@elyracode/ai 0.9.12 → 0.9.14

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.
@@ -70,6 +70,25 @@ export const MODELS = {
70
70
  contextWindow: 300000,
71
71
  maxTokens: 8192,
72
72
  },
73
+ "anthropic.claude-fable-5": {
74
+ id: "anthropic.claude-fable-5",
75
+ name: "Claude Fable 5",
76
+ api: "bedrock-converse-stream",
77
+ provider: "amazon-bedrock",
78
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
79
+ reasoning: true,
80
+ thinkingType: "adaptive",
81
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
82
+ input: ["text", "image"],
83
+ cost: {
84
+ input: 10,
85
+ output: 50,
86
+ cacheRead: 1,
87
+ cacheWrite: 12.5,
88
+ },
89
+ contextWindow: 1000000,
90
+ maxTokens: 128000,
91
+ },
73
92
  "anthropic.claude-haiku-4-5-20251001-v1:0": {
74
93
  id: "anthropic.claude-haiku-4-5-20251001-v1:0",
75
94
  name: "Claude Haiku 4.5",
@@ -762,6 +781,24 @@ export const MODELS = {
762
781
  contextWindow: 128000,
763
782
  maxTokens: 4096,
764
783
  },
784
+ "jp.anthropic.claude-haiku-4-5-20251001-v1:0": {
785
+ id: "jp.anthropic.claude-haiku-4-5-20251001-v1:0",
786
+ name: "Claude Haiku 4.5 (JP)",
787
+ api: "bedrock-converse-stream",
788
+ provider: "amazon-bedrock",
789
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
790
+ reasoning: true,
791
+ thinkingType: "budget",
792
+ input: ["text", "image"],
793
+ cost: {
794
+ input: 1,
795
+ output: 5,
796
+ cacheRead: 0.1,
797
+ cacheWrite: 1.25,
798
+ },
799
+ contextWindow: 200000,
800
+ maxTokens: 64000,
801
+ },
765
802
  "jp.anthropic.claude-opus-4-7": {
766
803
  id: "jp.anthropic.claude-opus-4-7",
767
804
  name: "Claude Opus 4.7 (JP)",
@@ -1841,109 +1878,6 @@ export const MODELS = {
1841
1878
  },
1842
1879
  },
1843
1880
  "anthropic": {
1844
- "claude-3-5-sonnet-20240620": {
1845
- id: "claude-3-5-sonnet-20240620",
1846
- name: "Claude Sonnet 3.5",
1847
- api: "anthropic-messages",
1848
- provider: "anthropic",
1849
- baseUrl: "https://api.anthropic.com",
1850
- reasoning: false,
1851
- input: ["text", "image"],
1852
- cost: {
1853
- input: 3,
1854
- output: 15,
1855
- cacheRead: 0.3,
1856
- cacheWrite: 3.75,
1857
- },
1858
- contextWindow: 200000,
1859
- maxTokens: 8192,
1860
- },
1861
- "claude-3-5-sonnet-20241022": {
1862
- id: "claude-3-5-sonnet-20241022",
1863
- name: "Claude Sonnet 3.5 v2",
1864
- api: "anthropic-messages",
1865
- provider: "anthropic",
1866
- baseUrl: "https://api.anthropic.com",
1867
- reasoning: false,
1868
- input: ["text", "image"],
1869
- cost: {
1870
- input: 3,
1871
- output: 15,
1872
- cacheRead: 0.3,
1873
- cacheWrite: 3.75,
1874
- },
1875
- contextWindow: 200000,
1876
- maxTokens: 8192,
1877
- },
1878
- "claude-3-7-sonnet-20250219": {
1879
- id: "claude-3-7-sonnet-20250219",
1880
- name: "Claude Sonnet 3.7",
1881
- api: "anthropic-messages",
1882
- provider: "anthropic",
1883
- baseUrl: "https://api.anthropic.com",
1884
- reasoning: true,
1885
- thinkingType: "budget",
1886
- input: ["text", "image"],
1887
- cost: {
1888
- input: 3,
1889
- output: 15,
1890
- cacheRead: 0.3,
1891
- cacheWrite: 3.75,
1892
- },
1893
- contextWindow: 200000,
1894
- maxTokens: 64000,
1895
- },
1896
- "claude-3-haiku-20240307": {
1897
- id: "claude-3-haiku-20240307",
1898
- name: "Claude Haiku 3",
1899
- api: "anthropic-messages",
1900
- provider: "anthropic",
1901
- baseUrl: "https://api.anthropic.com",
1902
- reasoning: false,
1903
- input: ["text", "image"],
1904
- cost: {
1905
- input: 0.25,
1906
- output: 1.25,
1907
- cacheRead: 0.03,
1908
- cacheWrite: 0.3,
1909
- },
1910
- contextWindow: 200000,
1911
- maxTokens: 4096,
1912
- },
1913
- "claude-3-opus-20240229": {
1914
- id: "claude-3-opus-20240229",
1915
- name: "Claude Opus 3",
1916
- api: "anthropic-messages",
1917
- provider: "anthropic",
1918
- baseUrl: "https://api.anthropic.com",
1919
- reasoning: false,
1920
- input: ["text", "image"],
1921
- cost: {
1922
- input: 15,
1923
- output: 75,
1924
- cacheRead: 1.5,
1925
- cacheWrite: 18.75,
1926
- },
1927
- contextWindow: 200000,
1928
- maxTokens: 4096,
1929
- },
1930
- "claude-3-sonnet-20240229": {
1931
- id: "claude-3-sonnet-20240229",
1932
- name: "Claude Sonnet 3",
1933
- api: "anthropic-messages",
1934
- provider: "anthropic",
1935
- baseUrl: "https://api.anthropic.com",
1936
- reasoning: false,
1937
- input: ["text", "image"],
1938
- cost: {
1939
- input: 3,
1940
- output: 15,
1941
- cacheRead: 0.3,
1942
- cacheWrite: 0.3,
1943
- },
1944
- contextWindow: 200000,
1945
- maxTokens: 4096,
1946
- },
1947
1881
  "claude-fable-5": {
1948
1882
  id: "claude-fable-5",
1949
1883
  name: "Claude Fable 5",
@@ -1999,24 +1933,6 @@ export const MODELS = {
1999
1933
  contextWindow: 200000,
2000
1934
  maxTokens: 64000,
2001
1935
  },
2002
- "claude-opus-4-0": {
2003
- id: "claude-opus-4-0",
2004
- name: "Claude Opus 4 (latest)",
2005
- api: "anthropic-messages",
2006
- provider: "anthropic",
2007
- baseUrl: "https://api.anthropic.com",
2008
- reasoning: true,
2009
- thinkingType: "budget",
2010
- input: ["text", "image"],
2011
- cost: {
2012
- input: 15,
2013
- output: 75,
2014
- cacheRead: 1.5,
2015
- cacheWrite: 18.75,
2016
- },
2017
- contextWindow: 200000,
2018
- maxTokens: 32000,
2019
- },
2020
1936
  "claude-opus-4-1": {
2021
1937
  id: "claude-opus-4-1",
2022
1938
  name: "Claude Opus 4.1 (latest)",
@@ -2053,24 +1969,6 @@ export const MODELS = {
2053
1969
  contextWindow: 200000,
2054
1970
  maxTokens: 32000,
2055
1971
  },
2056
- "claude-opus-4-20250514": {
2057
- id: "claude-opus-4-20250514",
2058
- name: "Claude Opus 4",
2059
- api: "anthropic-messages",
2060
- provider: "anthropic",
2061
- baseUrl: "https://api.anthropic.com",
2062
- reasoning: true,
2063
- thinkingType: "budget",
2064
- input: ["text", "image"],
2065
- cost: {
2066
- input: 15,
2067
- output: 75,
2068
- cacheRead: 1.5,
2069
- cacheWrite: 18.75,
2070
- },
2071
- contextWindow: 200000,
2072
- maxTokens: 32000,
2073
- },
2074
1972
  "claude-opus-4-5": {
2075
1973
  id: "claude-opus-4-5",
2076
1974
  name: "Claude Opus 4.5 (latest)",
@@ -2164,42 +2062,6 @@ export const MODELS = {
2164
2062
  contextWindow: 1000000,
2165
2063
  maxTokens: 128000,
2166
2064
  },
2167
- "claude-sonnet-4-0": {
2168
- id: "claude-sonnet-4-0",
2169
- name: "Claude Sonnet 4 (latest)",
