@asm-agent/coding-agent 0.8.5 → 0.8.7

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 (62) hide show
  1. package/CHANGELOG.md +8 -0
  2. package/dist/bundle/{anthropic-BS3XM5BT.js → anthropic-XSMQHGYB.js} +1 -1
  3. package/dist/bundle/{azure-openai-responses-IENK6KME.js → azure-openai-responses-XLQAIKKH.js} +2 -2
  4. package/dist/bundle/{bundled-modules-VBE3REQM.js → bundled-modules-5OCN73BM.js} +4 -4
  5. package/dist/bundle/{chunk-D55J7N6R.js → chunk-2LPSALBF.js} +377 -299
  6. package/dist/bundle/{chunk-J6ATXG62.js → chunk-CMMSLBAW.js} +12 -8
  7. package/dist/bundle/{chunk-D5ZUG2IX.js → chunk-E3YE2Q7A.js} +66 -3
  8. package/dist/bundle/{chunk-KC3DQ3DI.js → chunk-IAQLPSMN.js} +609 -222
  9. package/dist/bundle/{chunk-G73LOLKD.js → chunk-YPNK4MRU.js} +1 -1
  10. package/dist/bundle/{cli-main-JCK7QTSE.js → cli-main-QYX5R3LF.js} +4 -4
  11. package/dist/bundle/cli.js +1 -1
  12. package/dist/bundle/{compile-UQNZ2TRI.js → compile-BYYUFOG3.js} +1 -1
  13. package/dist/bundle/{google-L6GUE5MM.js → google-ZXJEPWJA.js} +1 -1
  14. package/dist/bundle/{google-vertex-ALYRXEBH.js → google-vertex-WAF3RIJ6.js} +1 -1
  15. package/dist/bundle/{main-OA5G7OQN.js → main-EOUAQCJH.js} +4 -4
  16. package/dist/bundle/{mistral-NTC6RHCF.js → mistral-GDZXSXRS.js} +1 -1
  17. package/dist/bundle/{openai-codex-responses-FKZNCKA3.js → openai-codex-responses-7XMPW4LG.js} +2 -2
  18. package/dist/bundle/{openai-completions-LQJM5PDC.js → openai-completions-LNSVGDMF.js} +4 -1
  19. package/dist/bundle/{openai-responses-AHIOFAPZ.js → openai-responses-MFZOBMIT.js} +2 -2
  20. package/dist/core/always-applied-skills.d.ts +3 -0
  21. package/dist/core/always-applied-skills.d.ts.map +1 -0
  22. package/dist/core/always-applied-skills.js +47 -0
  23. package/dist/core/always-applied-skills.js.map +1 -0
  24. package/dist/core/model-registry.d.ts.map +1 -1
  25. package/dist/core/model-registry.js +8 -0
  26. package/dist/core/model-registry.js.map +1 -1
  27. package/dist/core/ollama-models.d.ts +4 -0
  28. package/dist/core/ollama-models.d.ts.map +1 -0
  29. package/dist/core/ollama-models.js +56 -0
  30. package/dist/core/ollama-models.js.map +1 -0
  31. package/dist/core/provider-display-names.d.ts.map +1 -1
  32. package/dist/core/provider-display-names.js +1 -0
  33. package/dist/core/provider-display-names.js.map +1 -1
  34. package/dist/core/system-prompt.d.ts.map +1 -1
  35. package/dist/core/system-prompt.js +9 -0
  36. package/dist/core/system-prompt.js.map +1 -1
  37. package/dist/skills/final-response-summary/SKILL.md +39 -0
  38. package/dist/skills/request-report/SKILL.md +65 -0
  39. package/dist/skills/request-report/pyproject.toml +16 -0
  40. package/dist/skills/request-report/src/request_report/__init__.py +160 -0
  41. package/dist/skills/skill-creator/SKILL.md +2 -1
  42. package/dist/skills/solid-source-modularity/SKILL.md +48 -0
  43. package/dist/skills/solid-source-modularity/pyproject.toml +16 -0
  44. package/dist/skills/solid-source-modularity/src/solid_source_modularity/__init__.py +154 -0
  45. package/docs/models.md +2 -0
  46. package/docs/skills.md +8 -3
  47. package/examples/extensions/custom-provider-anthropic/package-lock.json +2 -2
  48. package/examples/extensions/custom-provider-anthropic/package.json +1 -1
  49. package/examples/extensions/custom-provider-gitlab-duo/package.json +1 -1
  50. package/examples/extensions/sandbox/package-lock.json +2 -2
  51. package/examples/extensions/sandbox/package.json +1 -1
  52. package/examples/extensions/with-deps/package-lock.json +2 -2
  53. package/examples/extensions/with-deps/package.json +1 -1
  54. package/package.json +5 -5
  55. package/skills/final-response-summary/SKILL.md +39 -0
  56. package/skills/request-report/SKILL.md +65 -0
  57. package/skills/request-report/pyproject.toml +16 -0
  58. package/skills/request-report/src/request_report/__init__.py +160 -0
  59. package/skills/skill-creator/SKILL.md +2 -1
  60. package/skills/solid-source-modularity/SKILL.md +48 -0
  61. package/skills/solid-source-modularity/pyproject.toml +16 -0
  62. package/skills/solid-source-modularity/src/solid_source_modularity/__init__.py +154 -0
@@ -89,6 +89,24 @@ var MODELS = {
89
89
  contextWindow: 1e6,
90
90
  maxTokens: 128e3
91
91
  },
92
+ "anthropic.claude-fable-5-1": {
93
+ id: "anthropic.claude-fable-5-1",
94
+ name: "Claude Fable 5.1",
95
+ api: "bedrock-converse-stream",
96
+ provider: "amazon-bedrock",
97
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
98
+ reasoning: true,
99
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
100
+ input: ["text", "image"],
101
+ cost: {
102
+ input: 10,
103
+ output: 50,
104
+ cacheRead: 0.25,
105
+ cacheWrite: 12.5
106
+ },
107
+ contextWindow: 1e6,
108
+ maxTokens: 128e3
109
+ },
92
110
  "anthropic.claude-haiku-4-5-20251001-v1:0": {
93
111
  id: "anthropic.claude-haiku-4-5-20251001-v1:0",
94
112
  name: "Claude Haiku 4.5",
@@ -635,6 +653,24 @@ var MODELS = {
635
653
  contextWindow: 1e6,
636
654
  maxTokens: 128e3
637
655
  },
656
+ "global.anthropic.claude-fable-5-1": {
657
+ id: "global.anthropic.claude-fable-5-1",
658
+ name: "Claude Fable 5.1 (Global)",
659
+ api: "bedrock-converse-stream",
660
+ provider: "amazon-bedrock",
661
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
662
+ reasoning: true,
663
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
664
+ input: ["text", "image"],
665
+ cost: {
666
+ input: 10,
667
+ output: 50,
668
+ cacheRead: 0.25,
669
+ cacheWrite: 12.5
670
+ },
671
+ contextWindow: 1e6,
672
+ maxTokens: 128e3
673
+ },
638
674
  "global.anthropic.claude-haiku-4-5-20251001-v1:0": {
639
675
  id: "global.anthropic.claude-haiku-4-5-20251001-v1:0",
640
676
  name: "Claude Haiku 4.5 (Global)",
@@ -1726,6 +1762,24 @@ var MODELS = {
1726
1762
  contextWindow: 1e6,
1727
1763
  maxTokens: 128e3
1728
1764
  },
1765
+ "us.anthropic.claude-fable-5-1": {
1766
+ id: "us.anthropic.claude-fable-5-1",
1767
+ name: "Claude Fable 5.1 (US)",
1768
+ api: "bedrock-converse-stream",
1769
