@elyracode/ai 0.9.33 → 0.9.34

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.
@@ -89,6 +89,25 @@ export const MODELS = {
89
89
  contextWindow: 1000000,
90
90
  maxTokens: 128000,
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
+ thinkingType: "adaptive",
100
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
101
+ input: ["text", "image"],
102
+ cost: {
103
+ input: 10,
104
+ output: 50,
105
+ cacheRead: 0.25,
106
+ cacheWrite: 12.5,
107
+ },
108
+ contextWindow: 1000000,
109
+ maxTokens: 128000,
110
+ },
92
111
  "anthropic.claude-haiku-4-5-20251001-v1:0": {
93
112
  id: "anthropic.claude-haiku-4-5-20251001-v1:0",
94
113
  name: "Claude Haiku 4.5",
@@ -654,6 +673,25 @@ export const MODELS = {
654
673
  contextWindow: 1000000,
655
674
  maxTokens: 128000,
656
675
  },
676
+ "global.anthropic.claude-fable-5-1": {
677
+ id: "global.anthropic.claude-fable-5-1",
678
+ name: "Claude Fable 5.1 (Global)",
679
+ api: "bedrock-converse-stream",
680
+ provider: "amazon-bedrock",
681
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
682
+ reasoning: true,
683
+ thinkingType: "adaptive",
684
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
685
+ input: ["text", "image"],
686
+ cost: {
687
+ input: 10,
688
+ output: 50,
689
+ cacheRead: 0.25,
690
+ cacheWrite: 12.5,
691
+ },
692
+ contextWindow: 1000000,
693
+ maxTokens: 128000,
694
+ },
657
695
  "global.anthropic.claude-haiku-4-5-20251001-v1:0": {
658
696
  id: "global.anthropic.claude-haiku-4-5-20251001-v1:0",
659
697
  name: "Claude Haiku 4.5 (Global)",
@@ -1750,6 +1788,25 @@ export const MODELS = {
1750
1788
  contextWindow: 1000000,
1751
1789
  maxTokens: 128000,
1752
1790
  },
1791
+ "us.anthropic.claude-fable-5-1": {
1792
+ id: "us.anthropic.claude-fable-5-1",
1793
+ name: "Claude Fable 5.1 (US)",
1794
+ api: "bedrock-converse-stream",
1795
+ provider: "amazon-bedrock",
1796
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1797
+ reasoning: true,
1798
+ thinkingType: "adaptive",
1799
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
1800
+ input: ["text", "image"],
1801
+ cost: {
1802
+ input: 11,
1803
+ output: 55,
1804
+ cacheRead: 0.275,
1805
+ cacheWrite: 13.75,
1806
+ },
1807
+ contextWindow: 1000000,
1808
+ maxTokens: 128000,
1809
+ },
1753
1810
  "us.anthropic.claude-haiku-4-5-20251001-v1:0": {
1754
1811
  id: "us.anthropic.claude-haiku-4-5-20251001-v1:0",
1755
1812
  name: "Claude Haiku 4.5 (US)",
@@ -2124,6 +2181,25 @@ export const MODELS = {
2124
2181
  contextWindow: 1000000,
2125
2182
  maxTokens: 128000,
2126
2183
  },
2184
+ "claude-fable-5-1": {
2185
+ id: "claude-fable-5-1",
2186
+ name: "Claude Fable 5.1",
2187
+ api: "anthropic-messages",
2188
+ provider: "anthropic",
2189
+ baseUrl: "https://api.anthropic.com",
2190
+ reasoning: true,
2191
+ thinkingType: "adaptive",
2192
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
2193
+ input: ["text", "image"],
2194
+ cost: {
2195
+ input: 10,
2196
+ output: 50,
2197
+ cacheRead: 0.25,
2198
+ cacheWrite: 12.5,
2199
+ },
2200
+ contextWindow: 1000000,
2201
+ maxTokens: 128000,
2202
+ },
2127
2203
  "claude-haiku-4-5": {
2128
2204
  id: "claude-haiku-4-5",
2129
2205
  name: "Claude Haiku 4.5 (latest)",
@@ -3906,7 +3982,7 @@ export const MODELS = {
3906
3982
  cacheWrite: 0,
3907
3983
  },
3908
3984
  contextWindow: 1310720,
3909
- maxTokens: 1310720,
3985
+ maxTokens: 1048576,
3910
3986
  },
3911
3987
  },
3912
3988
  "deepseek": {
@@ -4018,6 +4094,23 @@ export const MODELS = {
4018
4094
  contextWindow: 1000000,
4019
4095
  maxTokens: 131072,
4020
4096
  },
4097
+ "accounts/fireworks/models/glm-5p3-flash": {
4098
+ id: "accounts/fireworks/models/glm-5p3-flash",
4099
+ name: "GLM 5.3 Flash",
4100
+ api: "anthropic-messages",
4101
+ provider: "fireworks",
4102
+ baseUrl: "https://api.fireworks.ai/inference",
4103
+ reasoning: true,
4104
+ input: ["text", "image"],
4105
+ cost: {
4106
+ input: 0.15,
4107
+ output: 0.5,
4108
+ cacheRead: 0.029,
4109
+ cacheWrite: 0,
4110
+ },
4111
+ contextWindow: 1000000,
4112
+ maxTokens: 131072,
4113
+ },
4021
4114
  "accounts/fireworks/models/gpt-oss-120b": {
4022
4115
  id: "accounts/fireworks/models/gpt-oss-120b",
4023
4116
  name: "GPT OSS 120B",
@@ -5203,23 +5296,6 @@ export const MODELS = {
5203
5296
  contextWindow: 1048576,
5204
5297
  maxTokens: 65536,
5205
5298
  },
5206
- "gemini-robotics-er-1.6-preview": {
5207
- id: "gemini-robotics-er-1.6-preview",
5208
- name: "Gemini Robotics-ER 1.6 Preview",
5209
- api: "google-generative-ai",
5210
- provider: "google",
5211
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
5212
- reasoning: true,
5213
- input: ["text", "image"],
5214
- cost: {
5215
- input: 1,
5216
- output: 5,
5217
- cacheRead: 0,
5218
- cacheWrite: 0,
5219
- },
5220
- contextWindow: 131072,
5221
- maxTokens: 65536,
5222
- },
5223
5299
  "gemma-4-26b-a4b-it": {
5224
5300
  id: "gemma-4-26b-a4b-it",
5225
5301
  name: "Gemma 4 26B A4B IT",
@@ -5587,6 +5663,23 @@ export const MODELS = {
5587
5663
  contextWindow: 131072,
5588
5664
  maxTokens: 16384,
5589
5665
  },
5666
+ "qwen/qwen3.8-27b": {
5667
+ id: "qwen/qwen3.8-27b",
5668
+ name: "Qwen3.8 27B",
5669
+ api: "openai-completions",
5670
+ provider: "groq",
5671
+ baseUrl: "https://api.groq.com/openai/v1",
5672
+ reasoning: true,
5673
+ input: ["text", "image"],
5674
+ cost: {
5675
+ input: 0.8,
5676
+ output: 4,
5677
+ cacheRead: 0,
5678
+ cacheWrite: 0,
5679
+ },
5680
+ contextWindow: 131042,
5681
+ maxTokens: 16384,
5682
+ },
5590
5683
  },
5591
5684
  "huggingface": {
5592
5685
  "MiniMaxAI/MiniMax-M2": {
@@ -8793,6 +8886,24 @@ export const MODELS = {
8793
8886
  contextWindow: 1000000,
8794
8887
  maxTokens: 128000,
8795
8888
  },
8889
+ "claude-fable-5-1": {
8890
+ id: "claude-fable-5-1",
8891
+ name: "Claude Fable 5.1",
8892
+ api: "anthropic-messages",
8893
+ provider: "opencode",
8894
+ baseUrl: "https://opencode.ai/zen",
8895
+ reasoning: true,
8896
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
8897
+ input: ["text", "image"],
8898
+ cost: {
8899
+ input: 10,
8900
+ output: 50,
8901