2170
- api: "anthropic-messages",
2171
- provider: "anthropic",
2172
- baseUrl: "https://api.anthropic.com",
2173
- reasoning: true,
2174
- thinkingType: "budget",
2175
- input: ["text", "image"],
2176
- cost: {
2177
- input: 3,
2178
- output: 15,
2179
- cacheRead: 0.3,
2180
- cacheWrite: 3.75,
2181
- },
2182
- contextWindow: 200000,
2183
- maxTokens: 64000,
2184
- },
2185
- "claude-sonnet-4-20250514": {
2186
- id: "claude-sonnet-4-20250514",
2187
- name: "Claude Sonnet 4",
2188
- api: "anthropic-messages",
2189
- provider: "anthropic",
2190
- baseUrl: "https://api.anthropic.com",
2191
- reasoning: true,
2192
- thinkingType: "budget",
2193
- input: ["text", "image"],
2194
- cost: {
2195
- input: 3,
2196
- output: 15,
2197
- cacheRead: 0.3,
2198
- cacheWrite: 3.75,
2199
- },
2200
- contextWindow: 200000,
2201
- maxTokens: 64000,
2202
- },
2203
2065
  "claude-sonnet-4-5": {
2204
2066
  id: "claude-sonnet-4-5",
2205
2067
  name: "Claude Sonnet 4.5 (latest)",
@@ -2215,7 +2077,7 @@ export const MODELS = {
2215
2077
  cacheRead: 0.3,
2216
2078
  cacheWrite: 3.75,
2217
2079
  },
2218
- contextWindow: 200000,
2080
+ contextWindow: 1000000,
2219
2081
  maxTokens: 64000,
2220
2082
  },
2221
2083
  "claude-sonnet-4-5-20250929": {
@@ -2233,7 +2095,7 @@ export const MODELS = {
2233
2095
  cacheRead: 0.3,
2234
2096
  cacheWrite: 3.75,
2235
2097
  },
2236
- contextWindow: 200000,
2098
+ contextWindow: 1000000,
2237
2099
  maxTokens: 64000,
2238
2100
  },
2239
2101
  "claude-sonnet-4-6": {
@@ -2252,7 +2114,7 @@ export const MODELS = {
2252
2114
  cacheWrite: 3.75,
2253
2115
  },
2254
2116
  contextWindow: 1000000,
2255
- maxTokens: 64000,
2117
+ maxTokens: 128000,
2256
2118
  },
2257
2119
  "claude-sonnet-5": {
2258
2120
  id: "claude-sonnet-5",
@@ -2808,6 +2670,78 @@ export const MODELS = {
2808
2670
  contextWindow: 1050000,
2809
2671
  maxTokens: 128000,
2810
2672
  },
2673
+ "gpt-5.6": {
2674
+ id: "gpt-5.6",
2675
+ name: "GPT-5.6",
2676
+ api: "azure-openai-responses",
2677
+ provider: "azure-openai-responses",
2678
+ baseUrl: "",
2679
+ reasoning: true,
2680
+ thinkingLevelMap: { "off": null },
2681
+ input: ["text", "image"],
2682
+ cost: {
2683
+ input: 5,
2684
+ output: 30,
2685
+ cacheRead: 0.5,
2686
+ cacheWrite: 6.25,
2687
+ },
2688
+ contextWindow: 1050000,
2689
+ maxTokens: 128000,
2690
+ },
2691
+ "gpt-5.6-luna": {
2692
+ id: "gpt-5.6-luna",
2693
+ name: "GPT-5.6 Luna",
2694
+ api: "azure-openai-responses",
2695
+ provider: "azure-openai-responses",
2696
+ baseUrl: "",
2697
+ reasoning: true,
2698
+ thinkingLevelMap: { "off": null },
2699
+ input: ["text", "image"],
2700
+ cost: {
2701
+ input: 1,
2702
+ output: 6,
2703
+ cacheRead: 0.1,
2704
+ cacheWrite: 1.25,
2705
+ },
2706
+ contextWindow: 1050000,
2707
+ maxTokens: 128000,
2708
+ },
2709
+ "gpt-5.6-sol": {
2710
+ id: "gpt-5.6-sol",
2711
+ name: "GPT-5.6 Sol",
2712
+ api: "azure-openai-responses",
2713
+ provider: "azure-openai-responses",
2714
+ baseUrl: "",
2715
+ reasoning: true,
2716
+ thinkingLevelMap: { "off": null },
2717
+ input: ["text", "image"],
2718
+ cost: {
2719
+ input: 5,
2720
+ output: 30,
2721
+ cacheRead: 0.5,
2722
+ cacheWrite: 6.25,
2723
+ },
2724
+ contextWindow: 1050000,
2725
+ maxTokens: 128000,
2726
+ },
2727
+ "gpt-5.6-terra": {
2728
+ id: "gpt-5.6-terra",
2729
+ name: "GPT-5.6 Terra",
2730
+ api: "azure-openai-responses",
2731
+ provider: "azure-openai-responses",
2732
+ baseUrl: "",
2733
+ reasoning: true,
2734
+ thinkingLevelMap: { "off": null },
2735
+ input: ["text", "image"],
2736
+ cost: {
2737
+ input: 2.5,
2738
+ output: 15,
2739
+ cacheRead: 0.25,
2740
+ cacheWrite: 3.125,
2741
+ },
2742
+ contextWindow: 1050000,
2743
+ maxTokens: 128000,
2744
+ },
2811
2745
  "o1": {
2812
2746
  id: "o1",
2813
2747
  name: "o1",
@@ -2946,6 +2880,23 @@ export const MODELS = {
2946
2880
  },
2947
2881
  },
2948
2882
  "cerebras": {
2883
+ "gemma-4-31b": {
2884
+ id: "gemma-4-31b",
2885
+ name: "Gemma 4 31B IT",
2886
+ api: "openai-completions",
2887
+ provider: "cerebras",
2888
+ baseUrl: "https://api.cerebras.ai/v1",
2889
+ reasoning: true,
2890
+ input: ["text", "image"],
2891
+ cost: {
2892
+ input: 0.99,
2893
+ output: 1.49,
2894
+ cacheRead: 0,
2895
+ cacheWrite: 0,
2896
+ },
2897
+ contextWindow: 131072,
2898
+ maxTokens: 40960,
2899
+ },
2949
2900
  "gpt-oss-120b": {
2950
2901
  id: "gpt-oss-120b",
2951
2902
  name: "GPT OSS 120B",
@@ -3241,6 +3192,23 @@ export const MODELS = {
3241
3192
  contextWindow: 1000000,
3242
3193
  maxTokens: 64000,
3243
3194
  },
3195
+ "claude-sonnet-5": {
3196
+ id: "claude-sonnet-5",
3197
+ name: "Claude Sonnet 5",
3198
+ api: "anthropic-messages",
3199
+ provider: "cloudflare-ai-gateway",
3200
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
3201
+ reasoning: true,
3202
+ input: ["text", "image"],
3203
+ cost: {
3204
+ input: 2,
3205
+ output: 10,
3206
+ cacheRead: 0.2,
3207
+ cacheWrite: 2.5,
3208
+ },
3209
+ contextWindow: 1000000,
3210
+ maxTokens: 128000,
3211
+ },
3244
3212
  "gpt-4": {
3245
3213
  id: "gpt-4",
3246
3214
  name: "GPT-4",
@@ -3915,7 +3883,7 @@ export const MODELS = {
3915
3883
  cost: {
3916
3884
  input: 1.4,
3917
3885
  output: 4.4,
3918
- cacheRead: 0.26,
3886
+ cacheRead: 0.14,
3919
3887
  cacheWrite: 0,
3920
3888
  },
3921
3889
  contextWindow: 1048575,
@@ -4297,6 +4265,25 @@ export const MODELS = {
4297
4265
  contextWindow: 1000000,
4298
4266
  maxTokens: 32000,
4299
4267
  },
4268
+ "claude-sonnet-5": {
4269
+ id: "claude-sonnet-5",
4270
+ name: "Claude Sonnet 5",
4271
+ api: "openai-completions",
4272
+ provider: "github-copilot",
4273
+ baseUrl: "https://api.individual.githubcopilot.com",
4274
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
4275
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4276
+ reasoning: true,
4277
+ input: ["text", "image"],
4278
+ cost: {
4279
+ input: 2,
4280
+ output: 10,
4281
+ cacheRead: 0.2,
4282
+ cacheWrite: 2.5,
4283
+ },
4284
+ contextWindow: 1000000,
4285
+ maxTokens: 128000,
4286
+ },
4300
4287
  "gemini-2.5-pro": {
4301
4288
  id: "gemini-2.5-pro",
4302
4289
  name: "Gemini 2.5 Pro",
@@ -4544,6 +4531,44 @@ export const MODELS = {
4544
4531
  contextWindow: 400000,
4545
4532
  maxTokens: 128000,
4546
4533
  },
4534