+ provider: "amazon-bedrock",
1770
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1771
+ reasoning: true,
1772
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
1773
+ input: ["text", "image"],
1774
+ cost: {
1775
+ input: 11,
1776
+ output: 55,
1777
+ cacheRead: 0.275,
1778
+ cacheWrite: 13.75
1779
+ },
1780
+ contextWindow: 1e6,
1781
+ maxTokens: 128e3
1782
+ },
1729
1783
  "us.anthropic.claude-haiku-4-5-20251001-v1:0": {
1730
1784
  id: "us.anthropic.claude-haiku-4-5-20251001-v1:0",
1731
1785
  name: "Claude Haiku 4.5 (US)",
@@ -2092,6 +2146,24 @@ var MODELS = {
2092
2146
  contextWindow: 1e6,
2093
2147
  maxTokens: 128e3
2094
2148
  },
2149
+ "claude-fable-5-1": {
2150
+ id: "claude-fable-5-1",
2151
+ name: "Claude Fable 5.1",
2152
+ api: "anthropic-messages",
2153
+ provider: "anthropic",
2154
+ baseUrl: "https://api.anthropic.com",
2155
+ reasoning: true,
2156
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
2157
+ input: ["text", "image"],
2158
+ cost: {
2159
+ input: 10,
2160
+ output: 50,
2161
+ cacheRead: 0.25,
2162
+ cacheWrite: 12.5
2163
+ },
2164
+ contextWindow: 1e6,
2165
+ maxTokens: 128e3
2166
+ },
2095
2167
  "claude-haiku-4-5": {
2096
2168
  id: "claude-haiku-4-5",
2097
2169
  name: "Claude Haiku 4.5 (latest)",
@@ -3936,7 +4008,7 @@ var MODELS = {
3936
4008
  cacheWrite: 0
3937
4009
  },
3938
4010
  contextWindow: 1310720,
3939
- maxTokens: 1310720
4011
+ maxTokens: 1048576
3940
4012
  }
3941
4013
  },
3942
4014
  "deepseek": {
@@ -3989,9 +4061,26 @@ var MODELS = {
3989
4061
  reasoning: true,
3990
4062
  input: ["text"],
3991
4063
  cost: {
3992
- input: 0.14,
3993
- output: 0.28,
3994
- cacheRead: 0.028,
4064
+ input: 0.22,
4065
+ output: 0.66,
4066
+ cacheRead: 7e-3,
4067
+ cacheWrite: 0
4068
+ },
4069
+ contextWindow: 1e6,
4070
+ maxTokens: 384e3
4071
+ },
4072
+ "accounts/fireworks/models/deepseek-v4-flash-vision-exp": {
4073
+ id: "accounts/fireworks/models/deepseek-v4-flash-vision-exp",
4074
+ name: "DeepSeek V4 Flash Vision Exp",
4075
+ api: "anthropic-messages",
4076
+ provider: "fireworks",
4077
+ baseUrl: "https://api.fireworks.ai/inference",
4078
+ reasoning: true,
4079
+ input: ["text", "image"],
4080
+ cost: {
4081
+ input: 0.22,
4082
+ output: 0.66,
4083
+ cacheRead: 7e-3,
3995
4084
  cacheWrite: 0
3996
4085
  },
3997
4086
  contextWindow: 1e6,
@@ -4048,6 +4137,23 @@ var MODELS = {
4048
4137
  contextWindow: 1e6,
4049
4138
  maxTokens: 131072
4050
4139
  },
4140
+ "accounts/fireworks/models/glm-5p3-flash": {
4141
+ id: "accounts/fireworks/models/glm-5p3-flash",
4142
+ name: "GLM 5.3 Flash",
4143
+ api: "anthropic-messages",
4144
+ provider: "fireworks",
4145
+ baseUrl: "https://api.fireworks.ai/inference",
4146
+ reasoning: true,
4147
+ input: ["text", "image"],
4148
+ cost: {
4149
+ input: 0.15,
4150
+ output: 0.5,
4151
+ cacheRead: 0.03,
4152
+ cacheWrite: 0
4153
+ },
4154
+ contextWindow: 1e6,
4155
+ maxTokens: 131072
4156
+ },
4051
4157
  "accounts/fireworks/models/gpt-oss-120b": {
4052
4158
  id: "accounts/fireworks/models/gpt-oss-120b",
4053
4159
  name: "GPT OSS 120B",
@@ -5115,13 +5221,14 @@ var MODELS = {
5115
5221
  contextWindow: 1048576,
5116
5222
  maxTokens: 65536
5117
5223
  },
5118
- "gemini-flash-latest": {
5119
- id: "gemini-flash-latest",
5120
- name: "Gemini Flash Latest",
5224
+ "gemini-3.8-flash": {
5225
+ id: "gemini-3.8-flash",
5226
+ name: "Gemini 3.8 Flash",
5121
5227
  api: "google-generative-ai",
5122
5228
  provider: "google",
5123
5229
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
5124
5230
  reasoning: true,
5231
+ thinkingLevelMap: { "off": null },
5125
5232
  input: ["text", "image"],
5126
5233
  cost: {
5127
5234
  input: 0.75,
@@ -5132,38 +5239,38 @@ var MODELS = {
5132
5239
  contextWindow: 1048576,
5133
5240
  maxTokens: 65536
5134
5241
  },
5135
- "gemini-flash-lite-latest": {
5136
- id: "gemini-flash-lite-latest",
5137
- name: "Gemini Flash-Lite Latest",
5242
+ "gemini-flash-latest": {
5243
+ id: "gemini-flash-latest",
5244
+ name: "Gemini Flash Latest",
5138
5245
  api: "google-generative-ai",
5139
5246
  provider: "google",
5140
5247
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
5141
5248
  reasoning: true,
5142
5249
  input: ["text", "image"],
5143
5250
  cost: {
5144
- input: 0.3,
5145
- output: 2.5,
5146
- cacheRead: 0.03,
5251
+ input: 0.75,
5252
+ output: 3.75,
5253
+ cacheRead: 0.075,
5147
5254
  cacheWrite: 0
5148
5255
  },
5149
5256
  contextWindow: 1048576,
5150
5257
  maxTokens: 65536
5151
5258
  },
5152
- "gemini-robotics-er-1.6-preview": {
5153
- id: "gemini-robotics-er-1.6-preview",
5154
- name: "Gemini Robotics-ER 1.6 Preview",
5259
+ "gemini-flash-lite-latest": {
5260
+ id: "gemini-flash-lite-latest",
5261
+ name: "Gemini Flash-Lite Latest",
5155
5262
  api: "google-generative-ai",
5156
5263
  provider: "google",
5157
5264
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
5158
5265
  reasoning: true,
5159
5266
  input: ["text", "image"],
5160
5267
  cost: {
5161
- input: 1,
5162
- output: 5,
5163
- cacheRead: 0,
5268
+ input: 0.3,
5269
+ output: 2.5,
5270
+ cacheRead: 0.03,
5164
5271
  cacheWrite: 0
5165
5272
  },
5166
- contextWindow: 131072,
5273
+ contextWindow: 1048576,
5167
5274
  maxTokens: 65536
5168
5275
  },
5169
5276
  "gemma-4-26b-a4b-it": {
@@ -5532,6 +5639,23 @@ var MODELS = {
5532
5639
  },
5533
5640
  contextWindow: 131072,
5534
5641
  maxTokens: 16384
5642
+ },
5643
+ "qwen/qwen3.8-27b": {
5644
+ id: "qwen/qwen3.8-27b",
5645
+ name: "Qwen3.8 27B",
5646
+ api: "openai-completions",
5647
+ provider: "groq",
5648
+ baseUrl: "https://api.groq.com/openai/v1",
5649
+ reasoning: true,
5650
+ input: ["text", "image"],
5651
+ cost: {
5652
+ input: 0.8,
5653
+ output: 4,
5654
+ cacheRead: 0,
5655
+ cacheWrite: 0
5656
+ },
5657
+ contextWindow: 131042,
5658
+ maxTokens: 16384
5535
5659
  }
5536
5660
  },
5537
5661
  "huggingface": {
@@ -6219,6 +6343,24 @@ var MODELS = {
6219
6343
  contextWindow: 1048576,
6220
6344
  maxTokens: 384e3
6221
6345
  },
6346
+ "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp": {