+ cacheRead: 0.25,
8902
+ cacheWrite: 12.5,
8903
+ },
8904
+ contextWindow: 1000000,
8905
+ maxTokens: 128000,
8906
+ },
8796
8907
  "claude-haiku-4-5": {
8797
8908
  id: "claude-haiku-4-5",
8798
8909
  name: "Claude Haiku 4.5",
@@ -9556,23 +9667,6 @@ export const MODELS = {
9556
9667
  contextWindow: 256000,
9557
9668
  maxTokens: 256000,
9558
9669
  },
9559
- "hy3-free": {
9560
- id: "hy3-free",
9561
- name: "Hy3 Free",
9562
- api: "openai-completions",
9563
- provider: "opencode",
9564
- baseUrl: "https://opencode.ai/zen/v1",
9565
- reasoning: true,
9566
- input: ["text"],
9567
- cost: {
9568
- input: 0,
9569
- output: 0,
9570
- cacheRead: 0,
9571
- cacheWrite: 0,
9572
- },
9573
- contextWindow: 190000,
9574
- maxTokens: 64000,
9575
- },
9576
9670
  "kimi-k2.5": {
9577
9671
  id: "kimi-k2.5",
9578
9672
  name: "Kimi K2.5",
@@ -9992,16 +10086,16 @@ export const MODELS = {
9992
10086
  },
9993
10087
  "hy3": {
9994
10088
  id: "hy3",
9995
- name: "Hy3 (8x usage)",
10089
+ name: "Hy3",
9996
10090
  api: "openai-completions",
9997
10091
  provider: "opencode-go",
9998
10092
  baseUrl: "https://opencode.ai/zen/go/v1",
9999
10093
  reasoning: true,
10000
10094
  input: ["text"],
10001
10095
  cost: {
10002
- input: 0.0175,
10003
- output: 0.0725,
10004
- cacheRead: 0.004375,
10096
+ input: 0.14,
10097
+ output: 0.58,
10098
+ cacheRead: 0.035,
10005
10099
  cacheWrite: 0,
10006
10100
  },
10007
10101
  contextWindow: 256000,
@@ -10436,6 +10530,24 @@ export const MODELS = {
10436
10530
  contextWindow: 1000000,
10437
10531
  maxTokens: 128000,
10438
10532
  },
10533
+ "anthropic/claude-fable-5.1": {
10534
+ id: "anthropic/claude-fable-5.1",
10535
+ name: "Anthropic: Claude Fable 5.1",
10536
+ api: "openai-completions",
10537
+ provider: "openrouter",
10538
+ baseUrl: "https://openrouter.ai/api/v1",
10539
+ reasoning: true,
10540
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
10541
+ input: ["text", "image"],
10542
+ cost: {
10543
+ input: 10,
10544
+ output: 50,
10545
+ cacheRead: 0.25,
10546
+ cacheWrite: 12.5,
10547
+ },
10548
+ contextWindow: 1000000,
10549
+ maxTokens: 128000,
10550
+ },
10439
10551
  "anthropic/claude-fable-5:batch": {
10440
10552
  id: "anthropic/claude-fable-5:batch",
10441
10553
  name: "Anthropic: Claude Fable 5 (batch)",
@@ -10627,24 +10739,6 @@ export const MODELS = {
10627
10739
  contextWindow: 1000000,
10628
10740
  maxTokens: 128000,
10629
10741
  },
10630
- "anthropic/claude-opus-4.7-fast": {
10631
- id: "anthropic/claude-opus-4.7-fast",
10632
- name: "Anthropic: Claude Opus 4.7 (Fast)",
10633
- api: "openai-completions",
10634
- provider: "openrouter",
10635
- baseUrl: "https://openrouter.ai/api/v1",
10636
- reasoning: true,
10637
- thinkingLevelMap: { "xhigh": "xhigh" },
10638
- input: ["text", "image"],
10639
- cost: {
10640
- input: 30,
10641
- output: 150,
10642
- cacheRead: 3,
10643
- cacheWrite: 37.5,
10644
- },
10645
- contextWindow: 1000000,
10646
- maxTokens: 128000,
10647
- },
10648
10742
  "anthropic/claude-opus-4.7:batch": {
10649
10743
  id: "anthropic/claude-opus-4.7:batch",
10650
10744
  name: "Anthropic: Claude Opus 4.7 (batch)",
@@ -10681,24 +10775,6 @@ export const MODELS = {
10681
10775
  contextWindow: 1000000,
10682
10776
  maxTokens: 128000,
10683
10777
  },
10684
- "anthropic/claude-opus-4.8-fast": {
10685
- id: "anthropic/claude-opus-4.8-fast",
10686
- name: "Anthropic: Claude Opus 4.8 (Fast)",
10687
- api: "openai-completions",
10688
- provider: "openrouter",
10689
- baseUrl: "https://openrouter.ai/api/v1",
10690
- reasoning: true,
10691
- thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "max", "xhigh": "ultracode" },
10692
- input: ["text", "image"],
10693
- cost: {
10694
- input: 10,
10695
- output: 50,
10696
- cacheRead: 1,
10697
- cacheWrite: 12.5,
10698
- },
10699
- contextWindow: 1000000,
10700
- maxTokens: 128000,
10701
- },
10702
10778
  "anthropic/claude-opus-4.8:batch": {
10703
10779
  id: "anthropic/claude-opus-4.8:batch",
10704
10780
  name: "Anthropic: Claude Opus 4.8 (batch)",
@@ -10734,23 +10810,6 @@ export const MODELS = {
10734
10810
  contextWindow: 1000000,
10735
10811
  maxTokens: 128000,
10736
10812
  },
10737
- "anthropic/claude-opus-5-fast": {
10738
- id: "anthropic/claude-opus-5-fast",
10739
- name: "Claude Opus 5 (Fast)",
10740
- api: "openai-completions",
10741
- provider: "openrouter",
10742
- baseUrl: "https://openrouter.ai/api/v1",
10743
- reasoning: true,
10744
- input: ["text", "image"],
10745
- cost: {
10746
- input: 10,
10747
- output: 50,
10748
- cacheRead: 1,
10749
- cacheWrite: 12.5,
10750
- },
10751
- contextWindow: 1000000,
10752
- maxTokens: 128000,
10753
- },
10754
10813
  "anthropic/claude-opus-5:batch": {
10755
10814
  id: "anthropic/claude-opus-5:batch",
10756
10815
  name: "Claude Opus 5 (batch)",
@@ -10896,13 +10955,13 @@ export const MODELS = {
10896
10955
  reasoning: true,
10897
10956
  input: ["text"],
10898
10957
  cost: {
10899
- input: 0.22,
10900
- output: 0.85,
10958
+ input: 0.25,
10959
+ output: 0.7999999999999999,
10901
10960
  cacheRead: 0.06,
10902
10961
  cacheWrite: 0,
10903
10962
  },
10904
10963
  contextWindow: 262144,
10905
- maxTokens: 235929,
10964
+ maxTokens: 80000,
10906
10965
  },
10907
10966
  "auto": {
10908
10967
  id: "auto",
@@ -11221,9 +11280,9 @@ export const MODELS = {
11221
11280
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11222
11281
  input: ["text"],
11223
11282
  cost: {
11224
- input: 0.08316,
11225
- output: 0.16632,
11226
- cacheRead: 0.016632,
11283
+ input: 0.07322000000000001,
11284
+ output: 0.14644000000000001,
11285
+ cacheRead: 0.014644,
11227
11286
  cacheWrite: 0,
11228
11287
  },
11229
11288
  contextWindow: 1048576,
@@ -11240,9 +11299,9 @@ export const MODELS = {
11240
11299
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11241
11300
  input: ["text"],
11242
11301
  cost: {
11243
- input: 0.045,
11244
- output: 0.09,
11245
- cacheRead: 0.009,
11302
+ input: 0.065,
11303
+ output: 0.18,
11304
+ cacheRead: 0.016,
11246
11305
  cacheWrite: 0,
11247
11306
  },
11248
11307
