@asm-agent/coding-agent 0.8.6 → 0.8.8

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 (55) hide show
  1. package/CHANGELOG.md +8 -0
  2. package/dist/asm-agent-runtime/src/rlm/__pycache__/__init__.cpython-313.pyc +0 -0
  3. package/dist/asm-agent-runtime/src/rlm/__pycache__/_winjob.cpython-313.pyc +0 -0
  4. package/dist/asm-agent-runtime/src/rlm/__pycache__/bash.cpython-313.pyc +0 -0
  5. package/dist/asm-agent-runtime/src/rlm/__pycache__/harness.cpython-313.pyc +0 -0
  6. package/dist/asm-agent-runtime/src/rlm/__pycache__/mcp.cpython-313.pyc +0 -0
  7. package/dist/asm-agent-runtime/src/rlm/__pycache__/mcp_base.cpython-313.pyc +0 -0
  8. package/dist/asm-agent-runtime/src/rlm/__pycache__/repl.cpython-313.pyc +0 -0
  9. package/dist/asm-agent-runtime/test/__pycache__/test_agent_message_skill.cpython-313.pyc +0 -0
  10. package/dist/asm-agent-runtime/test/__pycache__/test_bash.cpython-313.pyc +0 -0
  11. package/dist/asm-agent-runtime/test/__pycache__/test_harness.cpython-313.pyc +0 -0
  12. package/dist/asm-agent-runtime/test/__pycache__/test_mcp.cpython-313.pyc +0 -0
  13. package/dist/asm-agent-runtime/test/__pycache__/test_mcp_base.cpython-313.pyc +0 -0
  14. package/dist/asm-agent-runtime/test/__pycache__/test_repl.cpython-313.pyc +0 -0
  15. package/dist/asm-agent-runtime/test/__pycache__/test_subagent_registry.cpython-313.pyc +0 -0
  16. package/dist/asm-agent-runtime/test/__pycache__/test_winjob.cpython-313.pyc +0 -0
  17. package/dist/bundle/{anthropic-CILMWJ23.js → anthropic-OFECORE7.js} +1 -1
  18. package/dist/bundle/{azure-openai-responses-TPNZ54LG.js → azure-openai-responses-AOVTLR6N.js} +2 -2
  19. package/dist/bundle/{bundled-modules-SKYRKITN.js → bundled-modules-JQCJDEIY.js} +4 -4
  20. package/dist/bundle/{chunk-EFDSSG52.js → chunk-7TB7CGPV.js} +319 -292
  21. package/dist/bundle/{chunk-IYXHHLR6.js → chunk-A65OM3TZ.js} +1 -1
  22. package/dist/bundle/{chunk-J6ATXG62.js → chunk-CMMSLBAW.js} +12 -8
  23. package/dist/bundle/{chunk-YYVQTKC6.js → chunk-JC2TT4MZ.js} +88 -4
  24. package/dist/bundle/{chunk-7QIBGY2R.js → chunk-M67RGWDQ.js} +597 -191
  25. package/dist/bundle/{cli-main-O3HK7MNQ.js → cli-main-FNHDQGQD.js} +4 -4
  26. package/dist/bundle/cli.js +1 -1
  27. package/dist/bundle/{compile-UQNZ2TRI.js → compile-BYYUFOG3.js} +1 -1
  28. package/dist/bundle/{google-3TL5FKLN.js → google-RVJL6RIQ.js} +1 -1
  29. package/dist/bundle/{google-vertex-WVFMK6QO.js → google-vertex-EZTRRRH6.js} +1 -1
  30. package/dist/bundle/{main-4QYKME2K.js → main-IYXIIAJN.js} +4 -4
  31. package/dist/bundle/{mistral-QV2OSBWW.js → mistral-FSGKSMA7.js} +1 -1
  32. package/dist/bundle/{openai-codex-responses-J2GJ2FAO.js → openai-codex-responses-VM5Y564D.js} +2 -2
  33. package/dist/bundle/{openai-completions-W622H2EL.js → openai-completions-X46FOQDN.js} +5 -2
  34. package/dist/bundle/{openai-responses-V75QG5T7.js → openai-responses-SOQNEPBE.js} +2 -2
  35. package/dist/core/model-registry.d.ts.map +1 -1
  36. package/dist/core/model-registry.js +9 -1
  37. package/dist/core/model-registry.js.map +1 -1
  38. package/dist/core/ollama-models.d.ts +6 -0
  39. package/dist/core/ollama-models.d.ts.map +1 -0
  40. package/dist/core/ollama-models.js +77 -0
  41. package/dist/core/ollama-models.js.map +1 -0
  42. package/dist/core/provider-display-names.d.ts.map +1 -1
  43. package/dist/core/provider-display-names.js +1 -0
  44. package/dist/core/provider-display-names.js.map +1 -1
  45. package/dist/skills/request-report/SKILL.md +19 -0
  46. package/docs/models.md +2 -0
  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/request-report/SKILL.md +19 -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)",
@@ -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,
@@ -4059,7 +4148,7 @@ var MODELS = {
4059
4148
  cost: {
4060
4149
  input: 0.15,
4061
4150
  output: 0.5,
4062
- cacheRead: 0.029,
4151
+ cacheRead: 0.03,
4063
4152
  cacheWrite: 0
4064
4153
  },
4065
