@elyracode/ai 0.8.4 → 0.9.0

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.
@@ -2826,6 +2826,24 @@ export const MODELS = {
2826
2826
  contextWindow: 1000000,
2827
2827
  maxTokens: 128000,
2828
2828
  },
2829
+ "claude-opus-4-8": {
2830
+ id: "claude-opus-4-8",
2831
+ name: "Claude Opus 4.8",
2832
+ api: "anthropic-messages",
2833
+ provider: "cloudflare-ai-gateway",
2834
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
2835
+ reasoning: true,
2836
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "max", "xhigh": "ultracode" },
2837
+ input: ["text", "image"],
2838
+ cost: {
2839
+ input: 5,
2840
+ output: 25,
2841
+ cacheRead: 0.5,
2842
+ cacheWrite: 6.25,
2843
+ },
2844
+ contextWindow: 1000000,
2845
+ maxTokens: 128000,
2846
+ },
2829
2847
  "claude-sonnet-4": {
2830
2848
  id: "claude-sonnet-4",
2831
2849
  name: "Claude Sonnet 4 (latest)",
@@ -3693,8 +3711,8 @@ export const MODELS = {
3693
3711
  cacheRead: 0,
3694
3712
  cacheWrite: 0,
3695
3713
  },
3696
- contextWindow: 144000,
3697
- maxTokens: 32000,
3714
+ contextWindow: 200000,
3715
+ maxTokens: 64000,
3698
3716
  },
3699
3717
  "claude-opus-4.5": {
3700
3718
  id: "claude-opus-4.5",
@@ -3711,7 +3729,7 @@ export const MODELS = {
3711
3729
  cacheRead: 0,
3712
3730
  cacheWrite: 0,
3713
3731
  },
3714
- contextWindow: 160000,
3732
+ contextWindow: 200000,
3715
3733
  maxTokens: 32000,
3716
3734
  },
3717
3735
  "claude-opus-4.6": {
@@ -3731,7 +3749,7 @@ export const MODELS = {
3731
3749
  cacheWrite: 0,
3732
3750
  },
3733
3751
  contextWindow: 1000000,
3734
- maxTokens: 64000,
3752
+ maxTokens: 32000,
3735
3753
  },
3736
3754
  "claude-opus-4.7": {
3737
3755
  id: "claude-opus-4.7",
@@ -3749,7 +3767,26 @@ export const MODELS = {
3749
3767
  cacheRead: 0,
3750
3768
  cacheWrite: 0,
3751
3769
  },
3752
- contextWindow: 144000,
3770
+ contextWindow: 200000,
3771
+ maxTokens: 32000,
3772
+ },
3773
+ "claude-opus-4.8": {
3774
+ id: "claude-opus-4.8",
3775
+ name: "Claude Opus 4.8",
3776
+ api: "anthropic-messages",
3777
+ provider: "github-copilot",
3778
+ baseUrl: "https://api.individual.githubcopilot.com",
3779
+ 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" },
3780
+ reasoning: true,
3781
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "max", "xhigh": "ultracode" },
3782
+ input: ["text", "image"],
3783
+ cost: {
3784
+ input: 0,
3785
+ output: 0,
3786
+ cacheRead: 0,
3787
+ cacheWrite: 0,
3788
+ },
3789
+ contextWindow: 200000,
3753
3790
  maxTokens: 64000,
3754
3791
  },
3755
3792
  "claude-sonnet-4.5": {
@@ -3768,7 +3805,7 @@ export const MODELS = {
3768
3805
  cacheRead: 0,
3769
3806
  cacheWrite: 0,
3770
3807
  },
3771
- contextWindow: 144000,
3808
+ contextWindow: 200000,
3772
3809
  maxTokens: 32000,
3773
3810
  },
3774
3811
  "claude-sonnet-4.6": {
@@ -3843,7 +3880,7 @@ export const MODELS = {
3843
3880
  cacheRead: 0,
3844
3881
  cacheWrite: 0,
3845
3882
  },
3846
- contextWindow: 128000,