  contextWindow: 1310720,
@@ -11297,13 +11356,13 @@ export const MODELS = {
11297
11356
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11298
11357
  input: ["text"],
11299
11358
  cost: {
11300
- input: 0.57942,
11301
- output: 1.15884,
11302
- cacheRead: 0.048285,
11359
+ input: 1.5999999999999999,
11360
+ output: 3.1999999999999997,
11361
+ cacheRead: 0.135,
11303
11362
  cacheWrite: 0,
11304
11363
  },
11305
11364
  contextWindow: 1048576,
11306
- maxTokens: 384000,
11365
+ maxTokens: 393216,
11307
11366
  },
11308
11367
  "deepseek/deepseek-v4-pro-0813": {
11309
11368
  id: "deepseek/deepseek-v4-pro-0813",
@@ -11921,6 +11980,23 @@ export const MODELS = {
11921
11980
  contextWindow: 131072,
11922
11981
  maxTokens: 117964,
11923
11982
  },
11983
+ "ibm-granite/granite-4.2-8b": {
11984
+ id: "ibm-granite/granite-4.2-8b",
11985
+ name: "IBM: Granite 4.2 8B",
11986
+ api: "openai-completions",
11987
+ provider: "openrouter",
11988
+ baseUrl: "https://openrouter.ai/api/v1",
11989
+ reasoning: true,
11990
+ input: ["text"],
11991
+ cost: {
11992
+ input: 0.09999999999999999,
11993
+ output: 0.15,
11994
+ cacheRead: 0.049999999999999996,
11995
+ cacheWrite: 0,
11996
+ },
11997
+ contextWindow: 131072,
11998
+ maxTokens: 117964,
11999
+ },
11924
12000
  "inception/mercury-2": {
11925
12001
  id: "inception/mercury-2",
11926
12002
  name: "Inception: Mercury 2",
@@ -11938,6 +12014,23 @@ export const MODELS = {
11938
12014
  contextWindow: 128000,
11939
12015
  maxTokens: 50000,
11940
12016
  },
12017
+ "inception/mercury-2.5-preview": {
12018
+ id: "inception/mercury-2.5-preview",
12019
+ name: "Inception: Mercury 2.5 Preview",
12020
+ api: "openai-completions",
12021
+ provider: "openrouter",
12022
+ baseUrl: "https://openrouter.ai/api/v1",
12023
+ reasoning: true,
12024
+ input: ["text"],
12025
+ cost: {
12026
+ input: 0.04,
12027
+ output: 0.15,
12028
+ cacheRead: 0.004,
12029
+ cacheWrite: 0,
12030
+ },
12031
+ contextWindow: 260000,
12032
+ maxTokens: 65536,
12033
+ },
11941
12034
  "inclusionai/ling-3.0-flash": {
11942
12035
  id: "inclusionai/ling-3.0-flash",
11943
12036
  name: "Ling-3.0-flash",
@@ -11972,39 +12065,22 @@ export const MODELS = {
11972
12065
  contextWindow: 262144,
11973
12066
  maxTokens: 32768,
11974
12067
  },
11975
- "kwaipilot/kat-coder-air-v2.5": {
11976
- id: "kwaipilot/kat-coder-air-v2.5",
11977
- name: "Kwaipilot: KAT-Coder-Air V2.5",
12068
+ "kwaipilot/kat-coder-pro-v2": {
12069
+ id: "kwaipilot/kat-coder-pro-v2",
12070
+ name: "Kwaipilot: KAT-Coder-Pro V2",
11978
12071
  api: "openai-completions",
11979
12072
  provider: "openrouter",
11980
12073
  baseUrl: "https://openrouter.ai/api/v1",
11981
12074
  reasoning: false,
11982
12075
  input: ["text"],
11983
12076
  cost: {
11984
- input: 0.15,
11985
- output: 0.6,
11986
- cacheRead: 0.03,
11987
- cacheWrite: 0,
11988
- },
11989
- contextWindow: 256000,
11990
- maxTokens: 80000,
11991
- },
11992
- "kwaipilot/kat-coder-pro-v2": {
11993
- id: "kwaipilot/kat-coder-pro-v2",
11994
- name: "Kwaipilot: KAT-Coder-Pro V2",
11995
- api: "openai-completions",
11996
- provider: "openrouter",
11997
- baseUrl: "https://openrouter.ai/api/v1",
11998
- reasoning: false,
11999
- input: ["text"],
12000
- cost: {
12001
- input: 0.3,
12002
- output: 1.2,
12003
- cacheRead: 0.06,
12077
+ input: 0.3,
12078
+ output: 1.2,
12079
+ cacheRead: 0.06,
12004
12080
  cacheWrite: 0,
12005
12081
  },
12006
12082
  contextWindow: 262144,
12007
- maxTokens: 80000,
12083
+ maxTokens: 144000,
12008
12084
  },
12009
12085
  "kwaipilot/kat-coder-pro-v2.5": {
12010
12086
  id: "kwaipilot/kat-coder-pro-v2.5",
@@ -12021,7 +12097,7 @@ export const MODELS = {
12021
12097
  cacheWrite: 0,
12022
12098
  },
12023
12099
  contextWindow: 262144,
12024
- maxTokens: 80000,
12100
+ maxTokens: 235929,
12025
12101
  },
12026
12102
  "liquid/lfm-2.5-2.6b:free": {
12027
12103
  id: "liquid/lfm-2.5-2.6b:free",
@@ -12118,12 +12194,12 @@ export const MODELS = {
12118
12194
  input: ["text", "image"],
12119
12195
  cost: {
12120
12196
  input: 0.19999999999999998,
12121
- output: 0.7999999999999999,
12197
+ output: 0.696,
12122
12198
  cacheRead: 0,
12123
12199
  cacheWrite: 0,
12124
12200
  },
12125
12201
  contextWindow: 1048576,
12126
- maxTokens: 16384,
12202
+ maxTokens: 115200,
12127
12203
  },
12128
12204
  "meta-llama/llama-4-scout": {
12129
12205
  id: "meta-llama/llama-4-scout",
@@ -12134,13 +12210,13 @@ export const MODELS = {
12134
12210
  reasoning: false,
12135
12211
  input: ["text", "image"],
12136
12212
  cost: {
12137
- input: 0.11,
12138
- output: 0.33999999999999997,
12139
- cacheRead: 0.055,
12213
+ input: 0.09999999999999999,
12214
+ output: 0.3,
12215
+ cacheRead: 0,
12140
12216
  cacheWrite: 0,
12141
12217
  },
12142
12218
  contextWindow: 1310720,
12143
- maxTokens: 8192,
12219
+ maxTokens: 16384,
12144
12220
  },
12145
12221
  "meta/muse-glimmer-30b": {
12146
12222
  id: "meta/muse-glimmer-30b",
@@ -12397,23 +12473,6 @@ export const MODELS = {
12397
12473
  contextWindow: 256000,
12398
12474
  maxTokens: 204800,
12399
12475
  },
12400
- "mistralai/codestral-2508:batch": {
12401
- id: "mistralai/codestral-2508:batch",
12402
- name: "Mistral: Codestral 2508 (batch)",
12403
- api: "openai-completions",
12404
- provider: "openrouter",
12405
- baseUrl: "https://openrouter.ai/api/v1",
12406
- reasoning: false,
12407
- input: ["text"],
12408
- cost: {
12409
- input: 0.3,
12410
- output: 0.8999999999999999,
12411
- cacheRead: 0.03,
12412
- cacheWrite: 0,
12413
- },
12414
- contextWindow: 256000,
12415
- maxTokens: 204800,
12416
- },
12417
12476
  "mistralai/devstral-2512": {
12418
12477
  id: "mistralai/devstral-2512",
12419
12478
  name: "Mistral: Devstral 2 2512",
@@ -12423,9 +12482,9 @@ export const MODELS = {
12423
12482
  reasoning: false,
12424
12483
  input: ["text"],
12425
12484
  cost: {
12426
- input: 0.44,
12427
- output: 2.2,
12428
- cacheRead: 0.044,
12485
+ input: 0.39999999999999997,
12486
+ output: 2,
12487
+ cacheRead: 0.04,
12429
12488
  cacheWrite: 0,
12430
12489
  },
12431
12490
  contextWindow: 262144,