+ "kimi-k2.7-code": {
4535
+ id: "kimi-k2.7-code",
4536
+ name: "Kimi K2.7 Code",
4537
+ api: "openai-completions",
4538
+ provider: "github-copilot",
4539
+ baseUrl: "https://api.individual.githubcopilot.com",
4540
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
4541
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4542
+ reasoning: true,
4543
+ input: ["text", "image"],
4544
+ cost: {
4545
+ input: 0.95,
4546
+ output: 4,
4547
+ cacheRead: 0.19,
4548
+ cacheWrite: 0,
4549
+ },
4550
+ contextWindow: 256000,
4551
+ maxTokens: 32000,
4552
+ },
4553
+ "mai-code-1-flash-picker": {
4554
+ id: "mai-code-1-flash-picker",
4555
+ name: "MAI-Code-1-Flash",
4556
+ api: "openai-completions",
4557
+ provider: "github-copilot",
4558
+ baseUrl: "https://api.individual.githubcopilot.com",
4559
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
4560
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4561
+ reasoning: true,
4562
+ input: ["text"],
4563
+ cost: {
4564
+ input: 0.75,
4565
+ output: 4.5,
4566
+ cacheRead: 0.075,
4567
+ cacheWrite: 0,
4568
+ },
4569
+ contextWindow: 256000,
4570
+ maxTokens: 128000,
4571
+ },
4547
4572
  },
4548
4573
  "google": {
4549
4574
  "gemini-2.0-flash": {
@@ -5826,6 +5851,24 @@ export const MODELS = {
5826
5851
  contextWindow: 131072,
5827
5852
  maxTokens: 32768,
5828
5853
  },
5854
+ "openai/gpt-oss-20b": {
5855
+ id: "openai/gpt-oss-20b",
5856
+ name: "GPT OSS 20B",
5857
+ api: "openai-completions",
5858
+ provider: "huggingface",
5859
+ baseUrl: "https://router.huggingface.co/v1",
5860
+ compat: { "supportsDeveloperRole": false },
5861
+ reasoning: true,
5862
+ input: ["text"],
5863
+ cost: {
5864
+ input: 0.1,
5865
+ output: 0.5,
5866
+ cacheRead: 0,
5867
+ cacheWrite: 0,
5868
+ },
5869
+ contextWindow: 131072,
5870
+ maxTokens: 32768,
5871
+ },
5829
5872
  "stepfun-ai/Step-3.5-Flash": {
5830
5873
  id: "stepfun-ai/Step-3.5-Flash",
5831
5874
  name: "Step 3.5 Flash",
@@ -6517,11 +6560,11 @@ export const MODELS = {
6517
6560
  api: "mistral-conversations",
6518
6561
  provider: "mistral",
6519
6562
  baseUrl: "https://api.mistral.ai",
6520
- reasoning: false,
6563
+ reasoning: true,
6521
6564
  input: ["text", "image"],
6522
6565
  cost: {
6523
- input: 0.4,
6524
- output: 2,
6566
+ input: 1.5,
6567
+ output: 7.5,
6525
6568
  cacheRead: 0,
6526
6569
  cacheWrite: 0,
6527
6570
  },
@@ -7562,6 +7605,78 @@ export const MODELS = {
7562
7605
  contextWindow: 1050000,
7563
7606
  maxTokens: 128000,
7564
7607
  },
7608
+ "gpt-5.6": {
7609
+ id: "gpt-5.6",
7610
+ name: "GPT-5.6",
7611
+ api: "openai-responses",
7612
+ provider: "openai",
7613
+ baseUrl: "https://api.openai.com/v1",
7614
+ reasoning: true,
7615
+ thinkingLevelMap: { "off": null },
7616
+ input: ["text", "image"],
7617
+ cost: {
7618
+ input: 5,
7619
+ output: 30,
7620
+ cacheRead: 0.5,
7621
+ cacheWrite: 6.25,
7622
+ },
7623
+ contextWindow: 1050000,
7624
+ maxTokens: 128000,
7625
+ },
7626
+ "gpt-5.6-luna": {
7627
+ id: "gpt-5.6-luna",
7628
+ name: "GPT-5.6 Luna",
7629
+ api: "openai-responses",
7630
+ provider: "openai",
7631
+ baseUrl: "https://api.openai.com/v1",
7632
+ reasoning: true,
7633
+ thinkingLevelMap: { "off": null },
7634
+ input: ["text", "image"],
7635
+ cost: {
7636
+ input: 1,
7637
+ output: 6,
7638
+ cacheRead: 0.1,
7639
+ cacheWrite: 1.25,
7640
+ },
7641
+ contextWindow: 1050000,
7642
+ maxTokens: 128000,
7643
+ },
7644
+ "gpt-5.6-sol": {
7645
+ id: "gpt-5.6-sol",
7646
+ name: "GPT-5.6 Sol",
7647
+ api: "openai-responses",
7648
+ provider: "openai",
7649
+ baseUrl: "https://api.openai.com/v1",
7650
+ reasoning: true,
7651
+ thinkingLevelMap: { "off": null },
7652
+ input: ["text", "image"],
7653
+ cost: {
7654
+ input: 5,
7655
+ output: 30,
7656
+ cacheRead: 0.5,
7657
+ cacheWrite: 6.25,
7658
+ },
7659
+ contextWindow: 1050000,
7660
+ maxTokens: 128000,
7661
+ },
7662
+ "gpt-5.6-terra": {
7663
+ id: "gpt-5.6-terra",
7664
+ name: "GPT-5.6 Terra",
7665
+ api: "openai-responses",
7666
+ provider: "openai",
7667
+ baseUrl: "https://api.openai.com/v1",
7668
+ reasoning: true,
7669
+ thinkingLevelMap: { "off": null },
7670
+ input: ["text", "image"],
7671
+ cost: {
7672
+ input: 2.5,
7673
+ output: 15,
7674
+ cacheRead: 0.25,
7675
+ cacheWrite: 3.125,
7676
+ },
7677
+ contextWindow: 1050000,
7678
+ maxTokens: 128000,
7679
+ },
7565
7680
  "o1": {
7566
7681
  id: "o1",
7567
7682
  name: "o1",
@@ -7897,6 +8012,24 @@ export const MODELS = {
7897
8012
  contextWindow: 200000,
7898
8013
  maxTokens: 32000,
7899
8014
  },
8015
+ "claude-fable-5": {
8016
+ id: "claude-fable-5",
8017
+ name: "Claude Fable 5",
8018
+ api: "anthropic-messages",
8019
+ provider: "opencode",
8020
+ baseUrl: "https://opencode.ai/zen",
8021
+ reasoning: true,
8022
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
8023
+ input: ["text", "image"],
8024
+ cost: {
8025
+ input: 10,
8026
+ output: 50,
8027
+ cacheRead: 1,
8028
+ cacheWrite: 12.5,
8029
+ },
8030
+ contextWindow: 1000000,
8031
+ maxTokens: 128000,
8032
+ },
7900
8033
  "claude-haiku-4-5": {
7901
8034
  id: "claude-haiku-4-5",
7902
8035
  name: "Claude Haiku 4.5",
@@ -8053,6 +8186,23 @@ export const MODELS = {
8053
8186
  contextWindow: 1000000,
8054
8187
  maxTokens: 64000,
8055
8188
  },
8189
+ "claude-sonnet-5": {
8190
+ id: "claude-sonnet-5",
8191
+ name: "Claude Sonnet 5",
8192
+ api: "anthropic-messages",
8193
+ provider: "opencode",
8194
+ baseUrl: "https://opencode.ai/zen",
8195
+ reasoning: true,
8196
+ input: ["text", "image"],
8197
+ cost: {
8198
+ input: 2,
8199
+ output: 10,
8200
+ cacheRead: 0.2,
8201
+ cacheWrite: 2.5,
8202
+ },
8203
+ contextWindow: 1000000,
8204
+ maxTokens: 128000,
8205
+ },
8056
8206
  "deepseek-v4-flash": {
8057
8207
  id: "deepseek-v4-flash",
8058
8208
  name: "DeepSeek V4 Flash",
@@ -8503,6 +8653,23 @@ export const MODELS = {
8503
8653
  contextWindow: 1050000,
8504
8654
  maxTokens: 128000,
8505
8655
  },
8656
+ "grok-4.5": {
8657
+ id: "grok-4.5",
8658
+ name: "Grok 4.5",
8659
+ api: "openai-completions",
8660
+ provider: "opencode",
8661
+ baseUrl: "https://opencode.ai/zen/v1",
8662
+ reasoning: true,
8663
+ input: ["text", "image"],
8664
+ cost: {
8665
+ input: 2,
8666
+ output: 6,
8667
+ cacheRead: 0.5,
8668
+ cacheWrite: 0,
8669
+ },
