@elyracode/ai 0.9.12 → 0.9.13

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",
@@ -2946,6 +2808,23 @@ export const MODELS = {
2946
2808
  },
2947
2809
  },
2948
2810
  "cerebras": {
2811
+ "gemma-4-31b": {
2812
+ id: "gemma-4-31b",
2813
+ name: "Gemma 4 31B IT",
2814
+ api: "openai-completions",
2815
+ provider: "cerebras",
2816
+ baseUrl: "https://api.cerebras.ai/v1",
2817
+ reasoning: true,
2818
+ input: ["text", "image"],
2819
+ cost: {
2820
+ input: 0.99,
2821
+ output: 1.49,
2822
+ cacheRead: 0,
2823
+ cacheWrite: 0,
2824
+ },
2825
+ contextWindow: 131072,
2826
+ maxTokens: 40960,
2827
+ },
2949
2828
  "gpt-oss-120b": {
2950
2829
  id: "gpt-oss-120b",
2951
2830
  name: "GPT OSS 120B",
@@ -3241,6 +3120,23 @@ export const MODELS = {
3241
3120
  contextWindow: 1000000,
3242
3121
  maxTokens: 64000,
3243
3122
  },
3123
+ "claude-sonnet-5": {
3124
+ id: "claude-sonnet-5",
3125
+ name: "Claude Sonnet 5",
3126
+ api: "anthropic-messages",
3127
+ provider: "cloudflare-ai-gateway",
3128
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
3129
+ reasoning: true,
3130
+ input: ["text", "image"],
3131
+ cost: {
3132
+ input: 2,
3133
+ output: 10,
3134
+ cacheRead: 0.2,
3135
+ cacheWrite: 2.5,
3136
+ },
3137
+ contextWindow: 1000000,
3138
+ maxTokens: 128000,
3139
+ },
3244
3140
  "gpt-4": {
3245
3141
  id: "gpt-4",
3246
3142
  name: "GPT-4",
@@ -3915,7 +3811,7 @@ export const MODELS = {
3915
3811
  cost: {
3916
3812
  input: 1.4,
3917
3813
  output: 4.4,
3918
- cacheRead: 0.26,
3814
+ cacheRead: 0.14,
3919
3815
  cacheWrite: 0,
3920
3816
  },
3921
3817
  contextWindow: 1048575,
@@ -4297,6 +4193,25 @@ export const MODELS = {
4297
4193
  contextWindow: 1000000,
4298
4194
  maxTokens: 32000,
4299
4195
  },
4196
+ "claude-sonnet-5": {
4197
+ id: "claude-sonnet-5",
4198
+ name: "Claude Sonnet 5",
4199
+ api: "openai-completions",
4200
+ provider: "github-copilot",
4201
+ baseUrl: "https://api.individual.githubcopilot.com",
4202
+ 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" },
4203
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4204
+ reasoning: true,
4205
+ input: ["text", "image"],
4206
+ cost: {
4207
+ input: 2,
4208
+ output: 10,
4209
+ cacheRead: 0.2,
4210
+ cacheWrite: 2.5,
4211
+ },
4212
+ contextWindow: 1000000,
4213
+ maxTokens: 128000,
4214
+ },
4300
4215
  "gemini-2.5-pro": {
4301
4216
  id: "gemini-2.5-pro",
4302
4217
  name: "Gemini 2.5 Pro",
@@ -4544,6 +4459,44 @@ export const MODELS = {
4544
4459
  contextWindow: 400000,
4545
4460
  maxTokens: 128000,
4546
4461
  },
4462
+ "kimi-k2.7-code": {
4463
+ id: "kimi-k2.7-code",
4464
+ name: "Kimi K2.7 Code",
4465
+ api: "openai-completions",
4466
+ provider: "github-copilot",
4467
+ baseUrl: "https://api.individual.githubcopilot.com",
4468
+ 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" },
4469
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4470
+ reasoning: true,
4471
+ input: ["text", "image"],
4472
+ cost: {
4473