@@ -12482,23 +12541,6 @@ export const MODELS = {
12482
12541
  contextWindow: 262144,
12483
12542
  maxTokens: 209715,
12484
12543
  },
12485
- "mistralai/ministral-8b-2512:batch": {
12486
- id: "mistralai/ministral-8b-2512:batch",
12487
- name: "Mistral: Ministral 3 8B 2512 (batch)",
12488
- api: "openai-completions",
12489
- provider: "openrouter",
12490
- baseUrl: "https://openrouter.ai/api/v1",
12491
- reasoning: false,
12492
- input: ["text", "image"],
12493
- cost: {
12494
- input: 0.15,
12495
- output: 0.15,
12496
- cacheRead: 0.015,
12497
- cacheWrite: 0,
12498
- },
12499
- contextWindow: 262144,
12500
- maxTokens: 209715,
12501
- },
12502
12544
  "mistralai/mistral-large": {
12503
12545
  id: "mistralai/mistral-large",
12504
12546
  name: "Mistral Large",
@@ -12550,23 +12592,6 @@ export const MODELS = {
12550
12592
  contextWindow: 262144,
12551
12593
  maxTokens: 209715,
12552
12594
  },
12553
- "mistralai/mistral-large-2512:batch": {
12554
- id: "mistralai/mistral-large-2512:batch",
12555
- name: "Mistral: Mistral Large 3 2512 (batch)",
12556
- api: "openai-completions",
12557
- provider: "openrouter",
12558
- baseUrl: "https://openrouter.ai/api/v1",
12559
- reasoning: false,
12560
- input: ["text", "image"],
12561
- cost: {
12562
- input: 0.5,
12563
- output: 1.5,
12564
- cacheRead: 0.049999999999999996,
12565
- cacheWrite: 0,
12566
- },
12567
- contextWindow: 262144,
12568
- maxTokens: 209715,
12569
- },
12570
12595
  "mistralai/mistral-medium-3": {
12571
12596
  id: "mistralai/mistral-medium-3",
12572
12597
  name: "Mistral: Mistral Medium 3",
@@ -12635,23 +12660,6 @@ export const MODELS = {
12635
12660
  contextWindow: 131072,
12636
12661
  maxTokens: 104857,
12637
12662
  },
12638
- "mistralai/mistral-medium-3.1:batch": {
12639
- id: "mistralai/mistral-medium-3.1:batch",
12640
- name: "Mistral: Mistral Medium 3.1 (batch)",
12641
- api: "openai-completions",
12642
- provider: "openrouter",
12643
- baseUrl: "https://openrouter.ai/api/v1",
12644
- reasoning: false,
12645
- input: ["text", "image"],
12646
- cost: {
12647
- input: 0.39999999999999997,
12648
- output: 2,
12649
- cacheRead: 0.04,
12650
- cacheWrite: 0,
12651
- },
12652
- contextWindow: 131072,
12653
- maxTokens: 104857,
12654
- },
12655
12663
  "mistralai/mistral-nemo": {
12656
12664
  id: "mistralai/mistral-nemo",
12657
12665
  name: "Mistral: Mistral Nemo",
@@ -12703,23 +12711,6 @@ export const MODELS = {
12703
12711
  contextWindow: 262144,
12704
12712
  maxTokens: 209715,
12705
12713
  },
12706
- "mistralai/mistral-small-2603:batch": {
12707
- id: "mistralai/mistral-small-2603:batch",
12708
- name: "Mistral: Mistral Small 4 (batch)",
12709
- api: "openai-completions",
12710
- provider: "openrouter",
12711
- baseUrl: "https://openrouter.ai/api/v1",
12712
- reasoning: true,
12713
- input: ["text", "image"],
12714
- cost: {
12715
- input: 0.15,
12716
- output: 0.6,
12717
- cacheRead: 0.015,
12718
- cacheWrite: 0,
12719
- },
12720
- contextWindow: 262144,
12721
- maxTokens: 209715,
12722
- },
12723
12714
  "mistralai/mistral-small-3.2-24b-instruct": {
12724
12715
  id: "mistralai/mistral-small-3.2-24b-instruct",
12725
12716
  name: "Mistral: Mistral Small 3.2 24B",
@@ -13145,6 +13136,23 @@ export const MODELS = {
13145
13136
  contextWindow: 16385,
13146
13137
  maxTokens: 4096,
13147
13138
  },
13139
+ "openai/gpt-3.5-turbo:batch": {
13140
+ id: "openai/gpt-3.5-turbo:batch",
13141
+ name: "OpenAI: GPT-3.5 Turbo (batch)",
13142
+ api: "openai-completions",
13143
+ provider: "openrouter",
13144
+ baseUrl: "https://openrouter.ai/api/v1",
13145
+ reasoning: false,
13146
+ input: ["text"],
13147
+ cost: {
13148
+ input: 0.25,
13149
+ output: 0.75,
13150
+ cacheRead: 0,
13151
+ cacheWrite: 0,
13152
+ },
13153
+ contextWindow: 16385,
13154
+ maxTokens: 4096,
13155
+ },
13148
13156
  "openai/gpt-4": {
13149
13157
  id: "openai/gpt-4",
13150
13158
  name: "OpenAI: GPT-4",
@@ -13162,6 +13170,23 @@ export const MODELS = {
13162
13170
  contextWindow: 8191,
13163
13171
  maxTokens: 4096,
13164
13172
  },
13173
+ "openai/gpt-4-turbo:batch": {
13174
+ id: "openai/gpt-4-turbo:batch",
13175
+ name: "OpenAI: GPT-4 Turbo (batch)",
13176
+ api: "openai-completions",
13177
+ provider: "openrouter",
13178
+ baseUrl: "https://openrouter.ai/api/v1",
13179
+ reasoning: false,
13180
+ input: ["text", "image"],
13181
+ cost: {
13182
+ input: 5,
13183
+ output: 15,
13184
+ cacheRead: 0,
13185
+ cacheWrite: 0,
13186
+ },
13187
+ contextWindow: 128000,
13188
+ maxTokens: 4096,
13189
+ },
13165
13190
  "openai/gpt-4.1": {
13166
13191
  id: "openai/gpt-4.1",
13167
13192
  name: "OpenAI: GPT-4.1",
@@ -13196,6 +13221,23 @@ export const MODELS = {
13196
13221
  contextWindow: 1047576,
13197
13222
  maxTokens: 32768,
13198
13223
  },
13224
+ "openai/gpt-4.1-mini:batch": {
13225
+ id: "openai/gpt-4.1-mini:batch",
13226
+ name: "OpenAI: GPT-4.1 Mini (batch)",
13227
+ api: "openai-completions",
13228
+ provider: "openrouter",
13229
+ baseUrl: "https://openrouter.ai/api/v1",
13230
+ reasoning: false,
13231
+ input: ["text", "image"],
13232
+ cost: {
13233
+ input: 0.19999999999999998,
13234
+ output: 0.7999999999999999,
13235
+ cacheRead: 0.049999999999999996,
13236
+ cacheWrite: 0,
13237
+ },
13238
+ contextWindow: 1047576,
13239
+ maxTokens: 32768,
13240
+ },
13199
13241
  "openai/gpt-4.1-nano": {
13200
13242
  id: "openai/gpt-4.1-nano",
13201
13243
  name: "OpenAI: GPT-4.1 Nano",
@@ -13207,11 +13249,45 @@ export const MODELS = {
13207
13249
  cost: {
13208
13250
  input: 0.09999999999999999,
13209
13251
  output: 0.39999999999999997,
13210
- cacheRead: 0.03,
13252
+ cacheRead: 0.024999999999999998,
13253
+ cacheWrite: 0,
13254
+ },
13255
+ contextWindow: 1047576,
13256
+ maxTokens: 32768,
13257
+ },
13258
+ "openai/gpt-4.1-nano:batch": {
13259
+ id: "openai/gpt-4.1-nano:batch",
13260
+ name: "OpenAI: GPT-4.1 Nano (batch)",
13261
+ api: "openai-completions",
13262
+ provider: "openrouter",
13263
+ baseUrl: "https://openrouter.ai/api/v1",
13264
+ reasoning: false,
13265
+ input: ["text", "image"],