8670
+ contextWindow: 500000,
8671
+ maxTokens: 500000,
8672
+ },
8506
8673
  "grok-build-0.1": {
8507
8674
  id: "grok-build-0.1",
8508
8675
  name: "Grok Build 0.1",
@@ -8520,6 +8687,23 @@ export const MODELS = {
8520
8687
  contextWindow: 256000,
8521
8688
  maxTokens: 256000,
8522
8689
  },
8690
+ "hy3-free": {
8691
+ id: "hy3-free",
8692
+ name: "Hy3 Free",
8693
+ api: "openai-completions",
8694
+ provider: "opencode",
8695
+ baseUrl: "https://opencode.ai/zen/v1",
8696
+ reasoning: true,
8697
+ input: ["text"],
8698
+ cost: {
8699
+ input: 0,
8700
+ output: 0,
8701
+ cacheRead: 0,
8702
+ cacheWrite: 0,
8703
+ },
8704
+ contextWindow: 256000,
8705
+ maxTokens: 64000,
8706
+ },
8523
8707
  "kimi-k2.5": {
8524
8708
  id: "kimi-k2.5",
8525
8709
  name: "Kimi K2.5",
@@ -8537,9 +8721,26 @@ export const MODELS = {
8537
8721
  contextWindow: 262144,
8538
8722
  maxTokens: 65536,
8539
8723
  },
8540
- "kimi-k2.6": {
8541
- id: "kimi-k2.6",
8542
- name: "Kimi K2.6",
8724
+ "kimi-k2.6": {
8725
+ id: "kimi-k2.6",
8726
+ name: "Kimi K2.6",
8727
+ api: "openai-completions",
8728
+ provider: "opencode",
8729
+ baseUrl: "https://opencode.ai/zen/v1",
8730
+ reasoning: true,
8731
+ input: ["text", "image"],
8732
+ cost: {
8733
+ input: 0.95,
8734
+ output: 4,
8735
+ cacheRead: 0.16,
8736
+ cacheWrite: 0,
8737
+ },
8738
+ contextWindow: 262144,
8739
+ maxTokens: 65536,
8740
+ },
8741
+ "kimi-k2.7-code": {
8742
+ id: "kimi-k2.7-code",
8743
+ name: "Kimi K2.7 Code",
8543
8744
  api: "openai-completions",
8544
8745
  provider: "opencode",
8545
8746
  baseUrl: "https://opencode.ai/zen/v1",
@@ -8548,11 +8749,11 @@ export const MODELS = {
8548
8749
  cost: {
8549
8750
  input: 0.95,
8550
8751
  output: 4,
8551
- cacheRead: 0.16,
8752
+ cacheRead: 0.19,
8552
8753
  cacheWrite: 0,
8553
8754
  },
8554
8755
  contextWindow: 262144,
8555
- maxTokens: 65536,
8756
+ maxTokens: 262144,
8556
8757
  },
8557
8758
  "mimo-v2.5-free": {
8558
8759
  id: "mimo-v2.5-free",
@@ -8573,7 +8774,7 @@ export const MODELS = {
8573
8774
  },
8574
8775
  "minimax-m2.5": {
8575
8776
  id: "minimax-m2.5",
8576
- name: "MiniMax M2.5",
8777
+ name: "MiniMax-M2.5",
8577
8778
  api: "openai-completions",
8578
8779
  provider: "opencode",
8579
8780
  baseUrl: "https://opencode.ai/zen/v1",
@@ -8590,7 +8791,7 @@ export const MODELS = {
8590
8791
  },
8591
8792
  "minimax-m2.7": {
8592
8793
  id: "minimax-m2.7",
8593
- name: "MiniMax M2.7",
8794
+ name: "MiniMax-M2.7",
8594
8795
  api: "openai-completions",
8595
8796
  provider: "opencode",
8596
8797
  baseUrl: "https://opencode.ai/zen/v1",
@@ -8605,6 +8806,23 @@ export const MODELS = {
8605
8806
  contextWindow: 204800,
8606
8807
  maxTokens: 131072,
8607
8808
  },
8809
+ "minimax-m3": {
8810
+ id: "minimax-m3",
8811
+ name: "MiniMax-M3",
8812
+ api: "openai-completions",
8813
+ provider: "opencode",
8814
+ baseUrl: "https://opencode.ai/zen/v1",
8815
+ reasoning: true,
8816
+ input: ["text", "image"],
8817
+ cost: {
8818
+ input: 0.3,
8819
+ output: 1.2,
8820
+ cacheRead: 0.06,
8821
+ cacheWrite: 0,
8822
+ },
8823
+ contextWindow: 512000,
8824
+ maxTokens: 128000,
8825
+ },
8608
8826
  "nemotron-3-ultra-free": {
8609
8827
  id: "nemotron-3-ultra-free",
8610
8828
  name: "Nemotron 3 Ultra Free",
@@ -8817,7 +9035,7 @@ export const MODELS = {
8817
9035
  },
8818
9036
  "minimax-m2.7": {
8819
9037
  id: "minimax-m2.7",
8820
- name: "MiniMax M2.7",
9038
+ name: "MiniMax-M2.7",
8821
9039
  api: "openai-completions",
8822
9040
  provider: "opencode-go",
8823
9041
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -8834,7 +9052,7 @@ export const MODELS = {
8834
9052
  },
8835
9053
  "minimax-m3": {
8836
9054
  id: "minimax-m3",
8837
- name: "MiniMax M3 (3x usage)",
9055
+ name: "MiniMax-M3",
8838
9056
  api: "anthropic-messages",
8839
9057
  provider: "opencode-go",
8840
9058
  baseUrl: "https://opencode.ai/zen/go",
@@ -8920,6 +9138,57 @@ export const MODELS = {
8920
9138
  contextWindow: 256000,
8921
9139
  maxTokens: 4096,
8922
9140
  },
9141
+ "aion-labs/aion-2.0": {
9142
+ id: "aion-labs/aion-2.0",
9143
+ name: "AionLabs: Aion-2.0",
9144
+ api: "openai-completions",
9145
+ provider: "openrouter",
9146
+ baseUrl: "https://openrouter.ai/api/v1",
9147
+ reasoning: true,
9148
+ input: ["text"],
9149
+ cost: {
9150
+ input: 0.7999999999999999,
9151
+ output: 1.5999999999999999,
9152
+ cacheRead: 0.19999999999999998,
9153
+ cacheWrite: 0,
9154
+ },
9155
+ contextWindow: 131072,
9156
+ maxTokens: 32768,
9157
+ },
9158
+ "aion-labs/aion-3.0": {
9159
+ id: "aion-labs/aion-3.0",
9160
+ name: "AionLabs: Aion-3.0",
9161
+ api: "openai-completions",
9162
+ provider: "openrouter",
9163
+ baseUrl: "https://openrouter.ai/api/v1",
9164
+ reasoning: true,
9165
+ input: ["text"],
9166
+ cost: {
9167
+ input: 3,
9168
+ output: 6,
9169
+ cacheRead: 0.75,
9170
+ cacheWrite: 0,
9171
+ },
9172
+ contextWindow: 131072,
9173
+ maxTokens: 32768,
9174
+ },
9175
+ "aion-labs/aion-3.0-mini": {
9176
+ id: "aion-labs/aion-3.0-mini",
9177
+ name: "AionLabs: Aion-3.0-Mini",
9178
+ api: "openai-completions",
9179
+ provider: "openrouter",
9180
+ baseUrl: "https://openrouter.ai/api/v1",
9181
+ reasoning: true,
9182
+ input: ["text"],
9183
+ cost: {
9184
+ input: 0.7,
9185
+ output: 1.4,
9186
+ cacheRead: 0.18,
9187
+ cacheWrite: 0,
9188
+ },
9189
+ contextWindow: 131072,
9190
+ maxTokens: 32768,
9191
+ },
8923
9192
  "amazon/nova-2-lite-v1": {
8924
9193
  id: "amazon/nova-2-lite-v1",
8925
9194
  name: "Amazon: Nova 2 Lite",
@@ -9479,8 +9748,8 @@ export const MODELS = {
9479
9748
  reasoning: false,
9480
9749
  input: ["text"],
9481
9750
  cost: {
9482
- input: 0.19999999999999998,
9483
- output: 0.77,
9751
+ input: 0.24,
9752
+ output: 0.8999999999999999,
9484
9753
  cacheRead: 0.135,
9485
9754
  cacheWrite: 0,
9486
9755
  },
@@ -9600,13 +9869,13 @@ export const MODELS = {
9600
9869
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9601
9870
  input: ["text"],
9602
9871
  cost: {
9603
- input: 0.098,
9604
- output: 0.196,
9605
- cacheRead: 0.02,
9872
+ input: 0.09,
9873
+ output: 0.18,
9874
+ cacheRead: 0.018,
9606
9875
  cacheWrite: 0,
9607
9876
  },
9608
9877
  contextWindow: 1048576,
9609
- maxTokens: 4096,
9878
+ maxTokens: 65536,
9610
9879
  },
9611
9880