6347
+ id: "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp",
6348
+ name: "DeepSeek V4 Flash Vision Exp",
6349
+ api: "openai-completions",
6350
+ provider: "huggingface",
6351
+ baseUrl: "https://router.huggingface.co/v1",
6352
+ compat: { "supportsDeveloperRole": false },
6353
+ reasoning: true,
6354
+ input: ["text", "image"],
6355
+ cost: {
6356
+ input: 0.44,
6357
+ output: 1.32,
6358
+ cacheRead: 0,
6359
+ cacheWrite: 0
6360
+ },
6361
+ contextWindow: 1048576,
6362
+ maxTokens: 384e3
6363
+ },
6222
6364
  "deepseek-ai/DeepSeek-V4-Pro": {
6223
6365
  id: "deepseek-ai/DeepSeek-V4-Pro",
6224
6366
  name: "DeepSeek V4 Pro",
@@ -6542,7 +6684,7 @@ var MODELS = {
6542
6684
  cacheWrite: 0
6543
6685
  },
6544
6686
  contextWindow: 262144,
6545
- maxTokens: 64e3
6687
+ maxTokens: 128e3
6546
6688
  },
6547
6689
  "thinkingmachines/Inkling": {
6548
6690
  id: "thinkingmachines/Inkling",
@@ -8850,6 +8992,24 @@ var MODELS = {
8850
8992
  contextWindow: 1e6,
8851
8993
  maxTokens: 128e3
8852
8994
  },
8995
+ "claude-fable-5-1": {
8996
+ id: "claude-fable-5-1",
8997
+ name: "Claude Fable 5.1",
8998
+ api: "anthropic-messages",
8999
+ provider: "opencode",
9000
+ baseUrl: "https://opencode.ai/zen",
9001
+ reasoning: true,
9002
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
9003
+ input: ["text", "image"],
9004
+ cost: {
9005
+ input: 10,
9006
+ output: 50,
9007
+ cacheRead: 0.25,
9008
+ cacheWrite: 12.5
9009
+ },
9010
+ contextWindow: 1e6,
9011
+ maxTokens: 128e3
9012
+ },
8853
9013
  "claude-haiku-4-5": {
8854
9014
  id: "claude-haiku-4-5",
8855
9015
  name: "Claude Haiku 4.5",
@@ -9172,6 +9332,24 @@ var MODELS = {
9172
9332
  contextWindow: 1048576,
9173
9333
  maxTokens: 65536
9174
9334
  },
9335
+ "gemini-3.8-flash": {
9336
+ id: "gemini-3.8-flash",
9337
+ name: "Gemini 3.8 Flash",
9338
+ api: "google-generative-ai",
9339
+ provider: "opencode",
9340
+ baseUrl: "https://opencode.ai/zen/v1",
9341
+ reasoning: true,
9342
+ thinkingLevelMap: { "off": null },
9343
+ input: ["text", "image"],
9344
+ cost: {
9345
+ input: 1.5,
9346
+ output: 7.5,
9347
+ cacheRead: 0.15,
9348
+ cacheWrite: 0
9349
+ },
9350
+ contextWindow: 1048576,
9351
+ maxTokens: 65536
9352
+ },
9175
9353
  "glm-5": {
9176
9354
  id: "glm-5",
9177
9355
  name: "GLM-5",
@@ -9616,23 +9794,6 @@ var MODELS = {
9616
9794
  contextWindow: 256e3,
9617
9795
  maxTokens: 256e3
9618
9796
  },
9619
- "hy3-free": {
9620
- id: "hy3-free",
9621
- name: "Hy3 Free",
9622
- api: "openai-completions",
9623
- provider: "opencode",
9624
- baseUrl: "https://opencode.ai/zen/v1",
9625
- reasoning: true,
9626
- input: ["text"],
9627
- cost: {
9628
- input: 0,
9629
- output: 0,
9630
- cacheRead: 0,
9631
- cacheWrite: 0
9632
- },
9633
- contextWindow: 19e4,
9634
- maxTokens: 64e3
9635
- },
9636
9797
  "kimi-k2.5": {
9637
9798
  id: "kimi-k2.5",
9638
9799
  name: "Kimi K2.5",
@@ -9821,6 +9982,23 @@ var MODELS = {
9821
9982
  contextWindow: 1048576,
9822
9983
  maxTokens: 131072
9823
9984
  },
9985
+ "muse-spark-1.3-contributor-free": {
9986
+ id: "muse-spark-1.3-contributor-free",
9987
+ name: "Muse Spark 1.3 Free",
9988
+ api: "openai-responses",
9989
+ provider: "opencode",
9990
+ baseUrl: "https://opencode.ai/zen/v1",
9991
+ reasoning: true,
9992
+ input: ["text", "image"],
9993
+ cost: {
9994
+ input: 0,
9995
+ output: 0,
9996
+ cacheRead: 0,
9997
+ cacheWrite: 0
9998
+ },
9999
+ contextWindow: 1048576,
10000
+ maxTokens: 131072
10001
+ },
9824
10002
  "nemotron-3-ultra-free": {
9825
10003
  id: "nemotron-3-ultra-free",
9826
10004
  name: "Nemotron 3 Ultra Free",
@@ -10053,20 +10231,20 @@ var MODELS = {
10053
10231
  },
10054
10232
  "hy3": {
10055
10233
  id: "hy3",
10056
- name: "Hy3 (8x usage)",
10234
+ name: "Hy3",
10057
10235
  api: "openai-completions",
10058
10236
  provider: "opencode-go",
10059
10237
  baseUrl: "https://opencode.ai/zen/go/v1",
10060
10238
  reasoning: true,
10061
10239
  input: ["text"],
10062
10240
  cost: {
10063
- input: 0.0175,
10064
- output: 0.0725,
10065
- cacheRead: 4375e-6,
10241
+ input: 0.14,
10242
+ output: 0.58,
10243
+ cacheRead: 0.035,
10066
10244
  cacheWrite: 0
10067
10245
  },
10068
10246
  contextWindow: 256e3,
10069
- maxTokens: 64e3
10247
+ maxTokens: 128e3
10070
10248
  },
10071
10249
  "hy4-preview": {
10072
10250
  id: "hy4-preview",
@@ -10239,6 +10417,23 @@ var MODELS = {
10239
10417
  contextWindow: 1048576,
10240
10418
  maxTokens: 131072
10241
10419
  },
10420
+ "muse-spark-1.3-contributor": {
10421
+ id: "muse-spark-1.3-contributor",
10422
+ name: "Muse Spark 1.3 Contributor",
10423
+ api: "openai-responses",
10424
+ provider: "opencode-go",
10425
+ baseUrl: "https://opencode.ai/zen/go/v1",
10426
+ reasoning: true,
10427
+ input: ["text", "image"],
10428
+ cost: {
10429
+ input: 0.1,
10430
+ output: 0.2,
10431
+ cacheRead: 2e-3,
10432
+ cacheWrite: 0
10433
+ },
10434
+ contextWindow: 1048576,
10435
+ maxTokens: 131072
10436
+ },
10242
10437
  "qwen3.6-plus": {
10243
10438
  id: "qwen3.6-plus",
10244
10439
  name: "Qwen3.6 Plus",
@@ -10506,6 +10701,24 @@ var MODELS = {
10506
10701
  contextWindow: 1e6,
10507
10702
  maxTokens: 128e3
10508
10703
  },
10704
+ "anthropic/claude-fable-5.1": {
10705
+ id: "anthropic/claude-fable-5.1",
10706
+ name: "Anthropic: Claude Fable 5.1",
10707
+ api: "openai-completions",
10708
+ provider: "openrouter",
10709
+ baseUrl: "https://openrouter.ai/api/v1",
10710
+ reasoning: true,
10711
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
10712
+ input: ["text", "image"],
10713
+ cost: {
10714
+ input: 10,
10715
+ output: 50,
10716
+ cacheRead: 0.25,
10717
+ cacheWrite: 12.5
10718
+ },
10719
+ contextWindow: 1e6,
10720
+ maxTokens: 128e3
10721
+ },
10509
10722
  "anthropic/claude-haiku-4.5": {
10510
10723
  id: "anthropic/claude-haiku-4.5",
10511
10724
  name: "Anthropic: Claude Haiku 4.5",
@@ -10618,27 +10831,9 @@ var MODELS = {
10618
10831
  contextWindow: 1e6,
10619
10832
  maxTokens: 128e3
10620
10833
  },
10621
- "anthropic/claude-opus-4.7-fast": {
10622