3883
+ contextWindow: 200000,
3847
3884
  maxTokens: 64000,
3848
3885
  },
3849
3886
  "gemini-3.5-flash": {
@@ -3862,7 +3899,7 @@ export const MODELS = {
3862
3899
  cacheRead: 0,
3863
3900
  cacheWrite: 0,
3864
3901
  },
3865
- contextWindow: 128000,
3902
+ contextWindow: 200000,
3866
3903
  maxTokens: 64000,
3867
3904
  },
3868
3905
  "gpt-4.1": {
@@ -3938,8 +3975,8 @@ export const MODELS = {
3938
3975
  cacheRead: 0,
3939
3976
  cacheWrite: 0,
3940
3977
  },
3941
- contextWindow: 264000,
3942
- maxTokens: 64000,
3978
+ contextWindow: 400000,
3979
+ maxTokens: 128000,
3943
3980
  },
3944
3981
  "gpt-5.2-codex": {
3945
3982
  id: "gpt-5.2-codex",
@@ -7849,24 +7886,6 @@ export const MODELS = {
7849
7886
  contextWindow: 204800,
7850
7887
  maxTokens: 131072,
7851
7888
  },
7852
- "qwen3.5-plus": {
7853
- id: "qwen3.5-plus",
7854
- name: "Qwen3.5 Plus",
7855
- api: "openai-completions",
7856
- provider: "opencode-go",
7857
- baseUrl: "https://opencode.ai/zen/go/v1",
7858
- compat: { "thinkingFormat": "qwen" },
7859
- reasoning: true,
7860
- input: ["text", "image"],
7861
- cost: {
7862
- input: 0.2,
7863
- output: 1.2,
7864
- cacheRead: 0.02,
7865
- cacheWrite: 0.25,
7866
- },
7867
- contextWindow: 262144,
7868
- maxTokens: 65536,
7869
- },
7870
7889
  "qwen3.6-plus": {
7871
7890
  id: "qwen3.6-plus",
7872
7891
  name: "Qwen3.6 Plus",
@@ -8318,23 +8337,6 @@ export const MODELS = {
8318
8337
  contextWindow: 2000000,
8319
8338
  maxTokens: 30000,
8320
8339
  },
8321
- "baidu/ernie-4.5-21b-a3b": {
8322
- id: "baidu/ernie-4.5-21b-a3b",
8323
- name: "Baidu: ERNIE 4.5 21B A3B",
8324
- api: "openai-completions",
8325
- provider: "openrouter",
8326
- baseUrl: "https://openrouter.ai/api/v1",
8327
- reasoning: false,
8328
- input: ["text"],
8329
- cost: {
8330
- input: 0.07,
8331
- output: 0.28,
8332
- cacheRead: 0,
8333
- cacheWrite: 0,
8334
- },
8335
- contextWindow: 131072,
8336
- maxTokens: 8000,
8337
- },
8338
8340
  "baidu/ernie-4.5-vl-28b-a3b": {
8339
8341
  id: "baidu/ernie-4.5-vl-28b-a3b",
8340
8342
  name: "Baidu: ERNIE 4.5 VL 28B A3B",
@@ -8601,13 +8603,13 @@ export const MODELS = {
8601
8603
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
8602
8604
  input: ["text"],
8603
8605
  cost: {
8604
- input: 0.09999999999999999,
8605
- output: 0.19999999999999998,
8606
- cacheRead: 0.02,
8606
+ input: 0.0983,
8607
+ output: 0.1966,
8608
+ cacheRead: 0.019700000000000002,
8607
8609
  cacheWrite: 0,
8608
8610
  },
8609
8611
  contextWindow: 1048576,
8610
- maxTokens: 16384,
8612
+ maxTokens: 131072,
8611
8613
  },
8612
8614
  "deepseek/deepseek-v4-flash:free": {
8613
8615
  id: "deepseek/deepseek-v4-flash:free",
@@ -8678,7 +8680,7 @@ export const MODELS = {
8678
8680
  cacheRead: 0.024999999999999998,
8679
8681
  cacheWrite: 0.08333333333333334,
8680
8682
  },
8681
- contextWindow: 1000000,
8683
+ contextWindow: 1048576,
8682
8684
  maxTokens: 8192,
8683
8685
  },
8684
8686