4154
  contextWindow: 1e6,
@@ -5132,13 +5221,14 @@ var MODELS = {
5132
5221
  contextWindow: 1048576,
5133
5222
  maxTokens: 65536
5134
5223
  },
5135
- "gemini-flash-latest": {
5136
- id: "gemini-flash-latest",
5137
- name: "Gemini Flash Latest",
5224
+ "gemini-3.8-flash": {
5225
+ id: "gemini-3.8-flash",
5226
+ name: "Gemini 3.8 Flash",
5138
5227
  api: "google-generative-ai",
5139
5228
  provider: "google",
5140
5229
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
5141
5230
  reasoning: true,
5231
+ thinkingLevelMap: { "off": null },
5142
5232
  input: ["text", "image"],
5143
5233
  cost: {
5144
5234
  input: 0.75,
@@ -5149,38 +5239,38 @@ var MODELS = {
5149
5239
  contextWindow: 1048576,
5150
5240
  maxTokens: 65536
5151
5241
  },
5152
- "gemini-flash-lite-latest": {
5153
- id: "gemini-flash-lite-latest",
5154
- name: "Gemini Flash-Lite Latest",
5242
+ "gemini-flash-latest": {
5243
+ id: "gemini-flash-latest",
5244
+ name: "Gemini Flash Latest",
5155
5245
  api: "google-generative-ai",
5156
5246
  provider: "google",
5157
5247
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
5158
5248
  reasoning: true,
5159
5249
  input: ["text", "image"],
5160
5250
  cost: {
5161
- input: 0.3,
5162
- output: 2.5,
5163
- cacheRead: 0.03,
5251
+ input: 0.75,
5252
+ output: 3.75,
5253
+ cacheRead: 0.075,
5164
5254
  cacheWrite: 0
5165
5255
  },
5166
5256
  contextWindow: 1048576,
5167
5257
  maxTokens: 65536
5168
5258
  },
5169
- "gemini-robotics-er-1.6-preview": {
5170
- id: "gemini-robotics-er-1.6-preview",
5171
- name: "Gemini Robotics-ER 1.6 Preview",
5259
+ "gemini-flash-lite-latest": {
5260
+ id: "gemini-flash-lite-latest",
5261
+ name: "Gemini Flash-Lite Latest",
5172
5262
  api: "google-generative-ai",
5173
5263
  provider: "google",
5174
5264
  baseUrl: "https://generativelanguage.googleapis.com/v1beta",
5175
5265
  reasoning: true,
5176
5266
  input: ["text", "image"],
5177
5267
  cost: {
5178
- input: 1,
5179
- output: 5,
5180
- cacheRead: 0,
5268
+ input: 0.3,
5269
+ output: 2.5,
5270
+ cacheRead: 0.03,
5181
5271
  cacheWrite: 0
5182
5272
  },
5183
- contextWindow: 131072,
5273
+ contextWindow: 1048576,
5184
5274
  maxTokens: 65536
5185
5275
  },
5186
5276
  "gemma-4-26b-a4b-it": {
@@ -5549,6 +5639,23 @@ var MODELS = {
5549
5639
  },
5550
5640
  contextWindow: 131072,
5551
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
5552
5659
  }
5553
5660
  },
5554
5661
  "huggingface": {
@@ -6236,6 +6343,24 @@ var MODELS = {
6236
6343
  contextWindow: 1048576,
6237
6344
  maxTokens: 384e3
6238
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
+ },
6239
6364
  "deepseek-ai/DeepSeek-V4-Pro": {
6240
6365
  id: "deepseek-ai/DeepSeek-V4-Pro",
6241
6366
  name: "DeepSeek V4 Pro",
@@ -6559,7 +6684,7 @@ var MODELS = {
6559
6684
  cacheWrite: 0
6560
6685
  },
6561
6686
  contextWindow: 262144,
6562
- maxTokens: 64e3
6687
+ maxTokens: 128e3
6563
6688
  },
6564
6689
  "thinkingmachines/Inkling": {
6565
6690
  id: "thinkingmachines/Inkling",
@@ -8867,6 +8992,24 @@ var MODELS = {
8867
8992
  contextWindow: 1e6,
8868
8993
  maxTokens: 128e3
8869
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
+ },
8870
9013
  "claude-haiku-4-5": {
8871
9014
  id: "claude-haiku-4-5",
8872
9015
  name: "Claude Haiku 4.5",
@@ -9189,6 +9332,24 @@ var MODELS = {
9189
9332
  contextWindow: 1048576,
9190
9333
  maxTokens: 65536
9191
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
+ },
9192
9353
  "glm-5": {
9193
9354
  id: "glm-5",
9194
9355
  name: "GLM-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",
@@ -10066,7 +10244,7 @@ var MODELS = {
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",
@@ -10618,24 +10831,6 @@ 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
10834
  "anthropic/claude-opus-4.8": {
10640
10835
  id: "anthropic/claude-opus-4.8",
10641
10836
  name: "Anthropic: Claude Opus 4.8",
@@ -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",