+ input: 0.95,
4474
+ output: 4,
4475
+ cacheRead: 0.19,
4476
+ cacheWrite: 0,
4477
+ },
4478
+ contextWindow: 256000,
4479
+ maxTokens: 32000,
4480
+ },
4481
+ "mai-code-1-flash-picker": {
4482
+ id: "mai-code-1-flash-picker",
4483
+ name: "MAI-Code-1-Flash",
4484
+ api: "openai-completions",
4485
+ provider: "github-copilot",
4486
+ baseUrl: "https://api.individual.githubcopilot.com",
4487
+ 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" },
4488
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4489
+ reasoning: true,
4490
+ input: ["text"],
4491
+ cost: {
4492
+ input: 0.75,
4493
+ output: 4.5,
4494
+ cacheRead: 0.075,
4495
+ cacheWrite: 0,
4496
+ },
4497
+ contextWindow: 256000,
4498
+ maxTokens: 128000,
4499
+ },
4547
4500
  },
4548
4501
  "google": {
4549
4502
  "gemini-2.0-flash": {
@@ -5826,6 +5779,24 @@ export const MODELS = {
5826
5779
  contextWindow: 131072,
5827
5780
  maxTokens: 32768,
5828
5781
  },
5782
+ "openai/gpt-oss-20b": {
5783
+ id: "openai/gpt-oss-20b",
5784
+ name: "GPT OSS 20B",
5785
+ api: "openai-completions",
5786
+ provider: "huggingface",
5787
+ baseUrl: "https://router.huggingface.co/v1",
5788
+ compat: { "supportsDeveloperRole": false },
5789
+ reasoning: true,
5790
+ input: ["text"],
5791
+ cost: {
5792
+ input: 0.1,
5793
+ output: 0.5,
5794
+ cacheRead: 0,
5795
+ cacheWrite: 0,
5796
+ },
5797
+ contextWindow: 131072,
5798
+ maxTokens: 32768,
5799
+ },
5829
5800
  "stepfun-ai/Step-3.5-Flash": {
5830
5801
  id: "stepfun-ai/Step-3.5-Flash",
5831
5802
  name: "Step 3.5 Flash",
@@ -6517,11 +6488,11 @@ export const MODELS = {
6517
6488
  api: "mistral-conversations",
6518
6489
  provider: "mistral",
6519
6490
  baseUrl: "https://api.mistral.ai",
6520
- reasoning: false,
6491
+ reasoning: true,
6521
6492
  input: ["text", "image"],
6522
6493
  cost: {
6523
- input: 0.4,
6524
- output: 2,
6494
+ input: 1.5,
6495
+ output: 7.5,
6525
6496
  cacheRead: 0,
6526
6497
  cacheWrite: 0,
6527
6498
  },
@@ -7897,6 +7868,24 @@ export const MODELS = {
7897
7868
  contextWindow: 200000,
7898
7869
  maxTokens: 32000,
7899
7870
  },
7871
+ "claude-fable-5": {
7872
+ id: "claude-fable-5",
7873
+ name: "Claude Fable 5",
7874
+ api: "anthropic-messages",
7875
+ provider: "opencode",
7876
+ baseUrl: "https://opencode.ai/zen",
7877
+ reasoning: true,
7878
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
7879
+ input: ["text", "image"],
7880
+ cost: {
7881
+ input: 10,
7882
+ output: 50,
7883
+ cacheRead: 1,
7884
+ cacheWrite: 12.5,
7885
+ },
7886
+ contextWindow: 1000000,
7887
+ maxTokens: 128000,
7888
+ },
7900
7889
  "claude-haiku-4-5": {
7901
7890
  id: "claude-haiku-4-5",
7902
7891
  name: "Claude Haiku 4.5",
@@ -8053,6 +8042,23 @@ export const MODELS = {
8053
8042
  contextWindow: 1000000,
8054
8043
  maxTokens: 64000,
8055
8044
  },
8045
+ "claude-sonnet-5": {
8046
+ id: "claude-sonnet-5",
8047
+ name: "Claude Sonnet 5",
8048
+ api: "anthropic-messages",
8049