- id: "anthropic/claude-opus-4.7-fast",
10623
- name: "Anthropic: Claude Opus 4.7 (Fast)",
10624
- api: "openai-completions",
10625
- provider: "openrouter",
10626
- baseUrl: "https://openrouter.ai/api/v1",
10627
- reasoning: true,
10628
- thinkingLevelMap: { "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
10629
- input: ["text", "image"],
10630
- cost: {
10631
- input: 30,
10632
- output: 150,
10633
- cacheRead: 3,
10634
- cacheWrite: 37.5
10635
- },
10636
- contextWindow: 1e6,
10637
- maxTokens: 128e3
10638
- },
10639
- "anthropic/claude-opus-4.8": {
10640
- id: "anthropic/claude-opus-4.8",
10641
- name: "Anthropic: Claude Opus 4.8",
10834
+ "anthropic/claude-opus-4.8": {
10835
+ id: "anthropic/claude-opus-4.8",
10836
+ name: "Anthropic: Claude Opus 4.8",
10642
10837
  api: "openai-completions",
10643
10838
  provider: "openrouter",
10644
10839
  baseUrl: "https://openrouter.ai/api/v1",
@@ -10654,24 +10849,6 @@ var MODELS = {
10654
10849
  contextWindow: 1e6,
10655
10850
  maxTokens: 128e3
10656
10851
  },
10657
- "anthropic/claude-opus-4.8-fast": {
10658
- id: "anthropic/claude-opus-4.8-fast",
10659
- name: "Anthropic: Claude Opus 4.8 (Fast)",
10660
- api: "openai-completions",
10661
- provider: "openrouter",
10662
- baseUrl: "https://openrouter.ai/api/v1",
10663
- reasoning: true,
10664
- thinkingLevelMap: { "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
10665
- input: ["text", "image"],
10666
- cost: {
10667
- input: 10,
10668
- output: 50,
10669
- cacheRead: 1,
10670
- cacheWrite: 12.5
10671
- },
10672
- contextWindow: 1e6,
10673
- maxTokens: 128e3
10674
- },
10675
10852
  "anthropic/claude-opus-5": {
10676
10853
  id: "anthropic/claude-opus-5",
10677
10854
  name: "Claude Opus 5",
@@ -10690,24 +10867,6 @@ var MODELS = {
10690
10867
  contextWindow: 1e6,
10691
10868
  maxTokens: 128e3
10692
10869
  },
10693
- "anthropic/claude-opus-5-fast": {
10694
- id: "anthropic/claude-opus-5-fast",
10695
- name: "Claude Opus 5 (Fast)",
10696
- api: "openai-completions",
10697
- provider: "openrouter",
10698
- baseUrl: "https://openrouter.ai/api/v1",
10699
- reasoning: true,
10700
- thinkingLevelMap: { "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
10701
- input: ["text", "image"],
10702
- cost: {
10703
- input: 10,
10704
- output: 50,
10705
- cacheRead: 1,
10706
- cacheWrite: 12.5
10707
- },
10708
- contextWindow: 1e6,
10709
- maxTokens: 128e3
10710
- },
10711
10870
  "anthropic/claude-sonnet-4": {
10712
10871
  id: "anthropic/claude-sonnet-4",
10713
10872
  name: "Anthropic: Claude Sonnet 4",
@@ -10793,13 +10952,13 @@ var MODELS = {
10793
10952
  thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null },
10794
10953
  input: ["text"],
10795
10954
  cost: {
10796
- input: 0.22,
10797
- output: 0.85,
10955
+ input: 0.25,
10956
+ output: 0.7999999999999999,
10798
10957
  cacheRead: 0.06,
10799
10958
  cacheWrite: 0
10800
10959
  },
10801
10960
  contextWindow: 262144,
10802
- maxTokens: 235929
10961
+ maxTokens: 8e4
10803
10962
  },
10804
10963
  "auto": {
10805
10964
  id: "auto",
@@ -10991,13 +11150,13 @@ var MODELS = {
10991
11150
  reasoning: false,
10992
11151
  input: ["text"],
10993
11152
  cost: {
10994
- input: 0.2574,
10995
- output: 1.0287,
11153
+ input: 0.32,
11154
+ output: 0.8899999999999999,
10996
11155
  cacheRead: 0,
10997
11156
  cacheWrite: 0
10998
11157
  },
10999
11158
  contextWindow: 163840,
11000
- maxTokens: 16e3
11159
+ maxTokens: 16384
11001
11160
  },
11002
11161
  "deepseek/deepseek-chat-v3-0324": {
11003
11162
  id: "deepseek/deepseek-chat-v3-0324",
@@ -11027,13 +11186,13 @@ var MODELS = {
11027
11186
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null },
11028
11187
  input: ["text"],
11029
11188
  cost: {
11030
- input: 0.55,
11031
- output: 1.6500000000000001,
11032
- cacheRead: 0.55,
11189
+ input: 0.25,
11190
+ output: 0.95,
11191
+ cacheRead: 0.13,
11033
11192
  cacheWrite: 0
11034
11193
  },
11035
11194
  contextWindow: 163840,
11036
- maxTokens: 144900
11195
+ maxTokens: 32768
11037
11196
  },
11038
11197
  "deepseek/deepseek-r1": {
11039
11198
  id: "deepseek/deepseek-r1",
@@ -11141,9 +11300,9 @@ var MODELS = {
11141
11300
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max", "max": null },
11142
11301
  input: ["text"],
11143
11302
  cost: {
11144
- input: 0.08176,
11145
- output: 0.16352,
11146
- cacheRead: 0.016352,
11303
+ input: 0.08553999999999999,
11304
+ output: 0.17107999999999998,
11305
+ cacheRead: 0.017108,
11147
11306
  cacheWrite: 0
11148
11307
  },
11149
11308
  contextWindow: 1048576,
@@ -11198,9 +11357,9 @@ var MODELS = {
11198
11357
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max", "max": null },
11199
11358
  input: ["text"],
11200
11359
  cost: {
11201
- input: 0.538878,
11202
- output: 1.077756,
11203
- cacheRead: 0.0449065,
11360
+ input: 1.035996,
11361
+ output: 2.071992,
11362
+ cacheRead: 0.086333,
11204
11363
  cacheWrite: 0
11205
11364
  },
11206
11365
  contextWindow: 1048576,
@@ -11520,6 +11679,24 @@ var MODELS = {
11520
11679
  contextWindow: 1048576,
11521
11680
  maxTokens: 65536
11522
11681
  },
11682
+ "google/gemini-3.8-flash": {
11683
+ id: "google/gemini-3.8-flash",
11684
+ name: "Google: Gemini 3.8 Flash",
11685
+ api: "openai-completions",
11686
+ provider: "openrouter",
11687
+ baseUrl: "https://openrouter.ai/api/v1",
11688
+ reasoning: true,
11689
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": null, "max": null },
11690
+ input: ["text", "image"],
11691
+ cost: {
11692
+ input: 0.75,
11693
+ output: 3.75,
11694
+ cacheRead: 0.075,
11695
+ cacheWrite: 0.0416666666666667
11696
+ },
11697
+ contextWindow: 1048576,
11698
+ maxTokens: 65536
11699
+ },
11523
11700
  "google/gemma-3-12b-it": {
11524
11701
  id: "google/gemma-3-12b-it",
11525
11702
  name: "Google: Gemma 3 12B",
@@ -11647,6 +11824,24 @@ var MODELS = {
11647
11824
  contextWindow: 131072,
11648
11825
  maxTokens: 117964
11649
11826
  },
11827
+ "ibm-granite/granite-4.2-8b": {
11828
+ id: "ibm-granite/granite-4.2-8b",
11829
+ name: "IBM: Granite 4.2 8B",