@@ -10690,33 +10867,15 @@ 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)",
10870
+ "anthropic/claude-sonnet-4": {
10871
+ id: "anthropic/claude-sonnet-4",
10872
+ name: "Anthropic: Claude Sonnet 4",
10696
10873
  api: "openai-completions",
10697
10874
  provider: "openrouter",
10698
10875
  baseUrl: "https://openrouter.ai/api/v1",
10876
+ compat: { "supportsReasoningEffort": false },
10699
10877
  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
- "anthropic/claude-sonnet-4": {
10712
- id: "anthropic/claude-sonnet-4",
10713
- name: "Anthropic: Claude Sonnet 4",
10714
- api: "openai-completions",
10715
- provider: "openrouter",
10716
- baseUrl: "https://openrouter.ai/api/v1",
10717
- compat: { "supportsReasoningEffort": false },
10718
- reasoning: true,
10719
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null },
10878
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null },
10720
10879
  input: ["text", "image"],
10721
10880
  cost: {
10722
10881
  input: 3,
@@ -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: 0.088606,
11145
- output: 0.177212,
11146
- cacheRead: 0.017721200000000003,
11303
+ input: 0.08399999999999999,
11304
+ output: 0.16799999999999998,
11305
+ cacheRead: 0.016800000000000002,
11147
11306
  cacheWrite: 0
11148
11307
  },
11149
11308
  contextWindow: 1048576,
@@ -11179,9 +11338,9 @@ var MODELS = {
11179
11338
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max", "max": null },
11180
11339
  input: ["text", "image"],
11181
11340
  cost: {
11182
- input: 0.44,
11183
- output: 1.32,
11184
- cacheRead: 0.014,
11341
+ input: 0.22,
11342
+ output: 0.66,
11343
+ cacheRead: 7e-3,
11185
11344
  cacheWrite: 0
11186
11345
  },
11187
11346
  contextWindow: 1048576,
@@ -11198,13 +11357,13 @@ 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: 1.5999999999999999,
11202
- output: 3.1999999999999997,
11203
- cacheRead: 0.135,
11360
+ input: 1.035996,
11361
+ output: 2.071992,
11362
+ cacheRead: 0.086333,
11204
11363
  cacheWrite: 0
11205
11364
  },
11206
11365
  contextWindow: 1048576,
11207
- maxTokens: 393216
11366
+ maxTokens: 384e3
11208
11367
  },
11209
11368
  "deepseek/deepseek-v4-pro-0813": {
11210
11369
  id: "deepseek/deepseek-v4-pro-0813",
@@ -11217,9 +11376,9 @@ var MODELS = {
11217
11376
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max", "max": null },
11218
11377
  input: ["text"],
11219
11378
  cost: {
11220
- input: 1.32,
11221
- output: 3.9600000000000004,
11222
- cacheRead: 0.044,
11379
+ input: 0.66,
11380
+ output: 1.9800000000000002,
11381
+ cacheRead: 0.022,
11223
11382
  cacheWrite: 0
11224
11383
  },
11225
11384
  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",
@@ -11684,9 +11897,9 @@ var MODELS = {
11684
11897
  contextWindow: 262144,
11685
11898
  maxTokens: 32768
11686
11899
  },
11687
- "inclusionai/ling-3.0-flash-fin:free": {
11688
- id: "inclusionai/ling-3.0-flash-fin:free",
11689
- name: "Ling 3.0 Flash Fin (free)",
11900
+ "inclusionai/ling-3.0-flash-fin": {
11901
+ id: "inclusionai/ling-3.0-flash-fin",
11902
+ name: "Ling 3.0 Flash Fin",
11690
11903
  api: "openai-completions",
11691
11904
  provider: "openrouter",
11692
11905
  baseUrl: "https://openrouter.ai/api/v1",
@@ -11695,30 +11908,32 @@ var MODELS = {
11695
11908
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null },
11696
11909
  input: ["text"],
11697
11910
  cost: {
11698
- input: 0,
11699
- output: 0,
11700
- cacheRead: 0,
11911
+ input: 0.06,
11912
+ output: 0.18,
11913
+ cacheRead: 0.012,
11701
11914
  cacheWrite: 0
11702
11915
  },
11703
11916
  contextWindow: 262144,
11704
- maxTokens: 32768
11917
+ maxTokens: 235929
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",
11919
+ "inclusionai/ling-3.0-flash-fin:free": {
11920
+ id: "inclusionai/ling-3.0-flash-fin:free",
11921
+ name: "Ling 3.0 Flash Fin (free)",
11709
11922
  api: "openai-completions",
11710
11923
  provider: "openrouter",
11711
11924