13266
+ cost: {
13267
+ input: 0.049999999999999996,
13268
+ output: 0.19999999999999998,
13269
+ cacheRead: 0.012499999999999999,
13211
13270
  cacheWrite: 0,
13212
13271
  },
13213
13272
  contextWindow: 1047576,
13214
- maxTokens: 942818,
13273
+ maxTokens: 32768,
13274
+ },
13275
+ "openai/gpt-4.1:batch": {
13276
+ id: "openai/gpt-4.1:batch",
13277
+ name: "OpenAI: GPT-4.1 (batch)",
13278
+ api: "openai-completions",
13279
+ provider: "openrouter",
13280
+ baseUrl: "https://openrouter.ai/api/v1",
13281
+ reasoning: false,
13282
+ input: ["text", "image"],
13283
+ cost: {
13284
+ input: 1,
13285
+ output: 4,
13286
+ cacheRead: 0.25,
13287
+ cacheWrite: 0,
13288
+ },
13289
+ contextWindow: 1047576,
13290
+ maxTokens: 32768,
13215
13291
  },
13216
13292
  "openai/gpt-4o": {
13217
13293
  id: "openai/gpt-4o",
@@ -13247,6 +13323,40 @@ export const MODELS = {
13247
13323
  contextWindow: 128000,
13248
13324
  maxTokens: 16384,
13249
13325
  },
13326
+ "openai/gpt-4o-mini:batch": {
13327
+ id: "openai/gpt-4o-mini:batch",
13328
+ name: "OpenAI: GPT-4o-mini (batch)",
13329
+ api: "openai-completions",
13330
+ provider: "openrouter",
13331
+ baseUrl: "https://openrouter.ai/api/v1",
13332
+ reasoning: false,
13333
+ input: ["text", "image"],
13334
+ cost: {
13335
+ input: 0.075,
13336
+ output: 0.3,
13337
+ cacheRead: 0.0375,
13338
+ cacheWrite: 0,
13339
+ },
13340
+ contextWindow: 128000,
13341
+ maxTokens: 16384,
13342
+ },
13343
+ "openai/gpt-4o:batch": {
13344
+ id: "openai/gpt-4o:batch",
13345
+ name: "OpenAI: GPT-4o (batch)",
13346
+ api: "openai-completions",
13347
+ provider: "openrouter",
13348
+ baseUrl: "https://openrouter.ai/api/v1",
13349
+ reasoning: false,
13350
+ input: ["text", "image"],
13351
+ cost: {
13352
+ input: 1.25,
13353
+ output: 5,
13354
+ cacheRead: 0.625,
13355
+ cacheWrite: 0,
13356
+ },
13357
+ contextWindow: 128000,
13358
+ maxTokens: 16384,
13359
+ },
13250
13360
  "openai/gpt-5": {
13251
13361
  id: "openai/gpt-5",
13252
13362
  name: "OpenAI: GPT-5",
@@ -13281,6 +13391,23 @@ export const MODELS = {
13281
13391
  contextWindow: 400000,
13282
13392
  maxTokens: 128000,
13283
13393
  },
13394
+ "openai/gpt-5-mini:batch": {
13395
+ id: "openai/gpt-5-mini:batch",
13396
+ name: "OpenAI: GPT-5 Mini (batch)",
13397
+ api: "openai-completions",
13398
+ provider: "openrouter",
13399
+ baseUrl: "https://openrouter.ai/api/v1",
13400
+ reasoning: true,
13401
+ input: ["text", "image"],
13402
+ cost: {
13403
+ input: 0.125,
13404
+ output: 1,
13405
+ cacheRead: 0.012499999999999999,
13406
+ cacheWrite: 0,
13407
+ },
13408
+ contextWindow: 400000,
13409
+ maxTokens: 128000,
13410
+ },
13284
13411
  "openai/gpt-5-nano": {
13285
13412
  id: "openai/gpt-5-nano",
13286
13413
  name: "OpenAI: GPT-5 Nano",
@@ -13298,6 +13425,23 @@ export const MODELS = {
13298
13425
  contextWindow: 400000,
13299
13426
  maxTokens: 128000,
13300
13427
  },
13428
+ "openai/gpt-5-nano:batch": {
13429
+ id: "openai/gpt-5-nano:batch",
13430
+ name: "OpenAI: GPT-5 Nano (batch)",
13431
+ api: "openai-completions",
13432
+ provider: "openrouter",
13433
+ baseUrl: "https://openrouter.ai/api/v1",
13434
+ reasoning: true,
13435
+ input: ["text", "image"],
13436
+ cost: {
13437
+ input: 0.024999999999999998,
13438
+ output: 0.19999999999999998,
13439
+ cacheRead: 0.0025,
13440
+ cacheWrite: 0,
13441
+ },
13442
+ contextWindow: 400000,
13443
+ maxTokens: 128000,
13444
+ },
13301
13445
  "openai/gpt-5-pro": {
13302
13446
  id: "openai/gpt-5-pro",
13303
13447
  name: "OpenAI: GPT-5 Pro",
@@ -13315,6 +13459,23 @@ export const MODELS = {
13315
13459
  contextWindow: 400000,
13316
13460
  maxTokens: 128000,
13317
13461
  },
13462
+ "openai/gpt-5-pro:batch": {
13463
+ id: "openai/gpt-5-pro:batch",
13464
+ name: "OpenAI: GPT-5 Pro (batch)",
13465
+ api: "openai-completions",
13466
+ provider: "openrouter",
13467
+ baseUrl: "https://openrouter.ai/api/v1",
13468
+ reasoning: true,
13469
+ input: ["text", "image"],
13470
+ cost: {
13471
+ input: 7.5,
13472
+ output: 60,
13473
+ cacheRead: 0,
13474
+ cacheWrite: 0,
13475
+ },
13476
+ contextWindow: 400000,
13477
+ maxTokens: 128000,
13478
+ },
13318
13479
  "openai/gpt-5.1": {
13319
13480
  id: "openai/gpt-5.1",
13320
13481
  name: "OpenAI: GPT-5.1",
@@ -13383,6 +13544,23 @@ export const MODELS = {
13383
13544
  contextWindow: 400000,
13384
13545
  maxTokens: 128000,
13385
13546
  },
13547
+ "openai/gpt-5.1:batch": {
13548
+ id: "openai/gpt-5.1:batch",
13549
+ name: "OpenAI: GPT-5.1 (batch)",
13550
+ api: "openai-completions",
13551
+ provider: "openrouter",
13552
+ baseUrl: "https://openrouter.ai/api/v1",
13553
+ reasoning: true,
13554
+ input: ["text", "image"],
13555
+ cost: {
13556
+ input: 0.625,
13557
+ output: 5,
13558
+ cacheRead: 0.0625,
13559
+ cacheWrite: 0,
13560
+ },
13561
+ contextWindow: 400000,
13562
+ maxTokens: 128000,
13563
+ },
13386
13564
  "openai/gpt-5.2": {
13387
13565
  id: "openai/gpt-5.2",
13388
13566
  name: "OpenAI: GPT-5.2",
@@ -13455,6 +13633,42 @@ export const MODELS = {
13455
13633
  contextWindow: 400000,
13456
13634
  maxTokens: 128000,
13457
13635
  },
13636
+ "openai/gpt-5.2-pro:batch": {
13637
+ id: "openai/gpt-5.2-pro:batch",
13638
+ name: "OpenAI: GPT-5.2 Pro (batch)",
13639
+ api: "openai-completions",
13640
+ provider: "openrouter",
13641
+ baseUrl: "https://openrouter.ai/api/v1",
13642
+ reasoning: true,
13643
+ thinkingLevelMap: { "xhigh": "xhigh" },
13644
+ input: ["text", "image"],
13645
+ cost: {
13646
+ input: 10.5,
13647
+ output: 84,
13648
+ cacheRead: 0,
13649
+ cacheWrite: 0,
13650
+ },
13651
+ contextWindow: 400000,
13652
+ maxTokens: 128000,
13653
+ },
13654
+ "openai/gpt-5.2:batch": {
13655
+ id: "openai/gpt-5.2:batch",
13656
+ name: "OpenAI: GPT-5.2 (batch)",
13657
+ api: "openai-completions",
13658
+ provider: "openrouter",
13659
+ baseUrl: "https://openrouter.ai/api/v1",
13660
+ reasoning: true,
13661
+ thinkingLevelMap: { "xhigh": "xhigh" },
13662
+ input: ["text", "image"],
13663
+ cost: {
13664
+ input: 0.875,
13665
+ output: 7,
13666
+ cacheRead: 0.0875,
13667
+ cacheWrite: 0,