11830
+ api: "openai-completions",
11831
+ provider: "openrouter",
11832
+ baseUrl: "https://openrouter.ai/api/v1",
11833
+ reasoning: true,
11834
+ thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": null },
11835
+ input: ["text"],
11836
+ cost: {
11837
+ input: 0.09999999999999999,
11838
+ output: 0.15,
11839
+ cacheRead: 0.049999999999999996,
11840
+ cacheWrite: 0
11841
+ },
11842
+ contextWindow: 131072,
11843
+ maxTokens: 117964
11844
+ },
11650
11845
  "inception/mercury-2": {
11651
11846
  id: "inception/mercury-2",
11652
11847
  name: "Inception: Mercury 2",
@@ -11665,6 +11860,24 @@ var MODELS = {
11665
11860
  contextWindow: 128e3,
11666
11861
  maxTokens: 5e4
11667
11862
  },
11863
+ "inception/mercury-2.5-preview": {
11864
+ id: "inception/mercury-2.5-preview",
11865
+ name: "Inception: Mercury 2.5 Preview",
11866
+ api: "openai-completions",
11867
+ provider: "openrouter",
11868
+ baseUrl: "https://openrouter.ai/api/v1",
11869
+ reasoning: true,
11870
+ thinkingLevelMap: { "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": null, "max": null },
11871
+ input: ["text"],
11872
+ cost: {
11873
+ input: 0.04,
11874
+ output: 0.15,
11875
+ cacheRead: 4e-3,
11876
+ cacheWrite: 0
11877
+ },
11878
+ contextWindow: 26e4,
11879
+ maxTokens: 65536
11880
+ },
11668
11881
  "inclusionai/ling-3.0-flash": {
11669
11882
  id: "inclusionai/ling-3.0-flash",
11670
11883
  name: "Ling-3.0-flash",
@@ -11703,23 +11916,6 @@ var MODELS = {
11703
11916
  contextWindow: 262144,
11704
11917
  maxTokens: 32768
11705
11918
  },
11706
- "kwaipilot/kat-coder-air-v2.5": {
11707
- id: "kwaipilot/kat-coder-air-v2.5",
11708
- name: "Kwaipilot: KAT-Coder-Air V2.5",
11709
- api: "openai-completions",
11710
- provider: "openrouter",
11711
- baseUrl: "https://openrouter.ai/api/v1",
11712
- reasoning: false,
11713
- input: ["text"],
11714
- cost: {
11715
- input: 0.15,
11716
- output: 0.6,
11717
- cacheRead: 0.03,
11718
- cacheWrite: 0
11719
- },
11720
- contextWindow: 256e3,
11721
- maxTokens: 8e4
11722
- },
11723
11919
  "kwaipilot/kat-coder-pro-v2": {
11724
11920
  id: "kwaipilot/kat-coder-pro-v2",
11725
11921
  name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -11735,7 +11931,7 @@ var MODELS = {
11735
11931
  cacheWrite: 0
11736
11932
  },
11737
11933
  contextWindow: 262144,
11738
- maxTokens: 8e4
11934
+ maxTokens: 144e3
11739
11935
  },
11740
11936
  "kwaipilot/kat-coder-pro-v2.5": {
11741
11937
  id: "kwaipilot/kat-coder-pro-v2.5",
@@ -11752,7 +11948,7 @@ var MODELS = {
11752
11948
  cacheWrite: 0
11753
11949
  },
11754
11950
  contextWindow: 262144,
11755
- maxTokens: 8e4
11951
+ maxTokens: 235929
11756
11952
  },
11757
11953
  "liquid/lfm-2.5-2.6b:free": {
11758
11954
  id: "liquid/lfm-2.5-2.6b:free",
@@ -11835,13 +12031,13 @@ var MODELS = {
11835
12031
  reasoning: false,
11836
12032
  input: ["text"],
11837
12033
  cost: {
11838
- input: 0.71,
11839
- output: 0.71,
11840
- cacheRead: 0.71,
12034
+ input: 0.09999999999999999,
12035
+ output: 0.32,
12036
+ cacheRead: 0,
11841
12037
  cacheWrite: 0
11842
12038
  },
11843
12039
  contextWindow: 131072,
11844
- maxTokens: 115200
12040
+ maxTokens: 16384
11845
12041
  },
11846
12042
  "meta-llama/llama-4-maverick": {
11847
12043
  id: "meta-llama/llama-4-maverick",
@@ -11853,12 +12049,12 @@ var MODELS = {
11853
12049
  input: ["text", "image"],
11854
12050
  cost: {
11855
12051
  input: 0.19999999999999998,
11856
- output: 0.7999999999999999,
12052
+ output: 0.696,
11857
12053
  cacheRead: 0,
11858
12054
  cacheWrite: 0
11859
12055
  },
11860
12056
  contextWindow: 1048576,
11861
- maxTokens: 16384
12057
+ maxTokens: 115200
11862
12058
  },
11863
12059
  "meta-llama/llama-4-scout": {
11864
12060
  id: "meta-llama/llama-4-scout",
@@ -11869,13 +12065,13 @@ var MODELS = {
11869
12065
  reasoning: false,
11870
12066
  input: ["text", "image"],
11871
12067
  cost: {
11872
- input: 0.11,
11873
- output: 0.33999999999999997,
11874
- cacheRead: 0.055,
12068
+ input: 0.09999999999999999,
12069
+ output: 0.3,
12070
+ cacheRead: 0,
11875
12071
  cacheWrite: 0
11876
12072
  },
11877
12073
  contextWindow: 1310720,
11878
- maxTokens: 8192
12074
+ maxTokens: 16384
11879
12075
  },
11880
12076
  "meta/muse-glimmer-30b": {
11881
12077
  id: "meta/muse-glimmer-30b",
@@ -11888,12 +12084,12 @@ var MODELS = {
11888
12084
  input: ["text", "image"],
11889
12085
  cost: {
11890
12086
  input: 0.3,
11891
- output: 1.2,
12087
+ output: 1.1,
11892
12088
  cacheRead: 0.04,
11893
12089
  cacheWrite: 0
11894
12090
  },
11895
12091
  contextWindow: 131072,
11896
- maxTokens: 16384
12092
+ maxTokens: 117964
11897
12093
  },
11898
12094
  "meta/muse-spark-1.1": {
11899
12095
  id: "meta/muse-spark-1.1",
@@ -11949,6 +12145,42 @@ var MODELS = {
11949
12145
  contextWindow: 1048576,
11950
12146
  maxTokens: 943718
11951
12147
  },
12148
+ "meta/muse-spark-1.3": {
12149
+ id: "meta/muse-spark-1.3",
12150
+ name: "Meta: Muse Spark 1.3",
12151
+ api: "openai-completions",
12152
+ provider: "openrouter",
12153
+ baseUrl: "https://openrouter.ai/api/v1",
12154
+ reasoning: true,
12155
+ thinkingLevelMap: { "off": null, "minimal": "minimal", "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": null },
12156
+ input: ["text", "image"],
12157
+ cost: {
12158
+ input: 1.25,
12159
+ output: 4.25,
12160
+ cacheRead: 0.15,
12161
+ cacheWrite: 0
12162
+ },
12163
+ contextWindow: 1048576,
12164
+ maxTokens: 943718
12165
+ },
12166
+ "meta/muse-spark-1.3-contributor": {
12167
+ id: "meta/muse-spark-1.3-contributor",
12168
+ name: "Meta: Muse Spark 1.3 Contributor",
12169
+ api: "openai-completions",
12170
+ provider: "openrouter",
12171
+ baseUrl: "https://openrouter.ai/api/v1",
12172
+ reasoning: true,
12173
+ thinkingLevelMap: { "off": null, "minimal": "minimal", "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": null },
12174
+ input: ["text", "image"],
12175
+ cost: {
12176
+ input: 0.09999999999999999,
12177
+ output: 0.19999999999999998,
12178
+ cacheRead: 2e-3,
12179
+ cacheWrite: 0
12180
+ },