  baseUrl: "https://openrouter.ai/api/v1",
11712
- reasoning: false,
11925
+ compat: { "supportsReasoningEffort": false },
11926
+ reasoning: true,
11927
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null },
11713
11928
  input: ["text"],
11714
11929
  cost: {
11715
- input: 0.15,
11716
- output: 0.6,
11717
- cacheRead: 0.03,
11930
+ input: 0,
11931
+ output: 0,
11932
+ cacheRead: 0,
11718
11933
  cacheWrite: 0
11719
11934
  },
11720
- contextWindow: 256e3,
11721
- maxTokens: 8e4
11935
+ contextWindow: 262144,
11936
+ maxTokens: 32768
11722
11937
  },
11723
11938
  "kwaipilot/kat-coder-pro-v2": {
11724
11939
  id: "kwaipilot/kat-coder-pro-v2",
@@ -11735,7 +11950,7 @@ var MODELS = {
11735
11950
  cacheWrite: 0
11736
11951
  },
11737
11952
  contextWindow: 262144,
11738
- maxTokens: 8e4
11953
+ maxTokens: 144e3
11739
11954
  },
11740
11955
  "kwaipilot/kat-coder-pro-v2.5": {
11741
11956
  id: "kwaipilot/kat-coder-pro-v2.5",
@@ -11752,7 +11967,7 @@ var MODELS = {
11752
11967
  cacheWrite: 0
11753
11968
  },
11754
11969
  contextWindow: 262144,
11755
- maxTokens: 8e4
11970
+ maxTokens: 235929
11756
11971
  },
11757
11972
  "liquid/lfm-2.5-2.6b:free": {
11758
11973
  id: "liquid/lfm-2.5-2.6b:free",
@@ -11835,13 +12050,13 @@ var MODELS = {
11835
12050
  reasoning: false,
11836
12051
  input: ["text"],
11837
12052
  cost: {
11838
- input: 0.71,
11839
- output: 0.71,
11840
- cacheRead: 0.71,
12053
+ input: 0.09999999999999999,
12054
+ output: 0.32,
12055
+ cacheRead: 0,
11841
12056
  cacheWrite: 0
11842
12057
  },
11843
12058
  contextWindow: 131072,
11844
- maxTokens: 115200
12059
+ maxTokens: 16384
11845
12060
  },
11846
12061
  "meta-llama/llama-4-maverick": {
11847
12062
  id: "meta-llama/llama-4-maverick",
@@ -11869,13 +12084,13 @@ var MODELS = {
11869
12084
  reasoning: false,
11870
12085
  input: ["text", "image"],
11871
12086
  cost: {
11872
- input: 0.11,
11873
- output: 0.33999999999999997,
11874
- cacheRead: 0.055,
12087
+ input: 0.09999999999999999,
12088
+ output: 0.3,
12089
+ cacheRead: 0,
11875
12090
  cacheWrite: 0
11876
12091
  },
11877
12092
  contextWindow: 1310720,
11878
- maxTokens: 8192
12093
+ maxTokens: 16384
11879
12094
  },
11880
12095
  "meta/muse-glimmer-30b": {
11881
12096
  id: "meta/muse-glimmer-30b",
@@ -11888,12 +12103,12 @@ var MODELS = {
11888
12103
  input: ["text", "image"],
11889
12104
  cost: {
11890
12105
  input: 0.3,
11891
- output: 1.2,
12106
+ output: 1.1,
11892
12107
  cacheRead: 0.04,
11893
12108
  cacheWrite: 0
11894
12109
  },
11895
12110
  contextWindow: 131072,
11896
- maxTokens: 16384
12111
+ maxTokens: 117964
11897
12112
  },
11898
12113
  "meta/muse-spark-1.1": {
11899
12114
  id: "meta/muse-spark-1.1",
@@ -11949,6 +12164,42 @@ var MODELS = {
11949
12164
  contextWindow: 1048576,
11950
12165
  maxTokens: 943718
11951
12166
  },
12167
+ "meta/muse-spark-1.3": {
12168
+ id: "meta/muse-spark-1.3",
12169
+ name: "Meta: Muse Spark 1.3",
12170
+ api: "openai-completions",
12171
+ provider: "openrouter",
12172
+ baseUrl: "https://openrouter.ai/api/v1",
12173
+ reasoning: true,
12174
+ thinkingLevelMap: { "off": null, "minimal": "minimal", "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": null },
12175
+ input: ["text", "image"],
12176
+ cost: {
12177
+ input: 1.25,
12178
+ output: 4.25,
12179
+ cacheRead: 0.15,
12180
+ cacheWrite: 0
12181
+ },
12182
+ contextWindow: 1048576,
12183
+ maxTokens: 943718
12184
+ },
12185
+ "meta/muse-spark-1.3-contributor": {
12186
+ id: "meta/muse-spark-1.3-contributor",
12187
+ name: "Meta: Muse Spark 1.3 Contributor",
12188
+ api: "openai-completions",
12189
+ provider: "openrouter",
12190
+ baseUrl: "https://openrouter.ai/api/v1",
12191
+ reasoning: true,
12192
+ thinkingLevelMap: { "off": null, "minimal": "minimal", "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": null },
12193
+ input: ["text", "image"],
12194
+ cost: {
12195
+ input: 0.09999999999999999,
12196