  "google/gemini-2.0-flash-lite-001": {
@@ -9174,6 +9176,23 @@ export const MODELS = {
9174
9176
  contextWindow: 131072,
9175
9177
  maxTokens: 4096,
9176
9178
  },
9179
+ "meta-llama/llama-4-maverick": {
9180
+ id: "meta-llama/llama-4-maverick",
9181
+ name: "Meta: Llama 4 Maverick",
9182
+ api: "openai-completions",
9183
+ provider: "openrouter",
9184
+ baseUrl: "https://openrouter.ai/api/v1",
9185
+ reasoning: false,
9186
+ input: ["text", "image"],
9187
+ cost: {
9188
+ input: 0.15,
9189
+ output: 0.6,
9190
+ cacheRead: 0,
9191
+ cacheWrite: 0,
9192
+ },
9193
+ contextWindow: 1048576,
9194
+ maxTokens: 16384,
9195
+ },
9177
9196
  "meta-llama/llama-4-scout": {
9178
9197
  id: "meta-llama/llama-4-scout",
9179
9198
  name: "Meta: Llama 4 Scout",
@@ -9259,23 +9278,6 @@ export const MODELS = {
9259
9278
  contextWindow: 204800,
9260
9279
  maxTokens: 196608,
9261
9280
  },
9262
- "minimax/minimax-m2.5:free": {
9263
- id: "minimax/minimax-m2.5:free",
9264
- name: "MiniMax: MiniMax M2.5 (free)",
9265
- api: "openai-completions",
9266
- provider: "openrouter",
9267
- baseUrl: "https://openrouter.ai/api/v1",
9268
- reasoning: true,
9269
- input: ["text"],
9270
- cost: {
9271
- input: 0,
9272
- output: 0,
9273
- cacheRead: 0,
9274
- cacheWrite: 0,
9275
- },
9276
- contextWindow: 262144,
9277
- maxTokens: 8192,
9278
- },
9279
9281
  "minimax/minimax-m2.7": {
9280
9282
  id: "minimax/minimax-m2.7",
9281
9283
  name: "MiniMax: MiniMax M2.7",
@@ -9285,13 +9287,13 @@ export const MODELS = {
9285
9287
  reasoning: true,
9286
9288
  input: ["text"],
9287
9289
  cost: {
9288
- input: 0.27899999999999997,
9290
+ input: 0.26,
9289
9291
  output: 1.2,
9290
9292
  cacheRead: 0,
9291
9293
  cacheWrite: 0,
9292
9294
  },
9293
9295
  contextWindow: 204800,
9294
- maxTokens: 131072,
9296
+ maxTokens: 4096,
9295
9297
  },
9296
9298
  "mistralai/codestral-2508": {
9297
9299
  id: "mistralai/codestral-2508",
@@ -9327,40 +9329,6 @@ export const MODELS = {
9327
9329
  contextWindow: 262144,
9328
9330
  maxTokens: 4096,
9329
9331
  },
9330
- "mistralai/devstral-medium": {
9331
- id: "mistralai/devstral-medium",
9332
- name: "Mistral: Devstral Medium",
9333
- api: "openai-completions",
9334
- provider: "openrouter",
9335
- baseUrl: "https://openrouter.ai/api/v1",
9336
- reasoning: false,
9337
- input: ["text"],
9338
- cost: {
9339
- input: 0.39999999999999997,
9340
- output: 2,
9341
- cacheRead: 0.04,
9342
- cacheWrite: 0,
9343
- },
9344
- contextWindow: 131072,
9345
- maxTokens: 4096,
9346
- },
9347
- "mistralai/devstral-small": {
9348
- id: "mistralai/devstral-small",
9349
- name: "Mistral: Devstral Small 1.1",
9350
- api: "openai-completions",
9351
- provider: "openrouter",
9352
- baseUrl: "https://openrouter.ai/api/v1",
9353
- reasoning: false,
9354
- input: ["text"],
9355
- cost: {
9356
- input: 0.09999999999999999,
9357
- output: 0.3,
9358
- cacheRead: 0.01,
9359
- cacheWrite: 0,
9360
- },
9361