+ provider: "opencode",
8050
+ baseUrl: "https://opencode.ai/zen",
8051
+ reasoning: true,
8052
+ input: ["text", "image"],
8053
+ cost: {
8054
+ input: 2,
8055
+ output: 10,
8056
+ cacheRead: 0.2,
8057
+ cacheWrite: 2.5,
8058
+ },
8059
+ contextWindow: 1000000,
8060
+ maxTokens: 128000,
8061
+ },
8056
8062
  "deepseek-v4-flash": {
8057
8063
  id: "deepseek-v4-flash",
8058
8064
  name: "DeepSeek V4 Flash",
@@ -8520,6 +8526,23 @@ export const MODELS = {
8520
8526
  contextWindow: 256000,
8521
8527
  maxTokens: 256000,
8522
8528
  },
8529
+ "hy3-free": {
8530
+ id: "hy3-free",
8531
+ name: "Hy3 Free",
8532
+ api: "openai-completions",
8533
+ provider: "opencode",
8534
+ baseUrl: "https://opencode.ai/zen/v1",
8535
+ reasoning: true,
8536
+ input: ["text"],
8537
+ cost: {
8538
+ input: 0,
8539
+ output: 0,
8540
+ cacheRead: 0,
8541
+ cacheWrite: 0,
8542
+ },
8543
+ contextWindow: 256000,
8544
+ maxTokens: 64000,
8545
+ },
8523
8546
  "kimi-k2.5": {
8524
8547
  id: "kimi-k2.5",
8525
8548
  name: "Kimi K2.5",
@@ -8552,7 +8575,24 @@ export const MODELS = {
8552
8575
  cacheWrite: 0,
8553
8576
  },
8554
8577
  contextWindow: 262144,
8555
- maxTokens: 65536,
8578
+ maxTokens: 65536,
8579
+ },
8580
+ "kimi-k2.7-code": {
8581
+ id: "kimi-k2.7-code",
8582
+ name: "Kimi K2.7 Code",
8583
+ api: "openai-completions",
8584
+ provider: "opencode",
8585
+ baseUrl: "https://opencode.ai/zen/v1",
8586
+ reasoning: true,
8587
+ input: ["text", "image"],
8588
+ cost: {
8589
+ input: 0.95,
8590
+ output: 4,
8591
+ cacheRead: 0.19,
8592
+ cacheWrite: 0,
8593
+ },
8594
+ contextWindow: 262144,
8595
+ maxTokens: 262144,
8556
8596
  },
8557
8597
  "mimo-v2.5-free": {
8558
8598
  id: "mimo-v2.5-free",
@@ -8573,7 +8613,7 @@ export const MODELS = {
8573
8613
  },
8574
8614
  "minimax-m2.5": {
8575
8615
  id: "minimax-m2.5",
8576
- name: "MiniMax M2.5",
8616
+ name: "MiniMax-M2.5",
8577
8617
  api: "openai-completions",
8578
8618
  provider: "opencode",
8579
8619
  baseUrl: "https://opencode.ai/zen/v1",
@@ -8590,7 +8630,7 @@ export const MODELS = {
8590
8630
  },
8591
8631
  "minimax-m2.7": {
8592
8632
  id: "minimax-m2.7",
8593
- name: "MiniMax M2.7",
8633
+ name: "MiniMax-M2.7",
8594
8634
  api: "openai-completions",
8595
8635
  provider: "opencode",
8596
8636
  baseUrl: "https://opencode.ai/zen/v1",
@@ -8605,6 +8645,23 @@ export const MODELS = {
8605
8645
  contextWindow: 204800,
8606
8646
  maxTokens: 131072,
8607
8647
  },
8648
+ "minimax-m3": {
8649
+ id: "minimax-m3",
8650
+ name: "MiniMax-M3",
8651
+ api: "openai-completions",
8652
+ provider: "opencode",
8653
+ baseUrl: "https://opencode.ai/zen/v1",
8654
+ reasoning: true,
8655
+ input: ["text", "image"],
8656
+ cost: {
8657
+ input: 0.3,
8658
+ output: 1.2,
8659
+ cacheRead: 0.06,
8660
+ cacheWrite: 0,
8661
+ },
8662
+ contextWindow: 512000,
8663
+ maxTokens: 128000,
8664
+ },
8608
8665
  "nemotron-3-ultra-free": {
8609
8666
  id: "nemotron-3-ultra-free",
8610
8667
  name: "Nemotron 3 Ultra Free",