+ output: 0.19999999999999998,
12197
+ cacheRead: 2e-3,
12198
+ cacheWrite: 0
12199
+ },
12200
+ contextWindow: 1048576,
12201
+ maxTokens: 943718
12202
+ },
11952
12203
  "minimax/minimax-m1": {
11953
12204
  id: "minimax/minimax-m1",
11954
12205
  name: "MiniMax: MiniMax M1",
@@ -12571,11 +12822,11 @@ var MODELS = {
12571
12822
  cost: {
12572
12823
  input: 0.049999999999999996,
12573
12824
  output: 0.19999999999999998,
12574
- cacheRead: 0.024999999999999998,
12825
+ cacheRead: 0.03,
12575
12826
  cacheWrite: 0
12576
12827
  },
12577
12828
  contextWindow: 262144,
12578
- maxTokens: 228e3
12829
+ maxTokens: 235929
12579
12830
  },
12580
12831
  "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
12581
12832
  id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
@@ -12642,13 +12893,13 @@ var MODELS = {
12642
12893
  thinkingLevelMap: { "minimal": null, "low": null, "medium": "medium", "high": "high", "xhigh": null, "max": null },
12643
12894
  input: ["text"],
12644
12895
  cost: {
12645
- input: 0.5,
12646
- output: 2.2,
12647
- cacheRead: 0.09999999999999999,
12896
+ input: 0.6,
12897
+ output: 2.4,
12898
+ cacheRead: 0.12,
12648
12899
  cacheWrite: 0
12649
12900
  },
12650
12901
  contextWindow: 262144,
12651
- maxTokens: 16384
12902
+ maxTokens: 182520
12652
12903
  },
12653
12904
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
12654
12905
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -14140,13 +14391,13 @@ var MODELS = {
14140
14391
  reasoning: false,
14141
14392
  input: ["text"],
14142
14393
  cost: {
14143
- input: 0.09,
14394
+ input: 0.09999999999999999,
14144
14395
  output: 1.1,
14145
- cacheRead: 0,
14396
+ cacheRead: 0.07,
14146
14397
  cacheWrite: 0
14147
14398
  },
14148
14399
  contextWindow: 262144,
14149
- maxTokens: 16384
14400
+ maxTokens: 235929
14150
14401
  },
14151
14402
  "qwen/qwen3-next-80b-a3b-thinking": {
14152
14403
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -14360,13 +14611,13 @@ var MODELS = {
14360
14611
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null },
14361
14612
  input: ["text", "image"],
14362
14613
  cost: {
14363
- input: 0.39,
14364
- output: 2.34,
14365
- cacheRead: 0,
14614
+ input: 0.55,
14615
+ output: 3.5,
14616
+ cacheRead: 0.22499999999999998,
14366
14617
  cacheWrite: 0
14367
14618
  },
14368
14619
  contextWindow: 262144,
14369
- maxTokens: 65536
14620
+ maxTokens: 235929
14370
14621
  },
14371
14622
  "qwen/qwen3.5-9b": {
14372
14623
  id: "qwen/qwen3.5-9b",
@@ -14803,9 +15054,9 @@ var MODELS = {
14803
15054
  thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": null },
14804
15055
  input: ["text"],
14805
15056
  cost: {
14806
- input: 0.13199999999999998,
14807
- output: 0.5279999999999999,
14808
- cacheRead: 0.032999999999999995,
15057
+ input: 0.0825,
15058
+ output: 0.33,
15059
+ cacheRead: 0.020625,
14809
15060
  cacheWrite: 0
14810
15061
  },
14811
15062
  contextWindow: 262144,
@@ -15172,13 +15423,13 @@ var MODELS = {
15172
15423
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null },
15173
15424
  input: ["text"],
15174
15425
  cost: {
15175
- input: 0.43,
15176
- output: 1.75,
15177
- cacheRead: 0.08,
15426
+ input: 0.55,
15427
+ output: 2.2,
15428
+ cacheRead: 0.11,
15178
15429
  cacheWrite: 0
15179
15430
  },
15180
15431
  contextWindow: 204800,
15181
- maxTokens: 16384
15432
+ maxTokens: 131072
15182
15433
  },
15183
15434
  "z-ai/glm-4.6v": {
15184
15435
  id: "z-ai/glm-4.6v",
@@ -15304,13 +15555,13 @@ var MODELS = {
15304
15555
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh", "max": null },
15305
15556
  input: ["text"],
15306
15557
  cost: {
15307
- input: 1.19,
15308
- output: 3.74,
15309
- cacheRead: 0.221,
15558
+ input: 0.966,
15559
+ output: 3.036,
15560
+ cacheRead: 0.1932,
15310
15561
  cacheWrite: 0
15311
15562
  },
15312
15563
  contextWindow: 1048576,
15313
- maxTokens: 262144
15564
+ maxTokens: 131072
15314
15565
  },
15315