- contextWindow: 131072,
9362
- maxTokens: 4096,
9363
- },
9364
9332
  "mistralai/ministral-14b-2512": {
9365
9333
  id: "mistralai/ministral-14b-2512",
9366
9334
  name: "Mistral: Ministral 3 14B 2512",
@@ -9446,23 +9414,6 @@ export const MODELS = {
9446
9414
  contextWindow: 131072,
9447
9415
  maxTokens: 4096,
9448
9416
  },
9449
- "mistralai/mistral-large-2411": {
9450
- id: "mistralai/mistral-large-2411",
9451
- name: "Mistral Large 2411",
9452
- api: "openai-completions",
9453
- provider: "openrouter",
9454
- baseUrl: "https://openrouter.ai/api/v1",
9455
- reasoning: false,
9456
- input: ["text"],
9457
- cost: {
9458
- input: 2,
9459
- output: 6,
9460
- cacheRead: 0.19999999999999998,
9461
- cacheWrite: 0,
9462
- },
9463
- contextWindow: 131072,
9464
- maxTokens: 4096,
9465
- },
9466
9417
  "mistralai/mistral-large-2512": {
9467
9418
  id: "mistralai/mistral-large-2512",
9468
9419
  name: "Mistral: Mistral Large 3 2512",
@@ -9616,23 +9567,6 @@ export const MODELS = {
9616
9567
  contextWindow: 65536,
9617
9568
  maxTokens: 4096,
9618
9569
  },
9619
- "mistralai/pixtral-large-2411": {
9620
- id: "mistralai/pixtral-large-2411",
9621
- name: "Mistral: Pixtral Large 2411",
9622
- api: "openai-completions",
9623
- provider: "openrouter",
9624
- baseUrl: "https://openrouter.ai/api/v1",
9625
- reasoning: false,
9626
- input: ["text", "image"],
9627
- cost: {
9628
- input: 2,
9629
- output: 6,
9630
- cacheRead: 0.19999999999999998,
9631
- cacheWrite: 0,
9632
- },
9633
- contextWindow: 131072,
9634
- maxTokens: 4096,
9635
- },
9636
9570
  "mistralai/voxtral-small-24b-2507": {
9637
9571
  id: "mistralai/voxtral-small-24b-2507",
9638
9572
  name: "Mistral: Voxtral Small 24B 2507",
@@ -9727,13 +9661,13 @@ export const MODELS = {
9727
9661
  reasoning: true,
9728
9662
  input: ["text", "image"],
9729
9663
  cost: {
9730
- input: 0.73,
9731
- output: 3.49,
9732
- cacheRead: 0.25,
9664
+ input: 0.684,
9665
+ output: 3.42,
9666
+ cacheRead: 0.144,
9733
9667
  cacheWrite: 0,
9734
9668
  },
9735
9669
  contextWindow: 262144,
9736
- maxTokens: 262142,
9670
+ maxTokens: 262144,
9737
9671
  },
9738
9672
  "moonshotai/kimi-k2.6:free": {
9739
9673
  id: "moonshotai/kimi-k2.6:free",
@@ -10092,23 +10026,6 @@ export const MODELS = {
10092
10026
  contextWindow: 128000,
10093
10027
  maxTokens: 16384,
10094
10028
  },
10095
- "openai/gpt-4o-audio-preview": {
10096
- id: "openai/gpt-4o-audio-preview",
10097
- name: "OpenAI: GPT-4o Audio",
10098
- api: "openai-completions",
10099
- provider: "openrouter",
10100
- baseUrl: "https://openrouter.ai/api/v1",
10101
- reasoning: false,
10102
- input: ["text"],
10103
- cost: {
10104
- input: 2.5,
10105
- output: 10,
10106
- cacheRead: 0,
10107
- cacheWrite: 0,
10108
- },
10109
- contextWindow: 128000,
10110
- maxTokens: 16384,
10111
- },
10112
10029
  "openai/gpt-4o-mini": {
10113
10030
  id: "openai/gpt-4o-mini",
10114
10031
  name: "OpenAI: GPT-4o-mini",