@@ -8817,7 +8874,7 @@ export const MODELS = {
8817
8874
  },
8818
8875
  "minimax-m2.7": {
8819
8876
  id: "minimax-m2.7",
8820
- name: "MiniMax M2.7",
8877
+ name: "MiniMax-M2.7",
8821
8878
  api: "openai-completions",
8822
8879
  provider: "opencode-go",
8823
8880
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -8834,7 +8891,7 @@ export const MODELS = {
8834
8891
  },
8835
8892
  "minimax-m3": {
8836
8893
  id: "minimax-m3",
8837
- name: "MiniMax M3 (3x usage)",
8894
+ name: "MiniMax-M3",
8838
8895
  api: "anthropic-messages",
8839
8896
  provider: "opencode-go",
8840
8897
  baseUrl: "https://opencode.ai/zen/go",
@@ -8920,6 +8977,57 @@ export const MODELS = {
8920
8977
  contextWindow: 256000,
8921
8978
  maxTokens: 4096,
8922
8979
  },
8980
+ "aion-labs/aion-2.0": {
8981
+ id: "aion-labs/aion-2.0",
8982
+ name: "AionLabs: Aion-2.0",
8983
+ api: "openai-completions",
8984
+ provider: "openrouter",
8985
+ baseUrl: "https://openrouter.ai/api/v1",
8986
+ reasoning: true,
8987
+ input: ["text"],
8988
+ cost: {
8989
+ input: 0.7999999999999999,
8990
+ output: 1.5999999999999999,
8991
+ cacheRead: 0.19999999999999998,
8992
+ cacheWrite: 0,
8993
+ },
8994
+ contextWindow: 131072,
8995
+ maxTokens: 32768,
8996
+ },
8997
+ "aion-labs/aion-3.0": {
8998
+ id: "aion-labs/aion-3.0",
8999
+ name: "AionLabs: Aion-3.0",
9000
+ api: "openai-completions",
9001
+ provider: "openrouter",
9002
+ baseUrl: "https://openrouter.ai/api/v1",
9003
+ reasoning: true,
9004
+ input: ["text"],
9005
+ cost: {
9006
+ input: 3,
9007
+ output: 6,
9008
+ cacheRead: 0.75,
9009
+ cacheWrite: 0,
9010
+ },
9011
+ contextWindow: 131072,
9012
+ maxTokens: 32768,
9013
+ },
9014
+ "aion-labs/aion-3.0-mini": {
9015
+ id: "aion-labs/aion-3.0-mini",
9016
+ name: "AionLabs: Aion-3.0-Mini",
9017
+ api: "openai-completions",
9018
+ provider: "openrouter",
9019
+ baseUrl: "https://openrouter.ai/api/v1",
9020
+ reasoning: true,
9021
+ input: ["text"],
9022
+ cost: {
9023
+ input: 0.7,
9024
+ output: 1.4,
9025
+ cacheRead: 0.18,
9026
+ cacheWrite: 0,
9027
+ },
9028
+ contextWindow: 131072,
9029
+ maxTokens: 32768,
9030
+ },
8923
9031
  "amazon/nova-2-lite-v1": {
8924
9032
  id: "amazon/nova-2-lite-v1",
8925
9033
  name: "Amazon: Nova 2 Lite",
@@ -9479,8 +9587,8 @@ export const MODELS = {
9479
9587
  reasoning: false,
9480
9588
  input: ["text"],
9481
9589
  cost: {
9482
- input: 0.19999999999999998,
9483
- output: 0.77,
9590
+ input: 0.24,
9591
+ output: 0.8999999999999999,
9484
9592
  cacheRead: 0.135,
9485
9593
  cacheWrite: 0,
9486
9594
  },
@@ -9600,13 +9708,13 @@ export const MODELS = {
9600
9708
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9601
9709
  input: ["text"],
9602
9710
  cost: {
9603
- input: 0.098,
9604
- output: 0.196,
9605
- cacheRead: 0.02,
9711
+ input: 0.09,
9712
+ output: 0.18,
9713
+ cacheRead: 0.018,
9606
9714
  cacheWrite: 0,
9607
9715
  },
9608
9716
  contextWindow: 1048576,
9609
- maxTokens: 4096,