  "deepseek/deepseek-v4-pro": {
9612
9881
  id: "deepseek/deepseek-v4-pro",
@@ -9661,23 +9930,6 @@ export const MODELS = {
9661
9930
  contextWindow: 1048576,
9662
9931
  maxTokens: 65535,
9663
9932
  },
9664
- "google/gemini-2.5-flash-lite-preview-09-2025": {
9665
- id: "google/gemini-2.5-flash-lite-preview-09-2025",
9666
- name: "Google: Gemini 2.5 Flash Lite Preview 09-2025",
9667
- api: "openai-completions",
9668
- provider: "openrouter",
9669
- baseUrl: "https://openrouter.ai/api/v1",
9670
- reasoning: true,
9671
- input: ["text", "image"],
9672
- cost: {
9673
- input: 0.09999999999999999,
9674
- output: 0.39999999999999997,
9675
- cacheRead: 0.01,
9676
- cacheWrite: 0.08333333333333334,
9677
- },
9678
- contextWindow: 1048576,
9679
- maxTokens: 65535,
9680
- },
9681
9933
  "google/gemini-2.5-pro": {
9682
9934
  id: "google/gemini-2.5-pro",
9683
9935
  name: "Google: Gemini 2.5 Pro",
@@ -10198,12 +10450,12 @@ export const MODELS = {
10198
10450
  input: ["text"],
10199
10451
  cost: {
10200
10452
  input: 0.255,
10201
- output: 1,
10202
- cacheRead: 0.03,
10453
+ output: 1.02,
10454
+ cacheRead: 0,
10203
10455
  cacheWrite: 0,
10204
10456
  },
10205
10457
  contextWindow: 204800,
10206
- maxTokens: 196608,
10458
+ maxTokens: 131072,
10207
10459
  },
10208
10460
  "minimax/minimax-m2.1": {
10209
10461
  id: "minimax/minimax-m2.1",
@@ -10214,13 +10466,13 @@ export const MODELS = {
10214
10466
  reasoning: true,
10215
10467
  input: ["text"],
10216
10468
  cost: {
10217
- input: 0.29,
10218
- output: 0.95,
10469
+ input: 0.3,
10470
+ output: 1.2,
10219
10471
  cacheRead: 0.03,
10220
10472
  cacheWrite: 0,
10221
10473
  },
10222
10474
  contextWindow: 204800,
10223
- maxTokens: 196608,
10475
+ maxTokens: 131072,
10224
10476
  },
10225
10477
  "minimax/minimax-m2.5": {
10226
10478
  id: "minimax/minimax-m2.5",
@@ -10231,9 +10483,9 @@ export const MODELS = {
10231
10483
  reasoning: true,
10232
10484
  input: ["text"],
10233
10485
  cost: {
10234
- input: 0.12,
10235
- output: 0.48,
10236
- cacheRead: 0,
10486
+ input: 0.15,
10487
+ output: 0.8999999999999999,
10488
+ cacheRead: 0.049999999999999996,
10237
10489
  cacheWrite: 0,
10238
10490
  },
10239
10491
  contextWindow: 204800,
@@ -10248,8 +10500,8 @@ export const MODELS = {
10248
10500
  reasoning: true,
10249
10501
  input: ["text"],
10250
10502
  cost: {
10251
- input: 0.18,
10252
- output: 0.72,
10503
+ input: 0.24,
10504
+ output: 0.96,
10253
10505
  cacheRead: 0,
10254
10506
  cacheWrite: 0,
10255
10507
  },
@@ -10607,11 +10859,11 @@ export const MODELS = {
10607
10859
  cost: {
10608
10860
  input: 0.6,
10609
10861
  output: 2.5,
10610
- cacheRead: 0.6,
10862
+ cacheRead: 0.15,
10611
10863
  cacheWrite: 0,
10612
10864
  },
10613
10865
  contextWindow: 262144,
10614
- maxTokens: 262144,
10866
+ maxTokens: 100352,
10615
10867
  },
10616
10868
  "moonshotai/kimi-k2.5": {
10617
10869
  id: "moonshotai/kimi-k2.5",
@@ -10639,9 +10891,9 @@ export const MODELS = {
10639
10891
  reasoning: true,
10640
10892
  input: ["text", "image"],
10641
10893
  cost: {
10642
- input: 0.55,
10643
- output: 3.1999999999999997,
10644
- cacheRead: 0.11,
10894
+ input: 0.65,
10895
+ output: 3.41,
10896
+ cacheRead: 0.14,
10645
10897
  cacheWrite: 0,
10646
10898
  },
10647
10899
  contextWindow: 262144,
@@ -10656,13 +10908,47 @@ export const MODELS = {
10656
10908
  reasoning: true,
10657
10909
  input: ["text", "image"],
10658
10910
  cost: {
10659
- input: 0.74,
10660
- output: 3.5,
10661
- cacheRead: 0.15,
10911
+ input: 0.72,
10912
+ output: 3.49,
10913
+ cacheRead: 0.159,
10662
10914
  cacheWrite: 0,
10663
10915
  },
10664
10916
  contextWindow: 262144,
10665
- maxTokens: 16384,
10917
+ maxTokens: 262144,
10918
+ },
10919
+ "nex-agi/nex-n2-mini": {
10920
+ id: "nex-agi/nex-n2-mini",
10921
+ name: "Nex AGI: Nex-N2-Mini",
10922
+ api: "openai-completions",
10923
+ provider: "openrouter",
10924
+ baseUrl: "https://openrouter.ai/api/v1",
10925
+ reasoning: true,
10926
+ input: ["text", "image"],
10927
+ cost: {
10928
+ input: 0.024999999999999998,
10929
+ output: 0.09999999999999999,
10930
+ cacheRead: 0.0025,
10931
+ cacheWrite: 0,
10932
+ },
10933
+ contextWindow: 262144,
10934
+ maxTokens: 262144,
10935
+ },
10936
+ "nex-agi/nex-n2-pro": {
10937
+ id: "nex-agi/nex-n2-pro",
10938
+ name: "Nex AGI: Nex-N2-Pro",
10939
+ api: "openai-completions",
10940
+ provider: "openrouter",
10941
+ baseUrl: "https://openrouter.ai/api/v1",
10942
+ reasoning: true,
10943
+ input: ["text", "image"],
10944
+ cost: {
10945
+ input: 0.25,
10946
+ output: 1,
10947
+ cacheRead: 0.024999999999999998,
10948
+ cacheWrite: 0,
10949
+ },
10950
+ contextWindow: 262144,
10951
+ maxTokens: 262144,
10666
10952
  },
10667
10953
  "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
10668
10954
  id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
@@ -10741,13 +11027,13 @@ export const MODELS = {
10741
11027
  reasoning: true,
10742
11028
  input: ["text"],
10743
11029
  cost: {
10744
- input: 0.08499999999999999,
10745
- output: 0.39999999999999997,
11030
+ input: 0.08,
11031
+ output: 0.44999999999999996,
10746
11032
  cacheRead: 0,
10747
11033
  cacheWrite: 0,
10748
11034
  },
10749
11035
  contextWindow: 1000000,
10750
- maxTokens: 16384,
11036
+ maxTokens: 4096,
10751
11037
  },
10752
11038
  "nvidia/nemotron-3-super-120b-a12b:free": {
10753
11039
  id: "nvidia/nemotron-3-super-120b-a12b:free",
@@ -11301,74 +11587,176 @@ export const MODELS = {
11301
11587
  contextWindow: 400000,
11302
11588
  maxTokens: 128000,
11303
11589
  },
11304
- "openai/gpt-5.4-nano": {
11305
- id: "openai/gpt-5.4-nano",
11306
- name: "OpenAI: GPT-5.4 Nano",
11590
+ "openai/gpt-5.4-nano": {
11591
+ id: "openai/gpt-5.4-nano",
11592
+ name: "OpenAI: GPT-5.4 Nano",
11593
+ api: "openai-completions",
11594
+ provider: "openrouter",
11595
+ baseUrl: "https://openrouter.ai/api/v1",
11596
+ reasoning: true,
11597
+ thinkingLevelMap: { "xhigh": "xhigh" },
11598
+ input: ["text", "image"],
11599
+ cost: {
11600
+ input: 0.19999999999999998,
11601
+ output: 1.25,
11602
+ cacheRead: 0.02,
11603
+ cacheWrite: 0,
11604
+ },
11605
+ contextWindow: 400000,
11606
+ maxTokens: 128000,
11607
+ },
11608
+ "openai/gpt-5.4-pro": {
11609
+ id: "openai/gpt-5.4-pro",