12181
+ contextWindow: 1048576,
12182
+ maxTokens: 943718
12183
+ },
11952
12184
  "minimax/minimax-m1": {
11953
12185
  id: "minimax/minimax-m1",
11954
12186
  name: "MiniMax: MiniMax M1",
@@ -12127,9 +12359,9 @@ var MODELS = {
12127
12359
  reasoning: false,
12128
12360
  input: ["text"],
12129
12361
  cost: {
12130
- input: 0.44,
12131
- output: 2.2,
12132
- cacheRead: 0.044,
12362
+ input: 0.39999999999999997,
12363
+ output: 2,
12364
+ cacheRead: 0.04,
12133
12365
  cacheWrite: 0
12134
12366
  },
12135
12367
  contextWindow: 262144,
@@ -12571,11 +12803,11 @@ var MODELS = {
12571
12803
  cost: {
12572
12804
  input: 0.049999999999999996,
12573
12805
  output: 0.19999999999999998,
12574
- cacheRead: 0.024999999999999998,
12806
+ cacheRead: 0.03,
12575
12807
  cacheWrite: 0
12576
12808
  },
12577
12809
  contextWindow: 262144,
12578
- maxTokens: 228e3
12810
+ maxTokens: 235929
12579
12811
  },
12580
12812
  "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
12581
12813
  id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
@@ -12642,13 +12874,13 @@ var MODELS = {
12642
12874
  thinkingLevelMap: { "minimal": null, "low": null, "medium": "medium", "high": "high", "xhigh": null, "max": null },
12643
12875
  input: ["text"],
12644
12876
  cost: {
12645
- input: 0.5,
12646
- output: 2.2,
12647
- cacheRead: 0.09999999999999999,
12877
+ input: 0.6,
12878
+ output: 2.4,
12879
+ cacheRead: 0.12,
12648
12880
  cacheWrite: 0
12649
12881
  },
12650
12882
  contextWindow: 262144,
12651
- maxTokens: 16384
12883
+ maxTokens: 182520
12652
12884
  },
12653
12885
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
12654
12886
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -12853,11 +13085,11 @@ var MODELS = {
12853
13085
  cost: {
12854
13086
  input: 0.09999999999999999,
12855
13087
  output: 0.39999999999999997,
12856
- cacheRead: 0.03,
13088
+ cacheRead: 0.024999999999999998,
12857
13089
  cacheWrite: 0
12858
13090
  },
12859
13091
  contextWindow: 1047576,
12860
- maxTokens: 942818
13092
+ maxTokens: 32768
12861
13093
  },
12862
13094
  "openai/gpt-4o": {
12863
13095
  id: "openai/gpt-4o",
@@ -14360,13 +14592,13 @@ var MODELS = {
14360
14592
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null },
14361
14593
  input: ["text", "image"],
14362
14594
  cost: {
14363
- input: 0.39,
14364
- output: 2.34,
14365
- cacheRead: 0,
14595
+ input: 0.55,
14596
+ output: 3.5,
14597
+ cacheRead: 0.22499999999999998,
14366
14598
  cacheWrite: 0
14367
14599
  },
14368
14600
  contextWindow: 262144,
14369
- maxTokens: 65536
14601
+ maxTokens: 235929
14370
14602
  },
14371
14603
  "qwen/qwen3.5-9b": {
14372
14604
  id: "qwen/qwen3.5-9b",
@@ -14803,9 +15035,9 @@ var MODELS = {
14803
15035
  thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": null },
14804
15036
  input: ["text"],
14805
15037
  cost: {
14806
- input: 0.0825,
14807
- output: 0.33,
14808
- cacheRead: 0.020625,
15038
+ input: 0.13199999999999998,
15039
+ output: 0.5279999999999999,
15040
+ cacheRead: 0.032999999999999995,
14809
15041
  cacheWrite: 0
14810
15042
  },
14811
15043
  contextWindow: 262144,
@@ -14874,13 +15106,13 @@ var MODELS = {
14874
15106
  thinkingLevelMap: { "minimal": "minimal", "low": "low", "medium": "medium", "high": "high", "xhigh": null, "max": "max" },
14875
15107
  input: ["text", "image"],
14876
15108
  cost: {
14877
- input: 0.95,
15109
+ input: 1,
14878
15110
  output: 4.05,
14879
- cacheRead: 0.16,
15111
+ cacheRead: 0.16999999999999998,
14880
15112
  cacheWrite: 0
14881
15113
  },
14882
15114
  contextWindow: 1048576,
14883
- maxTokens: 262144
15115
+ maxTokens: 471859
14884
15116
  },
14885
15117
  "thinkingmachines/inkling-small": {
14886
15118
  id: "thinkingmachines/inkling-small",
@@ -15172,13 +15404,13 @@ var MODELS = {
15172
15404
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null },
15173
15405
  input: ["text"],
15174
15406
  cost: {
15175
- input: 0.43,
15176
- output: 1.75,
15177
- cacheRead: 0.08,
15407
+ input: 0.55,
15408
+ output: 2.2,
15409
+ cacheRead: 0.11,
15178
15410
  cacheWrite: 0
15179
15411
  },
15180
15412
  contextWindow: 204800,
15181
- maxTokens: 16384
15413
+ maxTokens: 131072
15182
15414
  },
15183
15415
  "z-ai/glm-4.6v": {
15184
15416
  id: "z-ai/glm-4.6v",
@@ -15286,13 +15518,13 @@ var MODELS = {
15286
15518
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null },
15287
15519
  input: ["text"],
15288
15520
  cost: {
15289
- input: 1.26,
15290
- output: 3.9600000000000004,
15291
- cacheRead: 0.234,
15521
+ input: 0.966,
15522
+ output: 3.036,
15523
+ cacheRead: 0.1794,
15292
15524
  cacheWrite: 0
15293
15525
  },
15294
15526
  contextWindow: 204800,
15295
- maxTokens: 182476
15527
+ maxTokens: 128e3
15296
15528
  },
15297
15529
  "z-ai/glm-5.2": {
15298
15530
  id: "z-ai/glm-5.2",
@@ -15304,13 +15536,13 @@ var MODELS = {
15304
15536
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh", "max": null },
15305
15537
  input: ["text"],
15306
15538
  cost: {
15307
- input: 1.19,
15308
- output: 3.74,
15309
- cacheRead: 0.221,
15539
+ input: 0.966,
15540
+ output: 3.036,
15541
+ cacheRead: 0.1932,
15310
15542
  cacheWrite: 0
15311
15543
  },
15312
15544
  contextWindow: 1048576,
15313
- maxTokens: 262144
15545
+ maxTokens: 131072
15314
15546
  },
15315
15547
  "z-ai/glm-5.2:free": {
15316
15548
  id: "z-ai/glm-5.2:free",
@@ -15342,11 +15574,11 @@ var MODELS = {
15342
15574
  cost: {
15343
15575
  input: 1.4,
15344
15576
  output: 4.4,
15345
- cacheRead: 0.26,
15577
+ cacheRead: 0.14,
15346
15578
  cacheWrite: 0
15347
15579
  },
15348
15580
  contextWindow: 1310720,
15349
- maxTokens: 131072
15581
+ maxTokens: 262144
15350
15582
  },
15351
15583
  "z-ai/glm-5.3-flash": {
15352
15584
  id: "z-ai/glm-5.3-flash",
@@ -15397,7 +15629,7 @@ var MODELS = {
15397
15629
  cost: {
15398
15630
  input: 10,
15399
15631
  output: 50,
15400
- cacheRead: 1,
15632
+ cacheRead: 0.25,
15401
15633
  cacheWrite: 12.5
15402
15634
  },
15403
15635
  contextWindow: 1e6,
@@ -15469,9 +15701,9 @@ var MODELS = {
15469
15701