9717
+ maxTokens: 65536,
9610
9718
  },
9611
9719
  "deepseek/deepseek-v4-pro": {
9612
9720
  id: "deepseek/deepseek-v4-pro",
@@ -10198,12 +10306,12 @@ export const MODELS = {
10198
10306
  input: ["text"],
10199
10307
  cost: {
10200
10308
  input: 0.255,
10201
- output: 1,
10202
- cacheRead: 0.03,
10309
+ output: 1.02,
10310
+ cacheRead: 0,
10203
10311
  cacheWrite: 0,
10204
10312
  },
10205
10313
  contextWindow: 204800,
10206
- maxTokens: 196608,
10314
+ maxTokens: 131072,
10207
10315
  },
10208
10316
  "minimax/minimax-m2.1": {
10209
10317
  id: "minimax/minimax-m2.1",
@@ -10214,13 +10322,13 @@ export const MODELS = {
10214
10322
  reasoning: true,
10215
10323
  input: ["text"],
10216
10324
  cost: {
10217
- input: 0.29,
10218
- output: 0.95,
10325
+ input: 0.3,
10326
+ output: 1.2,
10219
10327
  cacheRead: 0.03,
10220
10328
  cacheWrite: 0,
10221
10329
  },
10222
10330
  contextWindow: 204800,
10223
- maxTokens: 196608,
10331
+ maxTokens: 131072,
10224
10332
  },
10225
10333
  "minimax/minimax-m2.5": {
10226
10334
  id: "minimax/minimax-m2.5",
@@ -10607,11 +10715,11 @@ export const MODELS = {
10607
10715
  cost: {
10608
10716
  input: 0.6,
10609
10717
  output: 2.5,
10610
- cacheRead: 0.6,
10718
+ cacheRead: 0.15,
10611
10719
  cacheWrite: 0,
10612
10720
  },
10613
10721
  contextWindow: 262144,
10614
- maxTokens: 262144,
10722
+ maxTokens: 100352,
10615
10723
  },
10616
10724
  "moonshotai/kimi-k2.5": {
10617
10725
  id: "moonshotai/kimi-k2.5",
@@ -10639,9 +10747,9 @@ export const MODELS = {
10639
10747
  reasoning: true,
10640
10748
  input: ["text", "image"],
10641
10749
  cost: {
10642
- input: 0.55,
10643
- output: 3.1999999999999997,
10644
- cacheRead: 0.11,
10750
+ input: 0.65,
10751
+ output: 3.41,
10752
+ cacheRead: 0.3,
10645
10753
  cacheWrite: 0,
10646
10754
  },
10647
10755
  contextWindow: 262144,
@@ -10664,6 +10772,40 @@ export const MODELS = {
10664
10772
  contextWindow: 262144,
10665
10773
  maxTokens: 16384,
10666
10774
  },
10775
+ "nex-agi/nex-n2-mini": {
10776
+ id: "nex-agi/nex-n2-mini",
10777
+ name: "Nex AGI: Nex-N2-Mini",
10778
+ api: "openai-completions",
10779
+ provider: "openrouter",
10780
+ baseUrl: "https://openrouter.ai/api/v1",
10781
+ reasoning: true,
10782
+ input: ["text", "image"],
10783
+ cost: {
10784
+ input: 0.024999999999999998,
10785
+ output: 0.09999999999999999,
10786
+ cacheRead: 0.0025,
10787
+ cacheWrite: 0,
10788
+ },
10789
+ contextWindow: 262144,
10790
+ maxTokens: 262144,
10791
+ },
10792
+ "nex-agi/nex-n2-pro": {
10793
+ id: "nex-agi/nex-n2-pro",
10794
+ name: "Nex AGI: Nex-N2-Pro",
10795
+ api: "openai-completions",
10796
+ provider: "openrouter",
10797
+ baseUrl: "https://openrouter.ai/api/v1",
10798
+ reasoning: true,
10799
+ input: ["text", "image"],
10800
+ cost: {
10801
+ input: 0.25,
10802
+ output: 1,
10803
+ cacheRead: 0.024999999999999998,
10804
+ cacheWrite: 0,
10805
+ },
10806
+ contextWindow: 262144,
10807
+ maxTokens: 262144,