11610
+ name: "OpenAI: GPT-5.4 Pro",
11611
+ api: "openai-completions",
11612
+ provider: "openrouter",
11613
+ baseUrl: "https://openrouter.ai/api/v1",
11614
+ reasoning: true,
11615
+ thinkingLevelMap: { "xhigh": "xhigh" },
11616
+ input: ["text", "image"],
11617
+ cost: {
11618
+ input: 30,
11619
+ output: 180,
11620
+ cacheRead: 0,
11621
+ cacheWrite: 0,
11622
+ },
11623
+ contextWindow: 1050000,
11624
+ maxTokens: 128000,
11625
+ },
11626
+ "openai/gpt-5.5": {
11627
+ id: "openai/gpt-5.5",
11628
+ name: "OpenAI: GPT-5.5",
11629
+ api: "openai-completions",
11630
+ provider: "openrouter",
11631
+ baseUrl: "https://openrouter.ai/api/v1",
11632
+ reasoning: true,
11633
+ thinkingLevelMap: { "xhigh": "xhigh" },
11634
+ input: ["text", "image"],
11635
+ cost: {
11636
+ input: 5,
11637
+ output: 30,
11638
+ cacheRead: 0.5,
11639
+ cacheWrite: 0,
11640
+ },
11641
+ contextWindow: 1050000,
11642
+ maxTokens: 128000,
11643
+ },
11644
+ "openai/gpt-5.5-pro": {
11645
+ id: "openai/gpt-5.5-pro",
11646
+ name: "OpenAI: GPT-5.5 Pro",
11647
+ api: "openai-completions",
11648
+ provider: "openrouter",
11649
+ baseUrl: "https://openrouter.ai/api/v1",
11650
+ reasoning: true,
11651
+ thinkingLevelMap: { "xhigh": "xhigh" },
11652
+ input: ["text", "image"],
11653
+ cost: {
11654
+ input: 30,
11655
+ output: 180,
11656
+ cacheRead: 0,
11657
+ cacheWrite: 0,
11658
+ },
11659
+ contextWindow: 1050000,
11660
+ maxTokens: 128000,
11661
+ },
11662
+ "openai/gpt-5.6-luna": {
11663
+ id: "openai/gpt-5.6-luna",
11664
+ name: "OpenAI: GPT-5.6 Luna",
11665
+ api: "openai-completions",
11666
+ provider: "openrouter",
11667
+ baseUrl: "https://openrouter.ai/api/v1",
11668
+ reasoning: true,
11669
+ input: ["text", "image"],
11670
+ cost: {
11671
+ input: 1,
11672
+ output: 6,
11673
+ cacheRead: 0.09999999999999999,
11674
+ cacheWrite: 1.25,
11675
+ },
11676
+ contextWindow: 1050000,
11677
+ maxTokens: 128000,
11678
+ },
11679
+ "openai/gpt-5.6-luna-pro": {
11680
+ id: "openai/gpt-5.6-luna-pro",
11681
+ name: "OpenAI: GPT-5.6 Luna Pro",
11682
+ api: "openai-completions",
11683
+ provider: "openrouter",
11684
+ baseUrl: "https://openrouter.ai/api/v1",
11685
+ reasoning: true,
11686
+ input: ["text", "image"],
11687
+ cost: {
11688
+ input: 1,
11689
+ output: 6,
11690
+ cacheRead: 0.09999999999999999,
11691
+ cacheWrite: 1.25,
11692
+ },
11693
+ contextWindow: 1050000,
11694
+ maxTokens: 128000,
11695
+ },
11696
+ "openai/gpt-5.6-sol": {
11697
+ id: "openai/gpt-5.6-sol",
11698
+ name: "OpenAI: GPT-5.6 Sol",
11307
11699
  api: "openai-completions",
11308
11700
  provider: "openrouter",
11309
11701
  baseUrl: "https://openrouter.ai/api/v1",
11310
11702
  reasoning: true,
11311
- thinkingLevelMap: { "xhigh": "xhigh" },
11312
11703
  input: ["text", "image"],
11313
11704
  cost: {
11314
- input: 0.19999999999999998,
11315
- output: 1.25,
11316
- cacheRead: 0.02,
11317
- cacheWrite: 0,
11705
+ input: 5,
11706
+ output: 30,
11707
+ cacheRead: 0.5,
11708
+ cacheWrite: 6.25,
11318
11709
  },
11319
- contextWindow: 400000,
11710
+ contextWindow: 1050000,
11320
11711
  maxTokens: 128000,
11321
11712
  },
11322
- "openai/gpt-5.4-pro": {
11323
- id: "openai/gpt-5.4-pro",
11324
- name: "OpenAI: GPT-5.4 Pro",
11713
+ "openai/gpt-5.6-sol-pro": {
11714
+ id: "openai/gpt-5.6-sol-pro",
11715
+ name: "OpenAI: GPT-5.6 Sol Pro",
11325
11716
  api: "openai-completions",
11326
11717
  provider: "openrouter",
11327
11718
  baseUrl: "https://openrouter.ai/api/v1",
11328
11719
  reasoning: true,
11329
- thinkingLevelMap: { "xhigh": "xhigh" },
11330
11720
  input: ["text", "image"],
11331
11721
  cost: {
11332
- input: 30,
11333
- output: 180,
11334
- cacheRead: 0,
11335
- cacheWrite: 0,
11722
+ input: 5,
11723
+ output: 30,
11724
+ cacheRead: 0.5,
11725
+ cacheWrite: 6.25,
11336
11726
  },
11337
11727
  contextWindow: 1050000,
11338
11728
  maxTokens: 128000,
11339
11729
  },
11340
- "openai/gpt-5.5": {
11341
- id: "openai/gpt-5.5",
11342
- name: "OpenAI: GPT-5.5",
11730
+ "openai/gpt-5.6-terra": {
11731
+ id: "openai/gpt-5.6-terra",
11732
+ name: "OpenAI: GPT-5.6 Terra",
11343
11733
  api: "openai-completions",
11344
11734
  provider: "openrouter",
11345
11735
  baseUrl: "https://openrouter.ai/api/v1",
11346
11736
  reasoning: true,
11347
- thinkingLevelMap: { "xhigh": "xhigh" },
11348
11737
  input: ["text", "image"],
11349
11738
  cost: {
11350
- input: 5,
11351
- output: 30,
11352
- cacheRead: 0.5,
11353
- cacheWrite: 0,
11739
+ input: 2.5,
11740
+ output: 15,
11741
+ cacheRead: 0.25,
11742
+ cacheWrite: 3.125,
11354
11743
  },
11355
11744
  contextWindow: 1050000,
11356
11745
  maxTokens: 128000,
11357
11746
  },
11358
- "openai/gpt-5.5-pro": {
11359
- id: "openai/gpt-5.5-pro",
11360
- name: "OpenAI: GPT-5.5 Pro",
11747
+ "openai/gpt-5.6-terra-pro": {
11748
+ id: "openai/gpt-5.6-terra-pro",
11749
+ name: "OpenAI: GPT-5.6 Terra Pro",
11361
11750
  api: "openai-completions",
11362
11751
  provider: "openrouter",
11363
11752
  baseUrl: "https://openrouter.ai/api/v1",
11364
11753
  reasoning: true,
11365
- thinkingLevelMap: { "xhigh": "xhigh" },
11366
11754
  input: ["text", "image"],
11367
11755
  cost: {
11368
- input: 30,
11369
- output: 180,
11370
- cacheRead: 0,
11371
- cacheWrite: 0,
11756
+ input: 2.5,
11757
+ output: 15,
11758
+ cacheRead: 0.25,
11759
+ cacheWrite: 3.125,
11372
11760
  },
11373
11761
  contextWindow: 1050000,
11374
11762
  maxTokens: 128000,
@@ -11433,13 +11821,13 @@ export const MODELS = {
11433
11821
  reasoning: true,
11434
11822
  input: ["text"],
11435
11823
  cost: {
11436
- input: 0.03,
11437
- output: 0.15,
11824
+ input: 0.036,
11825
+ output: 0.18,
11438
11826
  cacheRead: 0,
11439
11827
  cacheWrite: 0,
11440
11828
  },
11441
11829
  contextWindow: 131072,
11442
- maxTokens: 131072,
11830
+ maxTokens: 4096,
11443
11831
  },
11444
11832
  "openai/gpt-oss-120b:free": {
11445
11833
  id: "openai/gpt-oss-120b:free",
@@ -11730,26 +12118,26 @@ export const MODELS = {
11730
12118
  contextWindow: 262144,
11731
12119
  maxTokens: 32768,
11732
12120
  },
11733
- "poolside/laguna-xs.2": {
11734
- id: "poolside/laguna-xs.2",
11735
- name: "Poolside: Laguna XS.2",
12121
+ "poolside/laguna-xs-2.1": {
12122
+ id: "poolside/laguna-xs-2.1",