15566
  "z-ai/glm-5.2:free": {
15316
15567
  id: "z-ai/glm-5.2:free",
@@ -15342,11 +15593,11 @@ var MODELS = {
15342
15593
  cost: {
15343
15594
  input: 1.4,
15344
15595
  output: 4.4,
15345
- cacheRead: 0.26,
15596
+ cacheRead: 0.14,
15346
15597
  cacheWrite: 0
15347
15598
  },
15348
15599
  contextWindow: 1310720,
15349
- maxTokens: 131072
15600
+ maxTokens: 262144
15350
15601
  },
15351
15602
  "z-ai/glm-5.3-flash": {
15352
15603
  id: "z-ai/glm-5.3-flash",
@@ -15397,7 +15648,7 @@ var MODELS = {
15397
15648
  cost: {
15398
15649
  input: 10,
15399
15650
  output: 50,
15400
- cacheRead: 1,
15651
+ cacheRead: 0.25,
15401
15652
  cacheWrite: 12.5
15402
15653
  },
15403
15654
  contextWindow: 1e6,
@@ -15469,7 +15720,7 @@ var MODELS = {
15469
15720
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max", "max": null },
15470
15721
  input: ["text"],
15471
15722
  cost: {
15472
- input: 0.03,
15723
+ input: 0.049999999999999996,
15473
15724
  output: 0.16,
15474
15725
  cacheRead: 0.013000000000000001,
15475
15726
  cacheWrite: 0
@@ -15585,6 +15836,24 @@ var MODELS = {
15585
15836
  contextWindow: 5e5,
15586
15837
  maxTokens: 45e4
15587
15838
  },
15839
+ "~z-ai/glm-flash-latest": {
15840
+ id: "~z-ai/glm-flash-latest",
15841
+ name: "Z.ai: GLM Flash Latest",
15842
+ api: "openai-completions",
15843
+ provider: "openrouter",
15844
+ baseUrl: "https://openrouter.ai/api/v1",
15845
+ reasoning: true,
15846
+ thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max" },
15847
+ input: ["text", "image"],
15848
+ cost: {
15849
+ input: 0.075,
15850
+ output: 0.25,
15851
+ cacheRead: 0.015,
15852
+ cacheWrite: 0
15853
+ },
15854
+ contextWindow: 1310720,
15855
+ maxTokens: 943718
15856
+ },
15588
15857
  "~z-ai/glm-latest": {
15589
15858
  id: "~z-ai/glm-latest",
15590
15859
  name: "Z.ai: GLM Latest",
@@ -15595,13 +15864,13 @@ var MODELS = {
15595
15864
  thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max" },
15596
15865
  input: ["text"],
15597
15866
  cost: {
15598
- input: 1.1875,
15599
- output: 4.18,
15600
- cacheRead: 0.24699999999999997,
15867
+ input: 1.1340000000000001,
15868
+ output: 3.564,
15869
+ cacheRead: 0.1863,
15601
15870
  cacheWrite: 0
15602
15871
  },
15603
15872
  contextWindow: 1310720,
15604
- maxTokens: 131072
15873
+ maxTokens: 943718
15605
15874
  }
15606
15875
  },
15607
15876
  "prime-inference": {
@@ -15857,7 +16126,7 @@ var MODELS = {
15857
16126
  cacheWrite: 0
15858
16127
  },
15859
16128
  contextWindow: 163840,
15860
- maxTokens: 16e3
16129
+ maxTokens: 16384
15861
16130
  },
15862
16131
  "deepseek/deepseek-chat-v3-0324": {
15863
16132
  id: "deepseek/deepseek-chat-v3-0324",
@@ -15894,7 +16163,7 @@ var MODELS = {
15894
16163
  cacheWrite: 0
15895
16164
  },
15896
16165
  contextWindow: 163840,
15897
- maxTokens: 144900
16166
+ maxTokens: 32768
15898
16167
  },
15899
16168
  "deepseek/deepseek-v3.1-terminus": {
15900
16169
  id: "deepseek/deepseek-v3.1-terminus",
@@ -16010,7 +16279,7 @@ var MODELS = {
16010
16279
  cacheWrite: 0
16011
16280
  },
16012
16281
  contextWindow: 1048576,
16013
- maxTokens: 393216,
16282
+ maxTokens: 384e3,
16014
16283
  featured: true
16015
16284
  },
16016
16285
  "google/gemini-2.5-flash": {
@@ -16235,7 +16504,7 @@ var MODELS = {
16235
16504
  cacheWrite: 0
16236
16505
  },
16237
16506
  contextWindow: 131072,
16238
- maxTokens: 115200
16507
+ maxTokens: 16384
16239
16508
  },
16240
16509
  "meta-llama/llama-4-maverick": {
16241
16510
  id: "meta-llama/llama-4-maverick",
@@ -16518,7 +16787,7 @@ var MODELS = {
16518
16787
  cacheWrite: 0
16519
16788
  },
16520
16789
  contextWindow: 262144,
16521
- maxTokens: 228e3,
16790
+ maxTokens: 235929,
16522
16791
  featured: true
16523
16792
  },
16524
16793
  "nvidia/nemotron-3-super-120b-a12b": {
@@ -17526,7 +17795,7 @@ var MODELS = {
17526
17795
  cacheWrite: 0
17527
17796
  },
17528
17797
  contextWindow: 204800,
17529
- maxTokens: 16384
17798