13668
+ },
13669
+ contextWindow: 400000,
13670
+ maxTokens: 128000,
13671
+ },
13458
13672
  "openai/gpt-5.3-codex": {
13459
13673
  id: "openai/gpt-5.3-codex",
13460
13674
  name: "OpenAI: GPT-5.3-Codex",
@@ -13509,6 +13723,24 @@ export const MODELS = {
13509
13723
  contextWindow: 400000,
13510
13724
  maxTokens: 128000,
13511
13725
  },
13726
+ "openai/gpt-5.4-mini:batch": {
13727
+ id: "openai/gpt-5.4-mini:batch",
13728
+ name: "OpenAI: GPT-5.4 Mini (batch)",
13729
+ api: "openai-completions",
13730
+ provider: "openrouter",
13731
+ baseUrl: "https://openrouter.ai/api/v1",
13732
+ reasoning: true,
13733
+ thinkingLevelMap: { "xhigh": "xhigh" },
13734
+ input: ["text", "image"],
13735
+ cost: {
13736
+ input: 0.375,
13737
+ output: 2.25,
13738
+ cacheRead: 0.0375,
13739
+ cacheWrite: 0,
13740
+ },
13741
+ contextWindow: 400000,
13742
+ maxTokens: 128000,
13743
+ },
13512
13744
  "openai/gpt-5.4-nano": {
13513
13745
  id: "openai/gpt-5.4-nano",
13514
13746
  name: "OpenAI: GPT-5.4 Nano",
@@ -13519,17 +13751,107 @@ export const MODELS = {
13519
13751
  thinkingLevelMap: { "xhigh": "xhigh" },
13520
13752
  input: ["text", "image"],
13521
13753
  cost: {
13522
- input: 0.19999999999999998,
13523
- output: 1.25,
13524
- cacheRead: 0.02,
13754
+ input: 0.19999999999999998,
13755
+ output: 1.25,
13756
+ cacheRead: 0.02,
13757
+ cacheWrite: 0,
13758
+ },
13759
+ contextWindow: 400000,
13760
+ maxTokens: 128000,
13761
+ },
13762
+ "openai/gpt-5.4-nano:batch": {
13763
+ id: "openai/gpt-5.4-nano:batch",
13764
+ name: "OpenAI: GPT-5.4 Nano (batch)",
13765
+ api: "openai-completions",
13766
+ provider: "openrouter",
13767
+ baseUrl: "https://openrouter.ai/api/v1",
13768
+ reasoning: true,
13769
+ thinkingLevelMap: { "xhigh": "xhigh" },
13770
+ input: ["text", "image"],
13771
+ cost: {
13772
+ input: 0.09999999999999999,
13773
+ output: 0.625,
13774
+ cacheRead: 0.01,
13775
+ cacheWrite: 0,
13776
+ },
13777
+ contextWindow: 400000,
13778
+ maxTokens: 128000,
13779
+ },
13780
+ "openai/gpt-5.4-pro": {
13781
+ id: "openai/gpt-5.4-pro",
13782
+ name: "OpenAI: GPT-5.4 Pro",
13783
+ api: "openai-completions",
13784
+ provider: "openrouter",
13785
+ baseUrl: "https://openrouter.ai/api/v1",
13786
+ reasoning: true,
13787
+ thinkingLevelMap: { "xhigh": "xhigh" },
13788
+ input: ["text", "image"],
13789
+ cost: {
13790
+ input: 30,
13791
+ output: 180,
13792
+ cacheRead: 0,
13793
+ cacheWrite: 0,
13794
+ },
13795
+ contextWindow: 1050000,
13796
+ maxTokens: 128000,
13797
+ },
13798
+ "openai/gpt-5.4-pro:batch": {
13799
+ id: "openai/gpt-5.4-pro:batch",
13800
+ name: "OpenAI: GPT-5.4 Pro (batch)",
13801
+ api: "openai-completions",
13802
+ provider: "openrouter",
13803
+ baseUrl: "https://openrouter.ai/api/v1",
13804
+ reasoning: true,
13805
+ thinkingLevelMap: { "xhigh": "xhigh" },
13806
+ input: ["text", "image"],
13807
+ cost: {
13808
+ input: 15,
13809
+ output: 90,
13810
+ cacheRead: 0,
13811
+ cacheWrite: 0,
13812
+ },
13813
+ contextWindow: 1050000,
13814
+ maxTokens: 128000,
13815
+ },
13816
+ "openai/gpt-5.4:batch": {
13817
+ id: "openai/gpt-5.4:batch",
13818
+ name: "OpenAI: GPT-5.4 (batch)",
13819
+ api: "openai-completions",
13820
+ provider: "openrouter",
13821
+ baseUrl: "https://openrouter.ai/api/v1",
13822
+ reasoning: true,
13823
+ thinkingLevelMap: { "xhigh": "xhigh" },
13824
+ input: ["text", "image"],
13825
+ cost: {
13826
+ input: 1.25,
13827
+ output: 7.5,
13828
+ cacheRead: 0.125,
13829
+ cacheWrite: 0,
13830
+ },
13831
+ contextWindow: 1050000,
13832
+ maxTokens: 128000,
13833
+ },
13834
+ "openai/gpt-5.5": {
13835
+ id: "openai/gpt-5.5",
13836
+ name: "OpenAI: GPT-5.5",
13837
+ api: "openai-completions",
13838
+ provider: "openrouter",
13839
+ baseUrl: "https://openrouter.ai/api/v1",
13840
+ reasoning: true,
13841
+ thinkingLevelMap: { "xhigh": "xhigh" },
13842
+ input: ["text", "image"],
13843
+ cost: {
13844
+ input: 5,
13845
+ output: 30,
13846
+ cacheRead: 0.5,
13525
13847
  cacheWrite: 0,
13526
13848
  },
13527
- contextWindow: 400000,
13849
+ contextWindow: 1050000,
13528
13850
  maxTokens: 128000,
13529
13851
  },
13530
- "openai/gpt-5.4-pro": {
13531
- id: "openai/gpt-5.4-pro",
13532
- name: "OpenAI: GPT-5.4 Pro",
13852
+ "openai/gpt-5.5-pro": {
13853
+ id: "openai/gpt-5.5-pro",
13854
+ name: "OpenAI: GPT-5.5 Pro",
13533
13855
  api: "openai-completions",
13534
13856
  provider: "openrouter",
13535
13857
  baseUrl: "https://openrouter.ai/api/v1",
@@ -13545,9 +13867,9 @@ export const MODELS = {
13545
13867
  contextWindow: 1050000,
13546
13868
  maxTokens: 128000,
13547
13869
  },
13548
- "openai/gpt-5.5": {
13549
- id: "openai/gpt-5.5",
13550
- name: "OpenAI: GPT-5.5",
13870
+ "openai/gpt-5.5-pro:batch": {
13871
+ id: "openai/gpt-5.5-pro:batch",
13872
+ name: "OpenAI: GPT-5.5 Pro (batch)",
13551
13873
  api: "openai-completions",
13552
13874
  provider: "openrouter",
13553
13875
  baseUrl: "https://openrouter.ai/api/v1",
@@ -13555,17 +13877,17 @@ export const MODELS = {
13555
13877
  thinkingLevelMap: { "xhigh": "xhigh" },
13556
13878
  input: ["text", "image"],
13557
13879
  cost: {
13558
- input: 5,
13559
- output: 30,
13560
- cacheRead: 0.5,
13880
+ input: 15,
13881
+ output: 90,
13882
+ cacheRead: 0,
13561
13883
  cacheWrite: 0,
13562
13884
  },
13563
13885
  contextWindow: 1050000,
13564
13886
  maxTokens: 128000,
13565
13887
  },
13566
- "openai/gpt-5.5-pro": {
13567
- id: "openai/gpt-5.5-pro",
13568
- name: "OpenAI: GPT-5.5 Pro",
13888
+ "openai/gpt-5.5:batch": {
13889
+ id: "openai/gpt-5.5:batch",
13890
+ name: "OpenAI: GPT-5.5 (batch)",
13569
13891
  api: "openai-completions",
13570
13892
  provider: "openrouter",
13571
13893
  baseUrl: "https://openrouter.ai/api/v1",
@@ -13573,9 +13895,9 @@ export const MODELS = {
13573
13895
  thinkingLevelMap: { "xhigh": "xhigh" },
13574
13896
  input: ["text", "image"],
13575
13897
  cost: {
13576
- input: 30,
13577
- output: 180,
13578
- cacheRead: 0,
13898
+ input: 2.5,
13899
+ output: 15,
13900
+ cacheRead: 0.25,
13579
13901
  cacheWrite: 0,
13580
13902
  },
13581
13903