12123
+ name: "Poolside: Laguna XS 2.1",
11736
12124
  api: "openai-completions",
11737
12125
  provider: "openrouter",
11738
12126
  baseUrl: "https://openrouter.ai/api/v1",
11739
12127
  reasoning: true,
11740
12128
  input: ["text"],
11741
12129
  cost: {
11742
- input: 0.09999999999999999,
11743
- output: 0.19999999999999998,
11744
- cacheRead: 0.049999999999999996,
12130
+ input: 0.06,
12131
+ output: 0.12,
12132
+ cacheRead: 0.03,
11745
12133
  cacheWrite: 0,
11746
12134
  },
11747
12135
  contextWindow: 262144,
11748
12136
  maxTokens: 32768,
11749
12137
  },
11750
- "poolside/laguna-xs.2:free": {
11751
- id: "poolside/laguna-xs.2:free",
11752
- name: "Poolside: Laguna XS.2 (free)",
12138
+ "poolside/laguna-xs-2.1:free": {
12139
+ id: "poolside/laguna-xs-2.1:free",
12140
+ name: "Poolside: Laguna XS 2.1 (free)",
11753
12141
  api: "openai-completions",
11754
12142
  provider: "openrouter",
11755
12143
  baseUrl: "https://openrouter.ai/api/v1",
@@ -11960,13 +12348,13 @@ export const MODELS = {
11960
12348
  reasoning: true,
11961
12349
  input: ["text"],
11962
12350
  cost: {
11963
- input: 0.08,
11964
- output: 0.39999999999999997,
11965
- cacheRead: 0.08,
12351
+ input: 0.13,
12352
+ output: 1.56,
12353
+ cacheRead: 0,
11966
12354
  cacheWrite: 0,
11967
12355
  },
11968
12356
  contextWindow: 131072,
11969
- maxTokens: 131072,
12357
+ maxTokens: 32768,
11970
12358
  },
11971
12359
  "qwen/qwen3-32b": {
11972
12360
  id: "qwen/qwen3-32b",
@@ -11994,9 +12382,9 @@ export const MODELS = {
11994
12382
  reasoning: true,
11995
12383
  input: ["text"],
11996
12384
  cost: {
11997
- input: 0.049999999999999996,
11998
- output: 0.39999999999999997,
11999
- cacheRead: 0.049999999999999996,
12385
+ input: 0.117,
12386
+ output: 0.45499999999999996,
12387
+ cacheRead: 0,
12000
12388
  cacheWrite: 0,
12001
12389
  },
12002
12390
  contextWindow: 131072,
@@ -12283,8 +12671,8 @@ export const MODELS = {
12283
12671
  reasoning: false,
12284
12672
  input: ["text", "image"],
12285
12673
  cost: {
12286
- input: 0.08,
12287
- output: 0.5,
12674
+ input: 0.117,
12675
+ output: 0.45499999999999996,
12288
12676
  cacheRead: 0,
12289
12677
  cacheWrite: 0,
12290
12678
  },
@@ -12370,7 +12758,7 @@ export const MODELS = {
12370
12758
  cost: {
12371
12759
  input: 0.385,
12372
12760
  output: 2.4499999999999997,
12373
- cacheRead: 0,
12761
+ cacheRead: 0.111,
12374
12762
  cacheWrite: 0,
12375
12763
  },
12376
12764
  contextWindow: 256000,
@@ -12455,7 +12843,7 @@ export const MODELS = {
12455
12843
  cost: {
12456
12844
  input: 0.28500000000000003,
12457
12845
  output: 2.4,
12458
- cacheRead: 0,
12846
+ cacheRead: 0.15,
12459
12847
  cacheWrite: 0,
12460
12848
  },
12461
12849
  contextWindow: 262144,
@@ -12665,6 +13053,40 @@ export const MODELS = {
12665
13053
  contextWindow: 256000,
12666
13054
  maxTokens: 256000,
12667
13055
  },
13056
+ "tencent/hy3": {
13057
+ id: "tencent/hy3",
13058
+ name: "Tencent: Hy3",
13059
+ api: "openai-completions",
13060
+ provider: "openrouter",
13061
+ baseUrl: "https://openrouter.ai/api/v1",
13062
+ reasoning: true,
13063
+ input: ["text"],
13064
+ cost: {
13065
+ input: 0.14,
13066
+ output: 0.58,
13067
+ cacheRead: 0.035,
13068
+ cacheWrite: 0,
13069
+ },
13070
+ contextWindow: 262144,
13071
+ maxTokens: 4096,
13072
+ },
13073
+ "tencent/hy3:free": {
13074
+ id: "tencent/hy3:free",
13075
+ name: "Tencent: Hy3 (free)",
13076
+ api: "openai-completions",
13077
+ provider: "openrouter",
13078
+ baseUrl: "https://openrouter.ai/api/v1",
13079
+ reasoning: true,
13080
+ input: ["text"],
13081
+ cost: {
13082
+ input: 0,
13083
+ output: 0,
13084
+ cacheRead: 0,
13085
+ cacheWrite: 0,
13086
+ },
13087
+ contextWindow: 262144,
13088
+ maxTokens: 262144,
13089
+ },
12668
13090
  "thedrummer/unslopnemo-12b": {
12669
13091
  id: "thedrummer/unslopnemo-12b",
12670
13092
  name: "TheDrummer: UnslopNemo 12B",
@@ -12733,6 +13155,23 @@ export const MODELS = {
12733
13155
  contextWindow: 1000000,
12734
13156
  maxTokens: 4096,
12735
13157
  },
13158
+ "x-ai/grok-4.5": {
13159
+ id: "x-ai/grok-4.5",
13160
+ name: "xAI: Grok 4.5",
13161
+ api: "openai-completions",
13162
+ provider: "openrouter",
13163
+ baseUrl: "https://openrouter.ai/api/v1",
13164
+ reasoning: true,
13165
+ input: ["text", "image"],
13166
+ cost: {
13167
+ input: 2,
13168
+ output: 6,
13169
+ cacheRead: 0.5,
13170
+ cacheWrite: 0,
13171
+ },
13172
+ contextWindow: 500000,
13173
+ maxTokens: 4096,
13174
+ },
12736
13175
  "x-ai/grok-build-0.1": {
12737
13176
  id: "x-ai/grok-build-0.1",
12738
13177
  name: "xAI: Grok Build 0.1",
@@ -12761,7 +13200,7 @@ export const MODELS = {
12761
13200
  cost: {
12762
13201
  input: 0.105,
12763
13202
  output: 0.28,
12764
- cacheRead: 0,
13203
+ cacheRead: 0.028,
12765
13204
  cacheWrite: 0,
12766
13205
  },
12767
13206
  contextWindow: 1048576,
@@ -12946,13 +13385,13 @@ export const MODELS = {
12946
13385
  reasoning: true,
12947
13386
  input: ["text"],
12948
13387
  cost: {
12949
- input: 0.975,
12950
- output: 4.300000000000001,
12951
- cacheRead: 0,
13388
+ input: 0.966,
13389
+ output: 3.036,
13390
+ cacheRead: 0.1794,
12952
13391
  cacheWrite: 0,
12953
13392
  },
12954
13393
  contextWindow: 202752,
12955
- maxTokens: 4096,
13394
+ maxTokens: 128000,
12956
13395
  },
12957
13396
  "z-ai/glm-5.2": {
12958
13397
  id: "z-ai/glm-5.2",
@@ -12963,13 +13402,13 @@ export const MODELS = {
12963
13402
  reasoning: true,
12964
13403
  input: ["text"],
12965
13404
  cost: {
12966
- input: 0.9299999999999999,
12967
- output: 3,
12968
- cacheRead: 0.18,
13405
+ input: 0.54,
13406
+ output: 1.76,
13407
+ cacheRead: 0.09999999999999999,
12969
13408
  cacheWrite: 0,
12970
13409
  },
12971
13410
  contextWindow: 1048576,
12972
- maxTokens: 32768,
13411
+ maxTokens: 101376,
12973
13412
  },
12974
13413
  "z-ai/glm-5v-turbo": {
12975
13414
  id: "z-ai/glm-5v-turbo",
@@ -13100,9 +13539,9 @@ export const MODELS = {
13100
13539
  reasoning: true,
13101
13540
  input: ["text", "image"],
13102
13541
  cost: {
13103
- input: 0.55,
13104
- output: 3.1999999999999997,
13105
- cacheRead: 0.11,
13542
+ input: 0.65,
13543
+ output: 3.41,
13544
+ cacheRead: 0.14,
13106
13545
  cacheWrite: 0,
13107
13546
  },
13108
13547