+ maxTokens: 131072
17530
17799
  },
17531
17800
  "z-ai/glm-4.7": {
17532
17801
  id: "z-ai/glm-4.7",
@@ -17623,7 +17892,7 @@ var MODELS = {
17623
17892
  cacheWrite: 0
17624
17893
  },
17625
17894
  contextWindow: 1048576,
17626
- maxTokens: 262144,
17895
+ maxTokens: 131072,
17627
17896
  featured: true
17628
17897
  },
17629
17898
  "z-ai/glm-5.3": {
@@ -17643,7 +17912,7 @@ var MODELS = {
17643
17912
  cacheWrite: 0
17644
17913
  },
17645
17914
  contextWindow: 1310720,
17646
- maxTokens: 131072
17915
+ maxTokens: 262144
17647
17916
  },
17648
17917
  "z-ai/glm-5.3-flash": {
17649
17918
  id: "z-ai/glm-5.3-flash",
@@ -18142,6 +18411,23 @@ var MODELS = {
18142
18411
  contextWindow: 991e3,
18143
18412
  maxTokens: 128e3
18144
18413
  },
18414
+ "alibaba/qwen3.8-flash-next": {
18415
+ id: "alibaba/qwen3.8-flash-next",
18416
+ name: "Qwen 3.8 Flash Next",
18417
+ api: "anthropic-messages",
18418
+ provider: "vercel-ai-gateway",
18419
+ baseUrl: "https://ai-gateway.vercel.sh",
18420
+ reasoning: true,
18421
+ input: ["text", "image"],
18422
+ cost: {
18423
+ input: 0.12,
18424
+ output: 0.39999999999999997,
18425
+ cacheRead: 0.01,
18426
+ cacheWrite: 0
18427
+ },
18428
+ contextWindow: 1048576,
18429
+ maxTokens: 1048576
18430
+ },
18145
18431
  "alibaba/qwen3.8-max": {
18146
18432
  id: "alibaba/qwen3.8-max",
18147
18433
  name: "Qwen 3.8 Max",
@@ -18159,6 +18445,23 @@ var MODELS = {
18159
18445
  contextWindow: 1e6,
18160
18446
  maxTokens: 128e3
18161
18447
  },
18448
+ "alibaba/qwen3.8-max-0902": {
18449
+ id: "alibaba/qwen3.8-max-0902",
18450
+ name: "Qwen3.8 Max 0902",
18451
+ api: "anthropic-messages",
18452
+ provider: "vercel-ai-gateway",
18453
+ baseUrl: "https://ai-gateway.vercel.sh",
18454
+ reasoning: true,
18455
+ input: ["text", "image"],
18456
+ cost: {
18457
+ input: 2,
18458
+ output: 6,
18459
+ cacheRead: 0.25,
18460
+ cacheWrite: 2.5
18461
+ },
18462
+ contextWindow: 991e3,
18463
+ maxTokens: 128e3
18464
+ },
18162
18465
  "amazon/nova-2-lite": {
18163
18466
  id: "amazon/nova-2-lite",
18164
18467
  name: "Nova 2 Lite",
@@ -18262,6 +18565,24 @@ var MODELS = {
18262
18565
  contextWindow: 1e6,
18263
18566
  maxTokens: 128e3
18264
18567
  },
18568
+ "anthropic/claude-fable-5.1": {
18569
+ id: "anthropic/claude-fable-5.1",
18570
+ name: "Claude Fable 5.1",
18571
+ api: "anthropic-messages",
18572
+ provider: "vercel-ai-gateway",
18573
+ baseUrl: "https://ai-gateway.vercel.sh",
18574
+ reasoning: true,
18575
+ thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
18576
+ input: ["text", "image"],
18577
+ cost: {
18578
+ input: 10,
18579
+ output: 50,
18580
+ cacheRead: 0.25,
18581
+ cacheWrite: 12.5
18582
+ },
18583
+ contextWindow: 1e6,
18584
+ maxTokens: 128e3
18585
+ },
18265
18586
  "anthropic/claude-haiku-4.5": {
18266
18587
  id: "anthropic/claude-haiku-4.5",
18267
18588
  name: "Claude Haiku 4.5",
@@ -18576,23 +18897,6 @@ var MODELS = {
18576
18897
  contextWindow: 128e3,
18577
18898
  maxTokens: 8192
18578
18899
  },
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
18900
  "deepseek/deepseek-v3.1": {
18597
18901
  id: "deepseek/deepseek-v3.1",
18598
18902
  name: "DeepSeek V3.1",
@@ -18709,8 +19013,8 @@ var MODELS = {
18709
19013
  cacheRead: 7e-3,
18710
19014
  cacheWrite: 0
18711
19015
  },
18712
- contextWindow: 1e6,
18713
- maxTokens: 384e3
19016
+ contextWindow: 1048576,
19017
+ maxTokens: 1048576
18714
19018
  },
18715
19019
  "deepseek/deepseek-v4-pro": {
18716
19020
  id: "deepseek/deepseek-v4-pro",
@@ -18916,6 +19220,23 @@ var MODELS = {
18916
19220
  contextWindow: 1e6,
18917
19221
  maxTokens: 65536
18918
19222
  },
19223
+ "google/gemini-3.8-flash": {
19224
+ id: "google/gemini-3.8-flash",
19225
+ name: "Gemini 3.8 Flash",
19226
+ api: "anthropic-messages",
19227
+ provider: "vercel-ai-gateway",
19228
+ baseUrl: "https://ai-gateway.vercel.sh",
19229
+ reasoning: true,
19230
+ input: ["text", "image"],
19231
+ cost: {
