi-Agent",
13324
- api: "anthropic-messages",
13325
- provider: "vercel-ai-gateway",
13326
- baseUrl: "https://ai-gateway.vercel.sh",
13327
- reasoning: true,
13328
- input: ["text"],
13329
- cost: {
13330
- input: 2,
13331
- output: 6,
13332
- cacheRead: 0.19999999999999998,
13333
- cacheWrite: 0,
13334
- },
13335
- contextWindow: 2000000,
13336
- maxTokens: 2000000,
13337
- },
13338
12963
  "xai/grok-4.20-multi-agent-beta": {
13339
12964
  id: "xai/grok-4.20-multi-agent-beta",
13340
12965
  name: "Grok 4.20 Multi Agent Beta",
@@ -13352,23 +12977,6 @@ export const MODELS = {
13352
12977
  contextWindow: 2000000,
13353
12978
  maxTokens: 2000000,
13354
12979
  },
13355
- "xai/grok-4.20-non-reasoning": {
13356
- id: "xai/grok-4.20-non-reasoning",
13357
- name: "Grok 4.20 Non-Reasoning",
13358
- api: "anthropic-messages",
13359
- provider: "vercel-ai-gateway",
13360
- baseUrl: "https://ai-gateway.vercel.sh",
13361
- reasoning: false,
13362
- input: ["text", "image"],
13363
- cost: {
13364
- input: 2,
13365
- output: 6,
13366
- cacheRead: 0.19999999999999998,
13367
- cacheWrite: 0,
13368
- },
13369
- contextWindow: 2000000,
13370
- maxTokens: 2000000,
13371
- },
13372
12980
  "xai/grok-4.20-non-reasoning-beta": {
13373
12981
  id: "xai/grok-4.20-non-reasoning-beta",
13374
12982
  name: "Grok 4.20 Beta Non-Reasoning",
@@ -13386,23 +12994,6 @@ export const MODELS = {
13386
12994
  contextWindow: 2000000,
13387
12995
  maxTokens: 2000000,
13388
12996
  },
13389
- "xai/grok-4.20-reasoning": {
13390
- id: "xai/grok-4.20-reasoning",
13391
- name: "Grok 4.20 Reasoning",
13392
- api: "anthropic-messages",
13393
- provider: "vercel-ai-gateway",
13394
- baseUrl: "https://ai-gateway.vercel.sh",
13395
- reasoning: true,
13396
- input: ["text", "image"],
13397
- cost: {
13398
- input: 2,
13399
- output: 6,
13400
- cacheRead: 0.19999999999999998,
13401
- cacheWrite: 0,
13402
- },
13403
- contextWindow: 2000000,
13404
- maxTokens: 2000000,
13405
- },
13406
12997
  "xai/grok-4.20-reasoning-beta": {
13407
12998
  id: "xai/grok-4.20-reasoning-beta",
13408
12999
  name: "Grok 4.20 Beta Reasoning",
@@ -13446,9 +13037,9 @@ export const MODELS = {
13446
13037
  reasoning: true,
13447
13038
  input: ["text"],
13448
13039
  cost: {
13449
- input: 0.09,
13450
- output: 0.29,
13451
- cacheRead: 0.045,
13040
+ input: 0.09999999999999999,
13041
+ output: 0.3,
13042
+ cacheRead: 0.02,
13452
13043
  cacheWrite: 0,
13453
13044
  },
13454
13045
  contextWindow: 262144,
@@ -13582,13 +13173,13 @@ export const MODELS = {
13582
13173
  reasoning: true,
13583
13174
  input: ["text"],
13584
13175
  cost: {
13585
- input: 2.25,
13586
- output: 2.75,
13587
- cacheRead: 2.25,
13176
+ input: 0.6,
13177
+ output: 2.2,
13178
+ cacheRead: 0,
13588
13179
  cacheWrite: 0,
13589
13180
  },
13590
- contextWindow: 131000,
13591
- maxTokens: 40000,
13181
+ contextWindow: 200000,
13182
+ maxTokens: 120000,
13592
13183
  },
13593
13184
  "zai/glm-4.7-flash": {
13594
13185
  id: "zai/glm-4.7-flash",