  contextWindow: 1050000,
@@ -13615,6 +13937,40 @@ export const MODELS = {
13615
13937
  contextWindow: 1050000,
13616
13938
  maxTokens: 128000,
13617
13939
  },
13940
+ "openai/gpt-5.6-luna-pro:batch": {
13941
+ id: "openai/gpt-5.6-luna-pro:batch",
13942
+ name: "OpenAI: GPT-5.6 Luna Pro (batch)",
13943
+ api: "openai-completions",
13944
+ provider: "openrouter",
13945
+ baseUrl: "https://openrouter.ai/api/v1",
13946
+ reasoning: true,
13947
+ input: ["text", "image"],
13948
+ cost: {
13949
+ input: 0.09999999999999999,
13950
+ output: 0.6,
13951
+ cacheRead: 0.01,
13952
+ cacheWrite: 0,
13953
+ },
13954
+ contextWindow: 1050000,
13955
+ maxTokens: 128000,
13956
+ },
13957
+ "openai/gpt-5.6-luna:batch": {
13958
+ id: "openai/gpt-5.6-luna:batch",
13959
+ name: "OpenAI: GPT-5.6 Luna (batch)",
13960
+ api: "openai-completions",
13961
+ provider: "openrouter",
13962
+ baseUrl: "https://openrouter.ai/api/v1",
13963
+ reasoning: true,
13964
+ input: ["text", "image"],
13965
+ cost: {
13966
+ input: 0.09999999999999999,
13967
+ output: 0.6,
13968
+ cacheRead: 0.01,
13969
+ cacheWrite: 0,
13970
+ },
13971
+ contextWindow: 1050000,
13972
+ maxTokens: 128000,
13973
+ },
13618
13974
  "openai/gpt-5.6-sol": {
13619
13975
  id: "openai/gpt-5.6-sol",
13620
13976
  name: "OpenAI: GPT-5.6 Sol",
@@ -13649,6 +14005,40 @@ export const MODELS = {
13649
14005
  contextWindow: 1050000,
13650
14006
  maxTokens: 128000,
13651
14007
  },
14008
+ "openai/gpt-5.6-sol-pro:batch": {
14009
+ id: "openai/gpt-5.6-sol-pro:batch",
14010
+ name: "OpenAI: GPT-5.6 Sol Pro (batch)",
14011
+ api: "openai-completions",
14012
+ provider: "openrouter",
14013
+ baseUrl: "https://openrouter.ai/api/v1",
14014
+ reasoning: true,
14015
+ input: ["text", "image"],
14016
+ cost: {
14017
+ input: 1,
14018
+ output: 5,
14019
+ cacheRead: 0.09999999999999999,
14020
+ cacheWrite: 1.25,
14021
+ },
14022
+ contextWindow: 1050000,
14023
+ maxTokens: 128000,
14024
+ },
14025
+ "openai/gpt-5.6-sol:batch": {
14026
+ id: "openai/gpt-5.6-sol:batch",
14027
+ name: "OpenAI: GPT-5.6 Sol (batch)",
14028
+ api: "openai-completions",
14029
+ provider: "openrouter",
14030
+ baseUrl: "https://openrouter.ai/api/v1",
14031
+ reasoning: true,
14032
+ input: ["text", "image"],
14033
+ cost: {
14034
+ input: 1,
14035
+ output: 5,
14036
+ cacheRead: 0.09999999999999999,
14037
+ cacheWrite: 1.25,
14038
+ },
14039
+ contextWindow: 1050000,
14040
+ maxTokens: 128000,
14041
+ },
13652
14042
  "openai/gpt-5.6-terra": {
13653
14043
  id: "openai/gpt-5.6-terra",
13654
14044
  name: "OpenAI: GPT-5.6 Terra",
@@ -13683,6 +14073,57 @@ export const MODELS = {
13683
14073
  contextWindow: 1050000,
13684
14074
  maxTokens: 128000,
13685
14075
  },
14076
+ "openai/gpt-5.6-terra-pro:batch": {
14077
+ id: "openai/gpt-5.6-terra-pro:batch",
14078
+ name: "OpenAI: GPT-5.6 Terra Pro (batch)",
14079
+ api: "openai-completions",
14080
+ provider: "openrouter",
14081
+ baseUrl: "https://openrouter.ai/api/v1",
14082
+ reasoning: true,
14083
+ input: ["text", "image"],
14084
+ cost: {
14085
+ input: 1,
14086
+ output: 6,
14087
+ cacheRead: 0.09999999999999999,
14088
+ cacheWrite: 0,
14089
+ },
14090
+ contextWindow: 1050000,
14091
+ maxTokens: 128000,
14092
+ },
14093
+ "openai/gpt-5.6-terra:batch": {
14094
+ id: "openai/gpt-5.6-terra:batch",
14095
+ name: "OpenAI: GPT-5.6 Terra (batch)",
14096
+ api: "openai-completions",
14097
+ provider: "openrouter",
14098
+ baseUrl: "https://openrouter.ai/api/v1",
14099
+ reasoning: true,
14100
+ input: ["text", "image"],
14101
+ cost: {
14102
+ input: 1,
14103
+ output: 6,
14104
+ cacheRead: 0.09999999999999999,
14105
+ cacheWrite: 0,
14106
+ },
14107
+ contextWindow: 1050000,
14108
+ maxTokens: 128000,
14109
+ },
14110
+ "openai/gpt-5:batch": {
14111
+ id: "openai/gpt-5:batch",
14112
+ name: "OpenAI: GPT-5 (batch)",
14113
+ api: "openai-completions",
14114
+ provider: "openrouter",
14115
+ baseUrl: "https://openrouter.ai/api/v1",
14116
+ reasoning: true,
14117
+ input: ["text", "image"],
14118
+ cost: {
14119
+ input: 0.625,
14120
+ output: 5,
14121
+ cacheRead: 0.0625,
14122
+ cacheWrite: 0,
14123
+ },
14124
+ contextWindow: 400000,
14125
+ maxTokens: 128000,
14126
+ },
13686
14127
  "openai/gpt-audio": {
13687
14128
  id: "openai/gpt-audio",
13688
14129
  name: "OpenAI: GPT Audio",
@@ -13870,6 +14311,23 @@ export const MODELS = {
13870
14311
  contextWindow: 200000,
13871
14312
  maxTokens: 100000,
13872
14313
  },
14314
+ "openai/o3-mini:batch": {
14315
+ id: "openai/o3-mini:batch",
14316
+ name: "OpenAI: o3 Mini (batch)",
14317
+ api: "openai-completions",
14318
+ provider: "openrouter",
14319
+ baseUrl: "https://openrouter.ai/api/v1",
14320
+ reasoning: true,
14321
+ input: ["text"],
14322
+ cost: {
14323
+ input: 0.55,
14324
+ output: 2.2,
14325
+ cacheRead: 0.275,
14326
+ cacheWrite: 0,
14327
+ },
14328
+ contextWindow: 200000,
14329
+ maxTokens: 100000,
14330
+ },
13873
14331
  "openai/o3-pro": {
13874
14332
  id: "openai/o3-pro",
13875
14333
  name: "OpenAI: o3 Pro",
@@ -13887,6 +14345,23 @@ export const MODELS = {
13887
14345
  contextWindow: 200000,
13888
14346
  maxTokens: 100000,
13889
14347
  },
14348
+ "openai/o3:batch": {
14349
+ id: "openai/o3:batch",
14350
+ name: "OpenAI: o3 (batch)",
14351
+ api: "openai-completions",
14352
+ provider: "openrouter",
14353
+ baseUrl: "https://openrouter.ai/api/v1",
14354
+ reasoning: true,
14355
+ input: ["text", "image"],
14356
+ cost: {
14357
+ input: 1,
14358
+ output: 4,
14359
+ cacheRead: 0.25,
14360
+ cacheWrite: 0,
14361
+ },
14362
+ contextWindow: 200000,
14363
+ maxTokens: 100000,
14364
+ },
13890
14365
  "openai/o4-mini": {
13891
14366
  id: "openai/o4-mini",
13892
14367
  name: "OpenAI: o4 Mini",
@@ -13921,6 +14396,23 @@ export const MODELS = {
13921
14396
  contextWindow: 200000,
13922
14397
  maxTokens: 100000,
13923
14398
  },
14399
+ "openai/o4-mini:batch": {
14400
+ id: "openai/o4-mini:batch",
14401
+ name: "OpenAI: o4 Mini (batch)",
14402
+ api: "openai-completions",
14403
+ provider: "openrouter",
14404
+ baseUrl: "https://openrouter.ai/api/v1",