  contextWindow: 262144,
@@ -13120,7 +13559,7 @@ export const MODELS = {
13120
13559
  input: 5,
13121
13560
  output: 30,
13122
13561
  cacheRead: 0.5,
13123
- cacheWrite: 0,
13562
+ cacheWrite: 6.25,
13124
13563
  },
13125
13564
  contextWindow: 1050000,
13126
13565
  maxTokens: 128000,
@@ -13142,6 +13581,23 @@ export const MODELS = {
13142
13581
  contextWindow: 400000,
13143
13582
  maxTokens: 128000,
13144
13583
  },
13584
+ "~x-ai/grok-latest": {
13585
+ id: "~x-ai/grok-latest",
13586
+ name: "xAI: Grok Latest",
13587
+ api: "openai-completions",
13588
+ provider: "openrouter",
13589
+ baseUrl: "https://openrouter.ai/api/v1",
13590
+ reasoning: true,
13591
+ input: ["text", "image"],
13592
+ cost: {
13593
+ input: 2,
13594
+ output: 6,
13595
+ cacheRead: 0.5,
13596
+ cacheWrite: 0,
13597
+ },
13598
+ contextWindow: 500000,
13599
+ maxTokens: 4096,
13600
+ },
13145
13601
  },
13146
13602
  "together": {
13147
13603
  "MiniMaxAI/MiniMax-M2.7": {
@@ -13359,8 +13815,8 @@ export const MODELS = {
13359
13815
  reasoning: false,
13360
13816
  input: ["text"],
13361
13817
  cost: {
13362
- input: 0.88,
13363
- output: 0.88,
13818
+ input: 1.04,
13819
+ output: 1.04,
13364
13820
  cacheRead: 0,
13365
13821
  cacheWrite: 0,
13366
13822
  },
@@ -14014,6 +14470,24 @@ export const MODELS = {
14014
14470
  contextWindow: 200000,
14015
14471
  maxTokens: 4096,
14016
14472
  },
14473
+ "anthropic/claude-fable-5": {
14474
+ id: "anthropic/claude-fable-5",
14475
+ name: "Claude Fable 5",
14476
+ api: "anthropic-messages",
14477
+ provider: "vercel-ai-gateway",
14478
+ baseUrl: "https://ai-gateway.vercel.sh",
14479
+ reasoning: true,
14480
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
14481
+ input: ["text", "image"],
14482
+ cost: {
14483
+ input: 10,
14484
+ output: 50,
14485
+ cacheRead: 1,
14486
+ cacheWrite: 12.5,
14487
+ },
14488
+ contextWindow: 1000000,
14489
+ maxTokens: 128000,
14490
+ },
14017
14491
  "anthropic/claude-haiku-4.5": {
14018
14492
  id: "anthropic/claude-haiku-4.5",
14019
14493
  name: "Claude Haiku 4.5",
@@ -14867,6 +15341,23 @@ export const MODELS = {
14867
15341
  contextWindow: 128000,
14868
15342
  maxTokens: 8192,
14869
15343
  },
15344
+ "meta/muse-spark-1.1": {
15345
+ id: "meta/muse-spark-1.1",
15346
+ name: "Muse Spark 1.1",
15347
+ api: "anthropic-messages",
15348
+ provider: "vercel-ai-gateway",
15349
+ baseUrl: "https://ai-gateway.vercel.sh",
15350
+ reasoning: true,
15351
+ input: ["text"],
15352
+ cost: {
15353
+ input: 1.25,
15354
+ output: 4.25,
15355
+ cacheRead: 0.15,
15356
+ cacheWrite: 0,
15357
+ },
15358
+ contextWindow: 1048576,
15359
+ maxTokens: 1048576,
15360
+ },
14870
15361
  "minimax/minimax-m2": {
14871
15362
  id: "minimax/minimax-m2",
14872
15363
  name: "MiniMax M2",
@@ -15967,6 +16458,57 @@ export const MODELS = {
15967
16458
  contextWindow: 1000000,
15968
16459
  maxTokens: 128000,
15969
16460
  },
16461
+ "openai/gpt-5.6-luna": {
16462
+ id: "openai/gpt-5.6-luna",
16463
+ name: "GPT 5.6 Luna",
16464
+ api: "anthropic-messages",
16465
+ provider: "vercel-ai-gateway",
16466
+ baseUrl: "https://ai-gateway.vercel.sh",
16467
+ reasoning: true,
16468
+ input: ["text", "image"],
16469
+ cost: {
16470
+ input: 1,
16471
+ output: 6,
16472
+ cacheRead: 0.09999999999999999,
16473
+ cacheWrite: 1.25,
16474
+ },
16475
+ contextWindow: 1050000,
16476
+ maxTokens: 128000,
16477
+ },
16478
+ "openai/gpt-5.6-sol": {
16479
+ id: "openai/gpt-5.6-sol",
16480
+ name: "GPT 5.6 Sol",
16481
+ api: "anthropic-messages",
16482
+ provider: "vercel-ai-gateway",
16483
+ baseUrl: "https://ai-gateway.vercel.sh",
16484
+ reasoning: true,
16485
+ input: ["text", "image"],
16486
+ cost: {
16487
+ input: 5,
16488
+ output: 30,
16489
+ cacheRead: 0.5,
16490
+ cacheWrite: 6.25,
16491
+ },
16492
+ contextWindow: 1050000,
16493
+ maxTokens: 128000,
16494
+ },
16495
+ "openai/gpt-5.6-terra": {
16496
+ id: "openai/gpt-5.6-terra",
16497
+ name: "GPT 5.6 Terra",
16498
+ api: "anthropic-messages",
16499
+ provider: "vercel-ai-gateway",
16500
+ baseUrl: "https://ai-gateway.vercel.sh",
16501
+ reasoning: true,
16502
+ input: ["text", "image"],
16503
+ cost: {
16504
+ input: 2.5,
16505
+ output: 15,
16506
+ cacheRead: 0.25,
16507
+ cacheWrite: 3.125,
16508
+ },
16509
+ contextWindow: 1050000,
16510
+ maxTokens: 128000,
16511
+ },
15970
16512
  "openai/gpt-oss-120b": {
15971
16513
  id: "openai/gpt-oss-120b",
15972
16514
  name: "GPT OSS 120B",
@@ -16324,6 +16866,23 @@ export const MODELS = {
16324
16866
  contextWindow: 1000000,
16325
16867
  maxTokens: 1000000,
16326
16868
  },
16869
+ "xai/grok-4.5": {
16870
+ id: "xai/grok-4.5",
16871
+ name: "Grok 4.5",
16872
+ api: "anthropic-messages",
16873
+ provider: "vercel-ai-gateway",
16874
+ baseUrl: "https://ai-gateway.vercel.sh",
16875
+ reasoning: true,
16876
+ input: ["text", "image"],
16877
+ cost: {
16878
+ input: 2,
16879
+ output: 6,
16880
+ cacheRead: 0.5,
16881
+ cacheWrite: 0,
16882
+ },
16883
+ contextWindow: 500000,
16884
+ maxTokens: 500000,
16885
+ },
16327
16886
  "xai/grok-build-0.1": {
16328
16887
  id: "xai/grok-build-0.1",
16329
16888
  name: "Grok Build 0.1",
@@ -16588,12 +17147,12 @@ export const MODELS = {
16588
17147
  reasoning: true,
16589
17148
  input: ["text"],
16590
17149
  cost: {
16591
- input: 1.5,
16592
- output: 4.5,
16593
- cacheRead: 0.3,
17150
+ input: 1.4,
17151
+ output: 4.4,
17152
+ cacheRead: 0.26,
16594
17153
  cacheWrite: 0,
16595
17154
  },
16596
- contextWindow: 1000000,
17155
+ contextWindow: 1040000,
16597
17156
  maxTokens: 128000,
16598
17157
  },
16599
17158
  "zai/glm-5.2-fast": {
@@ -16683,6 +17242,23 @@ export const MODELS = {
16683
17242
  contextWindow: 1000000,
16684
17243
  maxTokens: 30000,
16685
17244
  },
17245
+ "grok-4.5": {
17246
+ id: "grok-4.5",
17247
+ name: "Grok 4.5",
17248
+ api: "openai-completions",
17249
+ provider: "xai",
17250
+ baseUrl: "https://api.x.ai/v1",
17251
+ reasoning: true,
17252
+ input: ["text", "image"],
17253
+ cost: {
17254
+ input: 2,
17255
+ output: 6,
17256
+ cacheRead: 0.5,
17257
+ cacheWrite: 0,
17258
+ },
17259
+ contextWindow: 500000,
17260
+ maxTokens: 500000,
17261
+ },
16686
17262
  "grok-build-0.1": {
16687
17263
  id: "grok-build-0.1",
16688
17264
  name: "Grok Build 0.1",