@@ -13658,40 +13249,6 @@ export const MODELS = {
13658
13249
  contextWindow: 202800,
13659
13250
  maxTokens: 131100,
13660
13251
  },
13661
- "zai/glm-5.1": {
13662
- id: "zai/glm-5.1",
13663
- name: "GLM 5.1",
13664
- api: "anthropic-messages",
13665
- provider: "vercel-ai-gateway",
13666
- baseUrl: "https://ai-gateway.vercel.sh",
13667
- reasoning: true,
13668
- input: ["text"],
13669
- cost: {
13670
- input: 1.4,
13671
- output: 4.4,
13672
- cacheRead: 0.26,
13673
- cacheWrite: 0,
13674
- },
13675
- contextWindow: 202800,
13676
- maxTokens: 64000,
13677
- },
13678
- "zai/glm-5v-turbo": {
13679
- id: "zai/glm-5v-turbo",
13680
- name: "GLM 5V Turbo",
13681
- api: "anthropic-messages",
13682
- provider: "vercel-ai-gateway",
13683
- baseUrl: "https://ai-gateway.vercel.sh",
13684
- reasoning: true,
13685
- input: ["text", "image"],
13686
- cost: {
13687
- input: 1.2,
13688
- output: 4,
13689
- cacheRead: 0.24,
13690
- cacheWrite: 0,
13691
- },
13692
- contextWindow: 200000,
13693
- maxTokens: 128000,
13694
- },
13695
13252
  },
13696
13253
  "xai": {
13697
13254
  "grok-2": {
@@ -14248,24 +13805,6 @@ export const MODELS = {
14248
13805
  contextWindow: 200000,
14249
13806
  maxTokens: 131072,
14250
13807
  },
14251
- "glm-4.7-flashx": {
14252
- id: "glm-4.7-flashx",
14253
- name: "GLM-4.7-FlashX",
14254
- api: "openai-completions",
14255
- provider: "zai",
14256
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14257
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
14258
- reasoning: true,
14259
- input: ["text"],
14260
- cost: {
14261
- input: 0.07,
14262
- output: 0.4,
14263
- cacheRead: 0.01,
14264
- cacheWrite: 0,
14265
- },
14266
- contextWindow: 200000,
14267
- maxTokens: 131072,
14268
- },
14269
13808
  "glm-5": {
14270
13809
  id: "glm-5",
14271
13810
  name: "GLM-5",
@@ -14302,42 +13841,6 @@ export const MODELS = {
14302
13841
  contextWindow: 200000,
14303
13842
  maxTokens: 131072,
14304
13843
  },
14305
- "glm-5.1": {
14306
- id: "glm-5.1",
14307
- name: "GLM-5.1",
14308
- api: "openai-completions",
14309
- provider: "zai",
14310
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14311
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
14312
- reasoning: true,
14313
- input: ["text"],
14314
- cost: {
14315
- input: 1.4,
14316
- output: 4.4,
14317
- cacheRead: 0.26,
14318
- cacheWrite: 0,
14319
- },
14320
- contextWindow: 200000,
14321
- maxTokens: 131072,
14322
- },
14323
- "glm-5v-turbo": {
14324
- id: "glm-5v-turbo",
14325
- name: "glm-5v-turbo",
14326
- api: "openai-completions",
14327
- provider: "zai",
14328
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
14329
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
14330
- reasoning: true,
14331
- input: ["text", "image"],
14332
- cost: {
14333
- input: 1.2,
14334
- output: 4,
14335
- cacheRead: 0.24,
14336
- cacheWrite: 0,
14337
- },
14338
- contextWindow: 200000,
14339
- maxTokens: 131072,
14340
- },
14341
13844
  },
14342
13845
  };
14343
13846
  //# sourceMappingURL=models.generated.js.map