14405
+ reasoning: true,
14406
+ input: ["text", "image"],
14407
+ cost: {
14408
+ input: 0.55,
14409
+ output: 2.2,
14410
+ cacheRead: 0.1375,
14411
+ cacheWrite: 0,
14412
+ },
14413
+ contextWindow: 200000,
14414
+ maxTokens: 100000,
14415
+ },
13924
14416
  "openrouter/auto": {
13925
14417
  id: "openrouter/auto",
13926
14418
  name: "Auto Router",
@@ -15086,13 +15578,13 @@ export const MODELS = {
15086
15578
  reasoning: true,
15087
15579
  input: ["text", "image"],
15088
15580
  cost: {
15089
- input: 0.95,
15581
+ input: 1,
15090
15582
  output: 4.05,
15091
- cacheRead: 0.16,
15583
+ cacheRead: 0.16999999999999998,
15092
15584
  cacheWrite: 0,
15093
15585
  },
15094
15586
  contextWindow: 1048576,
15095
- maxTokens: 262144,
15587
+ maxTokens: 471859,
15096
15588
  },
15097
15589
  "thinkingmachines/inkling-small": {
15098
15590
  id: "thinkingmachines/inkling-small",
@@ -15494,13 +15986,13 @@ export const MODELS = {
15494
15986
  reasoning: true,
15495
15987
  input: ["text"],
15496
15988
  cost: {
15497
- input: 1.26,
15498
- output: 3.9600000000000004,
15499
- cacheRead: 0.234,
15989
+ input: 0.966,
15990
+ output: 3.036,
15991
+ cacheRead: 0.1794,
15500
15992
  cacheWrite: 0,
15501
15993
  },
15502
15994
  contextWindow: 204800,
15503
- maxTokens: 182476,
15995
+ maxTokens: 128000,
15504
15996
  },
15505
15997
  "z-ai/glm-5.2": {
15506
15998
  id: "z-ai/glm-5.2",
@@ -15616,7 +16108,7 @@ export const MODELS = {
15616
16108
  cost: {
15617
16109
  input: 10,
15618
16110
  output: 50,
15619
- cacheRead: 1,
16111
+ cacheRead: 0.25,
15620
16112
  cacheWrite: 12.5,
15621
16113
  },
15622
16114
  contextWindow: 1000000,
@@ -15684,9 +16176,9 @@ export const MODELS = {
15684
16176
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
15685
16177
  input: ["text"],
15686
16178
  cost: {
15687
- input: 0.03,
15688
- output: 0.09999999999999999,
15689
- cacheRead: 0.007,
16179
+ input: 0.049980000000000004,
16180
+ output: 0.09996000000000001,
16181
+ cacheRead: 0.009996000000000001,
15690
16182
  cacheWrite: 0,
15691
16183
  },
15692
16184
  contextWindow: 1310720,
@@ -15803,13 +16295,13 @@ export const MODELS = {
15803
16295
  reasoning: true,
15804
16296
  input: ["text"],
15805
16297
  cost: {
15806
- input: 1.1875,
15807
- output: 4.18,
15808
- cacheRead: 0.24699999999999997,
16298
+ input: 1.17,
16299
+ output: 3.9600000000000004,
16300
+ cacheRead: 0.234,
15809
16301
  cacheWrite: 0,
15810
16302
  },
15811
16303
  contextWindow: 1310720,
15812
- maxTokens: 131072,
16304
+ maxTokens: 943718,
15813
16305
  },
15814
16306
  },
15815
16307
  "together": {
@@ -16171,6 +16663,25 @@ export const MODELS = {
16171
16663
  contextWindow: 512000,
16172
16664
  maxTokens: 164000,
16173
16665
  },
16666
+ "zai-org/GLM-5.3": {
16667
+ id: "zai-org/GLM-5.3",
16668
+ name: "GLM-5.3",
16669
+ api: "openai-completions",
16670
+ provider: "together",
16671
+ baseUrl: "https://api.together.ai/v1",
16672
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
16673
+ reasoning: true,
16674
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
16675
+ input: ["text"],
16676
+ cost: {
16677
+ input: 1.4,
16678
+ output: 4.4,
16679
+ cacheRead: 0.26,
16680
+ cacheWrite: 0,
16681
+ },
16682
+ contextWindow: 1048576,
16683
+ maxTokens: 262144,
16684
+ },
16174
16685
  "zai-org/GLM-5.3-Flash": {
16175
16686
  id: "zai-org/GLM-5.3-Flash",
16176
16687
  name: "GLM-5.3-Flash",
@@ -16668,6 +17179,23 @@ export const MODELS = {
16668
17179
  contextWindow: 991000,
16669
17180
  maxTokens: 128000,
16670
17181
  },
17182
+ "alibaba/qwen3.8-flash-next": {
17183
+ id: "alibaba/qwen3.8-flash-next",
17184
+ name: "Qwen 3.8 Flash Next",
17185
+ api: "anthropic-messages",
17186
+ provider: "vercel-ai-gateway",
17187
+ baseUrl: "https://ai-gateway.vercel.sh",
17188
+ reasoning: true,
17189
+ input: ["text", "image"],
17190
+ cost: {
17191
+ input: 0.12,
17192
+ output: 0.39999999999999997,
17193
+ cacheRead: 0.01,
17194
+ cacheWrite: 0,
17195
+ },
17196
+ contextWindow: 1048576,
17197
+ maxTokens: 1048576,
17198
+ },
16671
17199
  "alibaba/qwen3.8-max": {
16672
17200
  id: "alibaba/qwen3.8-max",
16673
17201
  name: "Qwen 3.8 Max",
@@ -16788,6 +17316,24 @@ export const MODELS = {
16788
17316
  contextWindow: 1000000,
16789
17317
  maxTokens: 128000,
16790
17318
  },
17319
+ "anthropic/claude-fable-5.1": {
17320
+ id: "anthropic/claude-fable-5.1",
17321
+ name: "Claude Fable 5.1",
17322
+ api: "anthropic-messages",
17323
+ provider: "vercel-ai-gateway",
17324
+ baseUrl: "https://ai-gateway.vercel.sh",
17325
+ reasoning: true,
17326
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
17327
+ input: ["text", "image"],
17328
+ cost: {
17329
+ input: 10,
17330
+ output: 50,
17331
+ cacheRead: 0.25,
17332
+ cacheWrite: 12.5,
17333
+ },
17334
+ contextWindow: 1000000,
17335
+ maxTokens: 128000,
17336
+ },
16791
17337
  "anthropic/claude-haiku-4.5": {
16792
17338
  id: "anthropic/claude-haiku-4.5",
16793
17339
  name: "Claude Haiku 4.5",
@@ -17231,8 +17777,8 @@ export const MODELS = {
17231
17777
  cacheRead: 0.007,
17232
17778
  cacheWrite: 0,
17233
17779
  },
17234
- contextWindow: 1000000,
17235
- maxTokens: 384000,
17780
+ contextWindow: 1048576,
17781
+ maxTokens: 1048576,
17236
17782
  },
17237
17783
  "deepseek/deepseek-v4-pro": {
17238
17784
  id: "deepseek/deepseek-v4-pro",
@@ -19765,6 +20311,23 @@ export const MODELS = {
19765
20311
  contextWindow: 1050000,
19766
20312
  maxTokens: 131000,
19767
20313
  },
20314
+ "xiaomi/mimo-v2.5-pro-ultraspeed": {
20315
+ id: "xiaomi/mimo-v2.5-pro-ultraspeed",
20316
+ name: "MiMo V2.5 Pro UltraSpeed",
20317
+ api: "anthropic-messages",
20318
+ provider: "vercel-ai-gateway",
20319
+ baseUrl: "https://ai-gateway.vercel.sh",
20320
+ reasoning: true,
20321
+ input: ["text"],
20322
+ cost: {
20323
+ input: 1.305,
20324
+ output: 2.61,
20325
+ cacheRead: 0.0108,
20326
+ cacheWrite: 0,
20327
+ },
20328
+ contextWindow: 1048576,
20329
+ maxTokens: 131072,
20330
+ },
19768
20331
  "zai/glm-4.5": {
19769
20332
  id: "zai/glm-4.5",
19770
20333
  name: "GLM 4.5",