10808
+ },
10667
10809
  "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
10668
10810
  id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
10669
10811
  name: "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5",
@@ -10741,13 +10883,13 @@ export const MODELS = {
10741
10883
  reasoning: true,
10742
10884
  input: ["text"],
10743
10885
  cost: {
10744
- input: 0.08499999999999999,
10745
- output: 0.39999999999999997,
10886
+ input: 0.08,
10887
+ output: 0.44999999999999996,
10746
10888
  cacheRead: 0,
10747
10889
  cacheWrite: 0,
10748
10890
  },
10749
10891
  contextWindow: 1000000,
10750
- maxTokens: 16384,
10892
+ maxTokens: 4096,
10751
10893
  },
10752
10894
  "nvidia/nemotron-3-super-120b-a12b:free": {
10753
10895
  id: "nvidia/nemotron-3-super-120b-a12b:free",
@@ -11730,6 +11872,40 @@ export const MODELS = {
11730
11872
  contextWindow: 262144,
11731
11873
  maxTokens: 32768,
11732
11874
  },
11875
+ "poolside/laguna-xs-2.1": {
11876
+ id: "poolside/laguna-xs-2.1",
11877
+ name: "Poolside: Laguna XS 2.1",
11878
+ api: "openai-completions",
11879
+ provider: "openrouter",
11880
+ baseUrl: "https://openrouter.ai/api/v1",
11881
+ reasoning: true,
11882
+ input: ["text"],
11883
+ cost: {
11884
+ input: 0.06,
11885
+ output: 0.12,
11886
+ cacheRead: 0.03,
11887
+ cacheWrite: 0,
11888
+ },
11889
+ contextWindow: 262144,
11890
+ maxTokens: 32768,
11891
+ },
11892
+ "poolside/laguna-xs-2.1:free": {
11893
+ id: "poolside/laguna-xs-2.1:free",
11894
+ name: "Poolside: Laguna XS 2.1 (free)",
11895
+ api: "openai-completions",
11896
+ provider: "openrouter",
11897
+ baseUrl: "https://openrouter.ai/api/v1",
11898
+ reasoning: true,
11899
+ input: ["text"],
11900
+ cost: {
11901
+ input: 0,
11902
+ output: 0,
11903
+ cacheRead: 0,
11904
+ cacheWrite: 0,
11905
+ },
11906
+ contextWindow: 262144,
11907
+ maxTokens: 32768,
11908
+ },
11733
11909
  "poolside/laguna-xs.2": {
11734
11910
  id: "poolside/laguna-xs.2",
11735
11911
  name: "Poolside: Laguna XS.2",
@@ -11960,13 +12136,13 @@ export const MODELS = {
11960
12136
  reasoning: true,
11961
12137
  input: ["text"],
11962
12138
  cost: {
11963
- input: 0.08,
11964
- output: 0.39999999999999997,
11965
- cacheRead: 0.08,
12139
+ input: 0.13,
12140
+ output: 1.56,
12141
+ cacheRead: 0,
11966
12142
  cacheWrite: 0,
11967
12143
  },
11968
12144
  contextWindow: 131072,
11969
- maxTokens: 131072,
12145
+ maxTokens: 32768,
11970
12146
  },
11971
12147
  "qwen/qwen3-32b": {
11972
12148
  id: "qwen/qwen3-32b",
@@ -11994,9 +12170,9 @@ export const MODELS = {
11994
12170
  reasoning: true,
11995
12171
  input: ["text"],
11996
12172
  cost: {
11997
- input: 0.049999999999999996,
11998
- output: 0.39999999999999997,
11999
- cacheRead: 0.049999999999999996,
12173
+ input: 0.117,
12174
+ output: 0.45499999999999996,
12175
+ cacheRead: 0,
12000
12176
  cacheWrite: 0,
12001
12177
  },
12002
12178
  contextWindow: 131072,
@@ -12283,8 +12459,8 @@ export const MODELS = {