@@ -10606,13 +10523,13 @@ export const MODELS = {
10606
10523
  reasoning: true,
10607
10524
  input: ["text"],
10608
10525
  cost: {
10609
- input: 0.03,
10526
+ input: 0.029,
10610
10527
  output: 0.14,
10611
10528
  cacheRead: 0,
10612
10529
  cacheWrite: 0,
10613
10530
  },
10614
10531
  contextWindow: 131072,
10615
- maxTokens: 131072,
10532
+ maxTokens: 4096,
10616
10533
  },
10617
10534
  "openai/gpt-oss-20b:free": {
10618
10535
  id: "openai/gpt-oss-20b:free",
@@ -10920,23 +10837,6 @@ export const MODELS = {
10920
10837
  contextWindow: 131072,
10921
10838
  maxTokens: 16384,
10922
10839
  },
10923
- "qwen/qwen-2.5-7b-instruct": {
10924
- id: "qwen/qwen-2.5-7b-instruct",
10925
- name: "Qwen: Qwen2.5 7B Instruct",
10926
- api: "openai-completions",
10927
- provider: "openrouter",
10928
- baseUrl: "https://openrouter.ai/api/v1",
10929
- reasoning: false,
10930
- input: ["text"],
10931
- cost: {
10932
- input: 0.04,
10933
- output: 0.09999999999999999,
10934
- cacheRead: 0,
10935
- cacheWrite: 0,
10936
- },
10937
- contextWindow: 131072,
10938
- maxTokens: 32768,
10939
- },
10940
10840
  "qwen/qwen-plus": {
10941
10841
  id: "qwen/qwen-plus",
10942
10842
  name: "Qwen: Qwen-Plus",
@@ -11048,13 +10948,13 @@ export const MODELS = {
11048
10948
  reasoning: true,
11049
10949
  input: ["text"],
11050
10950
  cost: {
11051
- input: 0.14950000000000002,
11052
- output: 1.495,
11053
- cacheRead: 0,
10951
+ input: 0.09999999999999999,
10952
+ output: 0.09999999999999999,
10953
+ cacheRead: 0.09999999999999999,
11054
10954
  cacheWrite: 0,
11055
10955
  },
11056
10956
  contextWindow: 262144,
11057
- maxTokens: 4096,
10957
+ maxTokens: 262144,
11058
10958
  },
11059
10959
  "qwen/qwen3-30b-a3b": {
11060
10960
  id: "qwen/qwen3-30b-a3b",
@@ -11490,13 +11390,13 @@ export const MODELS = {
11490
11390
  reasoning: true,
11491
11391
  input: ["text", "image"],
11492
11392
  cost: {
11493
- input: 0.13899999999999998,
11393
+ input: 0.14,
11494
11394
  output: 1,
11495
- cacheRead: 0,
11395
+ cacheRead: 0.049999999999999996,
11496
11396
  cacheWrite: 0,
11497
11397
  },
11498
11398
  contextWindow: 262144,
11499
- maxTokens: 4096,
11399
+ maxTokens: 262144,
11500
11400
  },
11501
11401
  "qwen/qwen3.5-397b-a17b": {
11502
11402
  id: "qwen/qwen3.5-397b-a17b",
@@ -11770,6 +11670,23 @@ export const MODELS = {
11770
11670
  contextWindow: 262144,
11771
11671
  maxTokens: 16384,
11772
11672
  },
11673
+ "stepfun/step-3.7-flash": {
11674
+ id: "stepfun/step-3.7-flash",
11675
+ name: "StepFun: Step 3.7 Flash",
11676
+ api: "openai-completions",
11677
+ provider: "openrouter",
11678
+ baseUrl: "https://openrouter.ai/api/v1",
11679
+ reasoning: true,
11680
+ input: ["text", "image"],
11681
+ cost: {
11682
+ input: 0.19999999999999998,
11683
+ output: 1.15,
11684
+ cacheRead: 0.04,
11685
+ cacheWrite: 0,
11686
+ },
11687
+ contextWindow: 256000,
11688
+ maxTokens: 256000,
11689
+ },
11773
11690
  "thedrummer/rocinante-12b": {