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max", "max": null },
15470
15702
  input: ["text"],
15471
15703
  cost: {
15472
- input: 0.03,
15473
- output: 0.09999999999999999,
15474
- cacheRead: 7e-3,
15704
+ input: 0.049999999999999996,
15705
+ output: 0.16,
15706
+ cacheRead: 0.013000000000000001,
15475
15707
  cacheWrite: 0
15476
15708
  },
15477
15709
  contextWindow: 1310720,
@@ -15585,6 +15817,24 @@ var MODELS = {
15585
15817
  contextWindow: 5e5,
15586
15818
  maxTokens: 45e4
15587
15819
  },
15820
+ "~z-ai/glm-flash-latest": {
15821
+ id: "~z-ai/glm-flash-latest",
15822
+ name: "Z.ai: GLM Flash Latest",
15823
+ api: "openai-completions",
15824
+ provider: "openrouter",
15825
+ baseUrl: "https://openrouter.ai/api/v1",
15826
+ reasoning: true,
15827
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max" },
15828
+ input: ["text", "image"],
15829
+ cost: {
15830
+ input: 0.075,
15831
+ output: 0.25,
15832
+ cacheRead: 0.015,
15833
+ cacheWrite: 0
15834
+ },
15835
+ contextWindow: 1310720,
15836
+ maxTokens: 943718
15837
+ },
15588
15838
  "~z-ai/glm-latest": {
15589
15839
  id: "~z-ai/glm-latest",
15590
15840
  name: "Z.ai: GLM Latest",
@@ -15595,13 +15845,13 @@ var MODELS = {
15595
15845
  thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max" },
15596
15846
  input: ["text"],
15597
15847
  cost: {
15598
- input: 1.1875,
15599
- output: 4.18,
15600
- cacheRead: 0.24699999999999997,
15848
+ input: 1.1340000000000001,
15849
+ output: 3.564,
15850
+ cacheRead: 0.1863,
15601
15851
  cacheWrite: 0
15602
15852
  },
15603
15853
  contextWindow: 1310720,
15604
- maxTokens: 131072
15854
+ maxTokens: 943718
15605
15855
  }
15606
15856
  },
15607
15857
  "prime-inference": {
@@ -15857,7 +16107,7 @@ var MODELS = {
15857
16107
  cacheWrite: 0
15858
16108
  },
15859
16109
  contextWindow: 163840,
15860
- maxTokens: 16e3
16110
+ maxTokens: 16384
15861
16111
  },
15862
16112
  "deepseek/deepseek-chat-v3-0324": {
15863
16113
  id: "deepseek/deepseek-chat-v3-0324",
@@ -15894,7 +16144,7 @@ var MODELS = {
15894
16144
  cacheWrite: 0
15895
16145
  },
15896
16146
  contextWindow: 163840,
15897
- maxTokens: 144900
16147
+ maxTokens: 32768
15898
16148
  },
15899
16149
  "deepseek/deepseek-v3.1-terminus": {
15900
16150
  id: "deepseek/deepseek-v3.1-terminus",
@@ -16235,7 +16485,7 @@ var MODELS = {
16235
16485
  cacheWrite: 0
16236
16486
  },
16237
16487
  contextWindow: 131072,
16238
- maxTokens: 115200
16488
+ maxTokens: 16384
16239
16489
  },
16240
16490
  "meta-llama/llama-4-maverick": {
16241
16491
  id: "meta-llama/llama-4-maverick",
@@ -16253,7 +16503,7 @@ var MODELS = {
16253
16503
  cacheWrite: 0
16254
16504
  },
16255
16505
  contextWindow: 1048576,
16256
- maxTokens: 16384
16506
+ maxTokens: 115200
16257
16507
  },
16258
16508
  "meta/muse-spark-1.2": {
16259
16509
  id: "meta/muse-spark-1.2",
@@ -16518,7 +16768,7 @@ var MODELS = {
16518
16768
  cacheWrite: 0
16519
16769
  },
16520
16770
  contextWindow: 262144,
16521
- maxTokens: 228e3,
16771
+ maxTokens: 235929,
16522
16772
  featured: true
16523
16773
  },
16524
16774
  "nvidia/nemotron-3-super-120b-a12b": {
@@ -16593,7 +16843,7 @@ var MODELS = {
16593
16843
  cacheWrite: 0
16594
16844
  },
16595
16845
  contextWindow: 1047576,
16596
- maxTokens: 942818
16846
+ maxTokens: 32768
16597
16847
  },
16598
16848
  "openai/gpt-4o": {
16599
16849
  id: "openai/gpt-4o",
@@ -17526,7 +17776,7 @@ var MODELS = {
17526
17776
  cacheWrite: 0
17527
17777
  },
17528
17778
  contextWindow: 204800,
17529
- maxTokens: 16384
17779
+ maxTokens: 131072
17530
17780
  },
17531
17781
  "z-ai/glm-4.7": {
17532
17782
  id: "z-ai/glm-4.7",
@@ -17603,7 +17853,7 @@ var MODELS = {
17603
17853
  cacheWrite: 0
17604
17854
  },
17605
17855
  contextWindow: 204800,
17606
- maxTokens: 182476,
17856
+ maxTokens: 128e3,
17607
17857
  featured: true
17608
17858
  },
17609
17859
  "z-ai/glm-5.2": {
@@ -17623,7 +17873,7 @@ var MODELS = {
17623
17873
  cacheWrite: 0
17624
17874
  },
17625
17875
  contextWindow: 1048576,
17626
- maxTokens: 262144,
17876
+ maxTokens: 131072,
17627
17877
  featured: true
17628
17878
  },
17629
17879
  "z-ai/glm-5.3": {
@@ -17643,7 +17893,7 @@ var MODELS = {
17643
17893
  cacheWrite: 0
17644
17894
  },
17645
17895
  contextWindow: 1310720,
17646
- maxTokens: 131072
17896
+ maxTokens: 262144
17647
17897
  },
17648
17898
  "z-ai/glm-5.3-flash": {
17649
17899
  id: "z-ai/glm-5.3-flash",
@@ -18142,6 +18392,23 @@ var MODELS = {
18142
18392
  contextWindow: 991e3,
18143
18393
  maxTokens: 128e3
18144
18394
  },
18395
+ "alibaba/qwen3.8-flash-next": {
18396
+ id: "alibaba/qwen3.8-flash-next",
18397
+ name: "Qwen 3.8 Flash Next",
18398
+ api: "anthropic-messages",
18399
+ provider: "vercel-ai-gateway",
18400
+ baseUrl: "https://ai-gateway.vercel.sh",
18401
+ reasoning: true,
18402
+ input: ["text", "image"],
18403
+ cost: {
18404
+ input: 0.12,
18405
+ output: 0.39999999999999997,
18406
+ cacheRead: 0.01,
18407
+ cacheWrite: 0
18408
+ },
18409
+ contextWindow: 1048576,
18410
+ maxTokens: 1048576
18411
+ },
18145
18412
  "alibaba/qwen3.8-max": {
18146
18413
  id: "alibaba/qwen3.8-max",
18147
18414
  name: "Qwen 3.8 Max",
@@ -18159,6 +18426,23 @@ var MODELS = {
18159
18426
  contextWindow: 1e6,
18160
18427
  maxTokens: 128e3
18161
18428
  },
18429
+ "alibaba/qwen3.8-max-0902": {
18430
+ id: "alibaba/qwen3.8-max-0902",
18431
+ name: "Qwen3.8 Max 0902",
18432
+ api: "anthropic-messages",
18433
+ provider: "vercel-ai-gateway",
18434
+ baseUrl: "https://ai-gateway.vercel.sh",
18435
+ reasoning: true,
18436
+ input: ["text", "image"],
18437
+ cost: {
18438
+ input: 2,
18439
+ output: 6,
18440
+ cacheRead: 0.25,
18441
+ cacheWrite: 2.5
18442
+ },
18443
+ contextWindow: 991e3,
18444
+ maxTokens: 128e3
18445
+ },
18162
18446
  "amazon/nova-2-lite": {
18163
18447
  id: "amazon/nova-2-lite",
18164
18448
  name: "Nova 2 Lite",
@@ -18262,6 +18546,24 @@ var MODELS = {
18262
18546
  contextWindow: 1e6,
18263
18547
  maxTokens: 128e3
18264
18548
  },
18549
+ "anthropic/claude-fable-5.1": {
18550