12283
12459
  reasoning: false,
12284
12460
  input: ["text", "image"],
12285
12461
  cost: {
12286
- input: 0.08,
12287
- output: 0.5,
12462
+ input: 0.117,
12463
+ output: 0.45499999999999996,
12288
12464
  cacheRead: 0,
12289
12465
  cacheWrite: 0,
12290
12466
  },
@@ -12370,7 +12546,7 @@ export const MODELS = {
12370
12546
  cost: {
12371
12547
  input: 0.385,
12372
12548
  output: 2.4499999999999997,
12373
- cacheRead: 0,
12549
+ cacheRead: 0.111,
12374
12550
  cacheWrite: 0,
12375
12551
  },
12376
12552
  contextWindow: 256000,
@@ -12455,7 +12631,7 @@ export const MODELS = {
12455
12631
  cost: {
12456
12632
  input: 0.28500000000000003,
12457
12633
  output: 2.4,
12458
- cacheRead: 0,
12634
+ cacheRead: 0.15,
12459
12635
  cacheWrite: 0,
12460
12636
  },
12461
12637
  contextWindow: 262144,
@@ -12665,6 +12841,40 @@ export const MODELS = {
12665
12841
  contextWindow: 256000,
12666
12842
  maxTokens: 256000,
12667
12843
  },
12844
+ "tencent/hy3": {
12845
+ id: "tencent/hy3",
12846
+ name: "Tencent: Hy3",
12847
+ api: "openai-completions",
12848
+ provider: "openrouter",
12849
+ baseUrl: "https://openrouter.ai/api/v1",
12850
+ reasoning: true,
12851
+ input: ["text"],
12852
+ cost: {
12853
+ input: 0.19999999999999998,
12854
+ output: 0.7999999999999999,
12855
+ cacheRead: 0.5,
12856
+ cacheWrite: 0,
12857
+ },
12858
+ contextWindow: 262144,
12859
+ maxTokens: 131072,
12860
+ },
12861
+ "tencent/hy3:free": {
12862
+ id: "tencent/hy3:free",
12863
+ name: "Tencent: Hy3 (free)",
12864
+ api: "openai-completions",
12865
+ provider: "openrouter",
12866
+ baseUrl: "https://openrouter.ai/api/v1",
12867
+ reasoning: true,
12868
+ input: ["text"],
12869
+ cost: {
12870
+ input: 0,
12871
+ output: 0,
12872
+ cacheRead: 0,
12873
+ cacheWrite: 0,
12874
+ },
12875
+ contextWindow: 262144,
12876
+ maxTokens: 262144,
12877
+ },
12668
12878
  "thedrummer/unslopnemo-12b": {
12669
12879
  id: "thedrummer/unslopnemo-12b",
12670
12880
  name: "TheDrummer: UnslopNemo 12B",
@@ -12761,7 +12971,7 @@ export const MODELS = {
12761
12971
  cost: {
12762
12972
  input: 0.105,
12763
12973
  output: 0.28,
12764
- cacheRead: 0,
12974
+ cacheRead: 0.028,
12765
12975
  cacheWrite: 0,
12766
12976
  },
12767
12977
  contextWindow: 1048576,
@@ -12946,13 +13156,13 @@ export const MODELS = {
12946
13156
  reasoning: true,
12947
13157
  input: ["text"],
12948
13158
  cost: {
12949
- input: 0.975,
12950
- output: 4.300000000000001,
12951
- cacheRead: 0,
13159
+ input: 0.966,
13160
+ output: 3.036,
13161
+ cacheRead: 0.1794,
12952
13162
  cacheWrite: 0,
12953
13163
  },
12954
13164
  contextWindow: 202752,
12955
- maxTokens: 4096,
13165
+ maxTokens: 128000,
12956
13166
  },
12957
13167
  "z-ai/glm-5.2": {
12958
13168
  id: "z-ai/glm-5.2",
@@ -12963,13 +13173,13 @@ export const MODELS = {
12963
13173
  reasoning: true,
12964
13174
  input: ["text"],
12965
13175
  cost: {
12966
- input: 0.9299999999999999,
12967
- output: 3,
12968