19232
+ input: 0.75,
19233
+ output: 3.75,
19234
+ cacheRead: 0.075,
19235
+ cacheWrite: 0
19236
+ },
19237
+ contextWindow: 1e6,
19238
+ maxTokens: 65536
19239
+ },
18919
19240
  "google/gemma-4-26b-a4b-it": {
18920
19241
  id: "google/gemma-4-26b-a4b-it",
18921
19242
  name: "Google Gemma 4 26B A4B",
@@ -19273,6 +19594,40 @@ var MODELS = {
19273
19594
  contextWindow: 1048576,
19274
19595
  maxTokens: 1048576
19275
19596
  },
19597
+ "meta/muse-spark-1.3": {
19598
+ id: "meta/muse-spark-1.3",
19599
+ name: "Muse Spark 1.3",
19600
+ api: "anthropic-messages",
19601
+ provider: "vercel-ai-gateway",
19602
+ baseUrl: "https://ai-gateway.vercel.sh",
19603
+ reasoning: true,
19604
+ input: ["text", "image"],
19605
+ cost: {
19606
+ input: 1.25,
19607
+ output: 4.25,
19608
+ cacheRead: 0.15,
19609
+ cacheWrite: 0
19610
+ },
19611
+ contextWindow: 1048576,
19612
+ maxTokens: 1048576
19613
+ },
19614
+ "meta/muse-spark-1.3-contributor": {
19615
+ id: "meta/muse-spark-1.3-contributor",
19616
+ name: "Muse Spark 1.3 Contributor",
19617
+ api: "anthropic-messages",
19618
+ provider: "vercel-ai-gateway",
19619
+ baseUrl: "https://ai-gateway.vercel.sh",
19620
+ reasoning: true,
19621
+ input: ["text", "image"],
19622
+ cost: {
19623
+ input: 0.09999999999999999,
19624
+ output: 0.19999999999999998,
19625
+ cacheRead: 2e-3,
19626
+ cacheWrite: 0
19627
+ },
19628
+ contextWindow: 1048576,
19629
+ maxTokens: 1048576
19630
+ },
19276
19631
  "minimax/minimax-m2": {
19277
19632
  id: "minimax/minimax-m2",
19278
19633
  name: "MiniMax M2",
@@ -21268,6 +21623,23 @@ var MODELS = {
21268
21623
  contextWindow: 105e4,
21269
21624
  maxTokens: 131e3
21270
21625
  },
21626
+ "xiaomi/mimo-v2.5-pro-ultraspeed": {
21627
+ id: "xiaomi/mimo-v2.5-pro-ultraspeed",
21628
+ name: "MiMo V2.5 Pro UltraSpeed",
21629
+ api: "anthropic-messages",
21630
+ provider: "vercel-ai-gateway",
21631
+ baseUrl: "https://ai-gateway.vercel.sh",
21632
+ reasoning: true,
21633
+ input: ["text"],
21634
+ cost: {
21635
+ input: 1.305,
21636
+ output: 2.61,
21637
+ cacheRead: 0.0108,
21638
+ cacheWrite: 0
21639
+ },
21640
+ contextWindow: 1048576,
21641
+ maxTokens: 131072
21642
+ },
21271
21643
  "zai/glm-4.5": {
21272
21644
  id: "zai/glm-4.5",
21273
21645
  name: "GLM 4.5",
@@ -21481,14 +21853,31 @@ var MODELS = {
21481
21853
  reasoning: true,
21482
21854
  input: ["text"],
21483
21855
  cost: {
21484
- input: 1.4,
21485
- output: 4.4,
21486
- cacheRead: 0.14,
21856
+ input: 0.7,
21857
+ output: 2.2,
21858
+ cacheRead: 0.13,
21487
21859
  cacheWrite: 0
21488
21860
  },
21489
21861
  contextWindow: 1e6,
21490
21862
  maxTokens: 1e6
21491
21863
  },
21864
+ "zai/glm-5.3-fast": {
21865
+ id: "zai/glm-5.3-fast",
21866
+ name: "GLM 5.3 Fast",
21867
+ api: "anthropic-messages",
21868
+ provider: "vercel-ai-gateway",
21869
+ baseUrl: "https://ai-gateway.vercel.sh",
21870
+ reasoning: true,
21871
+ input: ["text"],
21872
+ cost: {
21873
+ input: 2.0999999999999996,
21874
+ output: 6.6000000000000005,
21875
+ cacheRead: 0.21,
21876
+ cacheWrite: 0
21877
+ },
21878
+ contextWindow: 1048576,
21879
+ maxTokens: 262144
21880
+ },
21492
21881
  "zai/glm-5.3-flash": {
21493
21882
  id: "zai/glm-5.3-flash",
21494
21883
  name: "GLM 5.3 Flash",
@@ -21506,6 +21895,23 @@ var MODELS = {
21506
21895
  contextWindow: 1e6,
21507
21896
  maxTokens: 131e3
21508
21897
  },
21898
+ "zai/glm-5.3-promo-50": {
21899
+ id: "zai/glm-5.3-promo-50",
21900
+ name: "GLM 5.3 (50% off)",
21901
+ api: "anthropic-messages",
21902
+ provider: "vercel-ai-gateway",
21903
+ baseUrl: "https://ai-gateway.vercel.sh",
21904
+ reasoning: true,
21905
+ input: ["text"],
21906
+ cost: {
21907
+ input: 0.7,
21908
+ output: 2.2,
21909
+ cacheRead: 0.13,
21910
+ cacheWrite: 0
21911
+ },
21912
+ contextWindow: 1048576,
21913
+ maxTokens: 1048576
21914
+ },
21509
21915
  "zai/glm-5v-turbo": {
21510
21916
  id: "zai/glm-5v-turbo",
21511
21917
  name: "GLM 5V Turbo",