11774
11691
  id: "thedrummer/rocinante-12b",
11775
11692
  name: "TheDrummer: Rocinante 12B",
@@ -11804,23 +11721,6 @@ export const MODELS = {
11804
11721
  contextWindow: 32768,
11805
11722
  maxTokens: 32768,
11806
11723
  },
11807
- "upstage/solar-pro-3": {
11808
- id: "upstage/solar-pro-3",
11809
- name: "Upstage: Solar Pro 3",
11810
- api: "openai-completions",
11811
- provider: "openrouter",
11812
- baseUrl: "https://openrouter.ai/api/v1",
11813
- reasoning: true,
11814
- input: ["text"],
11815
- cost: {
11816
- input: 0.15,
11817
- output: 0.6,
11818
- cacheRead: 0.015,
11819
- cacheWrite: 0,
11820
- },
11821
- contextWindow: 128000,
11822
- maxTokens: 4096,
11823
- },
11824
11724
  "x-ai/grok-4.20": {
11825
11725
  id: "x-ai/grok-4.20",
11826
11726
  name: "xAI: Grok 4.20",
@@ -12221,13 +12121,13 @@ export const MODELS = {
12221
12121
  reasoning: true,
12222
12122
  input: ["text", "image"],
12223
12123
  cost: {
12224
- input: 0.73,
12225
- output: 3.49,
12226
- cacheRead: 0.25,
12124
+ input: 0.684,
12125
+ output: 3.42,
12126
+ cacheRead: 0.144,
12227
12127
  cacheWrite: 0,
12228
12128
  },
12229
12129
  contextWindow: 262144,
12230
- maxTokens: 262142,
12130
+ maxTokens: 262144,
12231
12131
  },
12232
12132
  "~openai/gpt-latest": {
12233
12133
  id: "~openai/gpt-latest",
@@ -12625,20 +12525,20 @@ export const MODELS = {
12625
12525
  },
12626
12526
  "alibaba/qwen-3-235b": {
12627
12527
  id: "alibaba/qwen-3-235b",
12628
- name: "Qwen3 235B A22b Instruct 2507",
12528
+ name: "Qwen3 235B A22B",
12629
12529
  api: "anthropic-messages",
12630
12530
  provider: "vercel-ai-gateway",
12631
12531
  baseUrl: "https://ai-gateway.vercel.sh",
12632
12532
  reasoning: false,
12633
12533
  input: ["text"],
12634
12534
  cost: {
12635
- input: 0.6,
12636
- output: 1.2,
12637
- cacheRead: 0.6,
12535
+ input: 0.22,
12536
+ output: 0.88,
12537
+ cacheRead: 0,
12638
12538
  cacheWrite: 0,
12639
12539
  },
12640
- contextWindow: 131000,
12641
- maxTokens: 40000,
12540
+ contextWindow: 262144,
12541
+ maxTokens: 16384,
12642
12542
  },
12643
12543
  "alibaba/qwen-3-30b": {
12644
12544
  id: "alibaba/qwen-3-30b",
@@ -14831,6 +14731,23 @@ export const MODELS = {
14831
14731
  contextWindow: 200000,
14832
14732
  maxTokens: 8000,
14833
14733
  },
14734
+ "stepfun/step-3.7-flash": {
14735
+ id: "stepfun/step-3.7-flash",
14736
+ name: "Step 3.7 Flash",
14737
+ api: "anthropic-messages",
14738
+ provider: "vercel-ai-gateway",
14739
+ baseUrl: "https://ai-gateway.vercel.sh",
14740
+ reasoning: true,
14741
+ input: ["text", "image"],
14742
+ cost: {
14743
+ input: 0.19999999999999998,
14744
+ output: 1.15,
14745
+ cacheRead: 0.04,
14746
+ cacheWrite: 0,
14747
+ },
14748
+ contextWindow: 256000,
14749
+ maxTokens: 256000,
14750
+ },
14834
14751
  "xai/grok-4.1-fast-non-reasoning": {
14835
14752
  id: "xai/grok-4.1-fast-non-reasoning",
14836
14753
  name: "Grok 4.1 Fast Non-Reasoning",