- cacheRead: 0.18,
13176
+ input: 0.56,
13177
+ output: 1.76,
13178
+ cacheRead: 0.10400000000000001,
12969
13179
  cacheWrite: 0,
12970
13180
  },
12971
13181
  contextWindow: 1048576,
12972
- maxTokens: 32768,
13182
+ maxTokens: 128000,
12973
13183
  },
12974
13184
  "z-ai/glm-5v-turbo": {
12975
13185
  id: "z-ai/glm-5v-turbo",
@@ -13100,9 +13310,9 @@ export const MODELS = {
13100
13310
  reasoning: true,
13101
13311
  input: ["text", "image"],
13102
13312
  cost: {
13103
- input: 0.55,
13104
- output: 3.1999999999999997,
13105
- cacheRead: 0.11,
13313
+ input: 0.65,
13314
+ output: 3.41,
13315
+ cacheRead: 0.3,
13106
13316
  cacheWrite: 0,
13107
13317
  },
13108
13318
  contextWindow: 262144,
@@ -13142,6 +13352,23 @@ export const MODELS = {
13142
13352
  contextWindow: 400000,
13143
13353
  maxTokens: 128000,
13144
13354
  },
13355
+ "~x-ai/grok-latest": {
13356
+ id: "~x-ai/grok-latest",
13357
+ name: "xAI: Grok Latest",
13358
+ api: "openai-completions",
13359
+ provider: "openrouter",
13360
+ baseUrl: "https://openrouter.ai/api/v1",
13361
+ reasoning: true,
13362
+ input: ["text", "image"],
13363
+ cost: {
13364
+ input: 1.25,
13365
+ output: 2.5,
13366
+ cacheRead: 0.19999999999999998,
13367
+ cacheWrite: 0,
13368
+ },
13369
+ contextWindow: 1000000,
13370
+ maxTokens: 4096,
13371
+ },
13145
13372
  },
13146
13373
  "together": {
13147
13374
  "MiniMaxAI/MiniMax-M2.7": {
@@ -13359,8 +13586,8 @@ export const MODELS = {
13359
13586
  reasoning: false,
13360
13587
  input: ["text"],
13361
13588
  cost: {
13362
- input: 0.88,
13363
- output: 0.88,
13589
+ input: 1.04,
13590
+ output: 1.04,
13364
13591
  cacheRead: 0,
13365
13592
  cacheWrite: 0,
13366
13593
  },
@@ -14014,6 +14241,24 @@ export const MODELS = {
14014
14241
  contextWindow: 200000,
14015
14242
  maxTokens: 4096,
14016
14243
  },
14244
+ "anthropic/claude-fable-5": {
14245
+ id: "anthropic/claude-fable-5",
14246
+ name: "Claude Fable 5",
14247
+ api: "anthropic-messages",
14248
+ provider: "vercel-ai-gateway",
14249
+ baseUrl: "https://ai-gateway.vercel.sh",
14250
+ reasoning: true,
14251
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
14252
+ input: ["text", "image"],
14253
+ cost: {
14254
+ input: 10,
14255
+ output: 50,
14256
+ cacheRead: 1,
14257
+ cacheWrite: 12.5,
14258
+ },
14259
+ contextWindow: 1000000,
14260
+ maxTokens: 128000,
14261
+ },
14017
14262
  "anthropic/claude-haiku-4.5": {
14018
14263
  id: "anthropic/claude-haiku-4.5",
14019
14264
  name: "Claude Haiku 4.5",
@@ -16588,12 +16833,12 @@ export const MODELS = {
16588
16833
  reasoning: true,
16589
16834
  input: ["text"],
16590
16835
  cost: {
16591
- input: 1.5,
16592
- output: 4.5,
16593
- cacheRead: 0.3,
16836
+ input: 1.4,
16837
+ output: 4.4,
16838
+ cacheRead: 0.26,
16594
16839
  cacheWrite: 0,
16595
16840
  },
16596
- contextWindow: 1000000,
16841
+ contextWindow: 1040000,
16597
16842
  maxTokens: 128000,
16598
16843
  },
16599
16844
  "zai/glm-5.2-fast": {