+ id: "anthropic/claude-fable-5.1",
18551
+ name: "Claude Fable 5.1",
18552
+ api: "anthropic-messages",
18553
+ provider: "vercel-ai-gateway",
18554
+ baseUrl: "https://ai-gateway.vercel.sh",
18555
+ reasoning: true,
18556
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
18557
+ input: ["text", "image"],
18558
+ cost: {
18559
+ input: 10,
18560
+ output: 50,
18561
+ cacheRead: 0.25,
18562
+ cacheWrite: 12.5
18563
+ },
18564
+ contextWindow: 1e6,
18565
+ maxTokens: 128e3
18566
+ },
18265
18567
  "anthropic/claude-haiku-4.5": {
18266
18568
  id: "anthropic/claude-haiku-4.5",
18267
18569
  name: "Claude Haiku 4.5",
@@ -18576,23 +18878,6 @@ var MODELS = {
18576
18878
  contextWindow: 128e3,
18577
18879
  maxTokens: 8192
18578
18880
  },
18579
- "deepseek/deepseek-v3": {
18580
- id: "deepseek/deepseek-v3",
18581
- name: "DeepSeek V3 0324",
18582
- api: "anthropic-messages",
18583
- provider: "vercel-ai-gateway",
18584
- baseUrl: "https://ai-gateway.vercel.sh",
18585
- reasoning: false,
18586
- input: ["text"],
18587
- cost: {
18588
- input: 0.27,
18589
- output: 1.12,
18590
- cacheRead: 0.135,
18591
- cacheWrite: 0
18592
- },
18593
- contextWindow: 163840,
18594
- maxTokens: 163840
18595
- },
18596
18881
  "deepseek/deepseek-v3.1": {
18597
18882
  id: "deepseek/deepseek-v3.1",
18598
18883
  name: "DeepSeek V3.1",
@@ -18709,8 +18994,8 @@ var MODELS = {
18709
18994
  cacheRead: 7e-3,
18710
18995
  cacheWrite: 0
18711
18996
  },
18712
- contextWindow: 1e6,
18713
- maxTokens: 384e3
18997
+ contextWindow: 1048576,
18998
+ maxTokens: 1048576
18714
18999
  },
18715
19000
  "deepseek/deepseek-v4-pro": {
18716
19001
  id: "deepseek/deepseek-v4-pro",
@@ -18916,6 +19201,23 @@ var MODELS = {
18916
19201
  contextWindow: 1e6,
18917
19202
  maxTokens: 65536
18918
19203
  },
19204
+ "google/gemini-3.8-flash": {
19205
+ id: "google/gemini-3.8-flash",
19206
+ name: "Gemini 3.8 Flash",
19207
+ api: "anthropic-messages",
19208
+ provider: "vercel-ai-gateway",
19209
+ baseUrl: "https://ai-gateway.vercel.sh",
19210
+ reasoning: true,
19211
+ input: ["text", "image"],
19212
+ cost: {
19213
+ input: 0.75,
19214
+ output: 3.75,
19215
+ cacheRead: 0.075,
19216
+ cacheWrite: 0
19217
+ },
19218
+ contextWindow: 1e6,
19219
+ maxTokens: 65536
19220
+ },
18919
19221
  "google/gemma-4-26b-a4b-it": {
18920
19222
  id: "google/gemma-4-26b-a4b-it",
18921
19223
  name: "Google Gemma 4 26B A4B",
@@ -19273,6 +19575,40 @@ var MODELS = {
19273
19575
  contextWindow: 1048576,
19274
19576
  maxTokens: 1048576
19275
19577
  },
19578
+ "meta/muse-spark-1.3": {
19579
+ id: "meta/muse-spark-1.3",
19580
+ name: "Muse Spark 1.3",
19581
+ api: "anthropic-messages",
19582
+ provider: "vercel-ai-gateway",
19583
+ baseUrl: "https://ai-gateway.vercel.sh",
19584
+ reasoning: true,
19585
+ input: ["text", "image"],
19586
+ cost: {
19587
+ input: 1.25,
19588
+ output: 4.25,
19589
+ cacheRead: 0.15,
19590
+ cacheWrite: 0
19591
+ },
19592
+ contextWindow: 1048576,
19593
+ maxTokens: 1048576
19594
+ },
19595
+ "meta/muse-spark-1.3-contributor": {
19596
+ id: "meta/muse-spark-1.3-contributor",
19597
+ name: "Muse Spark 1.3 Contributor",
19598
+ api: "anthropic-messages",
19599
+ provider: "vercel-ai-gateway",
19600
+ baseUrl: "https://ai-gateway.vercel.sh",
19601
+ reasoning: true,
19602
+ input: ["text", "image"],
19603
+ cost: {
19604
+ input: 0.09999999999999999,
19605
+ output: 0.19999999999999998,
19606
+ cacheRead: 2e-3,
19607
+ cacheWrite: 0
19608
+ },
19609
+ contextWindow: 1048576,
19610
+ maxTokens: 1048576
19611
+ },
19276
19612
  "minimax/minimax-m2": {
19277
19613
  id: "minimax/minimax-m2",
19278
19614
  name: "MiniMax M2",
@@ -21268,6 +21604,23 @@ var MODELS = {
21268
21604
  contextWindow: 105e4,
21269
21605
  maxTokens: 131e3
21270
21606
  },
21607
+ "xiaomi/mimo-v2.5-pro-ultraspeed": {
21608
+ id: "xiaomi/mimo-v2.5-pro-ultraspeed",
21609
+ name: "MiMo V2.5 Pro UltraSpeed",
21610
+ api: "anthropic-messages",
21611
+ provider: "vercel-ai-gateway",
21612
+ baseUrl: "https://ai-gateway.vercel.sh",
21613
+ reasoning: true,
21614
+ input: ["text"],
21615
+ cost: {
21616
+ input: 1.305,
21617
+ output: 2.61,
21618
+ cacheRead: 0.0108,
21619
+ cacheWrite: 0
21620
+ },
21621
+ contextWindow: 1048576,
21622
+ maxTokens: 131072
21623
+ },
21271
21624
  "zai/glm-4.5": {
21272
21625
  id: "zai/glm-4.5",
21273
21626
  name: "GLM 4.5",
@@ -21481,14 +21834,31 @@ var MODELS = {
21481
21834
  reasoning: true,
21482
21835
  input: ["text"],
21483
21836
  cost: {
21484
- input: 1.4,
21485
- output: 4.4,
21486
- cacheRead: 0.14,
21837
+ input: 0.7,
21838
+ output: 2.2,
21839
+ cacheRead: 0.13,
21487
21840
  cacheWrite: 0
21488
21841
  },
21489
21842
  contextWindow: 1e6,
21490
21843
  maxTokens: 1e6
21491
21844
  },
21845
+ "zai/glm-5.3-fast": {
21846
+ id: "zai/glm-5.3-fast",
21847
+ name: "GLM 5.3 Fast",
21848
+ api: "anthropic-messages",
21849
+ provider: "vercel-ai-gateway",
21850
+ baseUrl: "https://ai-gateway.vercel.sh",
21851
+ reasoning: true,
21852
+ input: ["text"],
21853
+ cost: {
21854
+ input: 2.0999999999999996,
21855
+ output: 6.6000000000000005,
21856
+ cacheRead: 0.21,
21857
+ cacheWrite: 0
21858
+ },
21859
+ contextWindow: 1048576,
21860
+ maxTokens: 262144
21861
+ },
21492
21862
  "zai/glm-5.3-flash": {
21493
21863
  id: "zai/glm-5.3-flash",
21494
21864
  name: "GLM 5.3 Flash",
@@ -21506,6 +21876,23 @@ var MODELS = {
21506
21876
  contextWindow: 1e6,
21507
21877
  maxTokens: 131e3
21508
21878
  },
21879
+ "zai/glm-5.3-promo-50": {
21880
+ id: "zai/glm-5.3-promo-50",
21881
+ name: "GLM 5.3 (50% off)",
21882
+ api: "anthropic-messages",
21883
+ provider: "vercel-ai-gateway",
21884
+ baseUrl: "https://ai-gateway.vercel.sh",
21885
+ reasoning: true,
21886
+ input: ["text"],
21887
+ cost: {
21888
+ input: 0.7,
21889
+ output: 2.2,
21890
+ cacheRead: 0.13,
21891
+ cacheWrite: 0
21892
+ },
21893
+ contextWindow: 1048576,
21894
+ maxTokens: 1048576
21895
+ },
21509
21896
  "zai/glm-5v-turbo": {
21510
21897
  id: "zai/glm-5v-turbo",
21511
21898
  name: "GLM 5V Turbo",