@mariozechner/pi-ai 0.9.1 → 0.9.3

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.
@@ -104,6 +104,23 @@ export const MODELS = {
104
104
  contextWindow: 200000,
105
105
  maxTokens: 8192,
106
106
  },
107
+ "claude-opus-4-5": {
108
+ id: "claude-opus-4-5",
109
+ name: "Claude Opus 4.5",
110
+ api: "anthropic-messages",
111
+ provider: "anthropic",
112
+ baseUrl: "https://api.anthropic.com",
113
+ reasoning: true,
114
+ input: ["text", "image"],
115
+ cost: {
116
+ input: 5,
117
+ output: 25,
118
+ cacheRead: 1.5,
119
+ cacheWrite: 18.75,
120
+ },
121
+ contextWindow: 200000,
122
+ maxTokens: 64000,
123
+ },
107
124
  "claude-3-opus-20240229": {
108
125
  id: "claude-3-opus-20240229",
109
126
  name: "Claude Opus 3",
@@ -1455,23 +1472,6 @@ export const MODELS = {
1455
1472
  contextWindow: 131072,
1456
1473
  maxTokens: 40960,
1457
1474
  },
1458
- "qwen-3-coder-480b": {
1459
- id: "qwen-3-coder-480b",
1460
- name: "Qwen 3 Coder 480B",
1461
- api: "openai-completions",
1462
- provider: "cerebras",
1463
- baseUrl: "https://api.cerebras.ai/v1",
1464
- reasoning: false,
1465
- input: ["text"],
1466
- cost: {
1467
- input: 2,
1468
- output: 2,
1469
- cacheRead: 0,
1470
- cacheWrite: 0,
1471
- },
1472
- contextWindow: 131000,
1473
- maxTokens: 32000,
1474
- },
1475
1475
  "gpt-oss-120b": {
1476
1476
  id: "gpt-oss-120b",
1477
1477
  name: "GPT OSS 120B",
@@ -1954,6 +1954,40 @@ export const MODELS = {
1954
1954
  },
1955
1955
  },
1956
1956
  openrouter: {
1957
+ "anthropic/claude-opus-4.5": {
1958
+ id: "anthropic/claude-opus-4.5",
1959
+ name: "Anthropic: Claude Opus 4.5",
1960
+ api: "openai-completions",
1961
+ provider: "openrouter",
1962
+ baseUrl: "https://openrouter.ai/api/v1",
1963
+ reasoning: true,
1964
+ input: ["text", "image"],
1965
+ cost: {
1966
+ input: 5,
1967
+ output: 25,
1968
+ cacheRead: 0.5,
1969
+ cacheWrite: 6.25,
1970
+ },
1971
+ contextWindow: 200000,
1972
+ maxTokens: 32000,
1973
+ },
1974
+ "allenai/olmo-3-7b-instruct": {
1975
+ id: "allenai/olmo-3-7b-instruct",
1976
+ name: "AllenAI: Olmo 3 7B Instruct",
1977
+ api: "openai-completions",
1978
+ provider: "openrouter",
1979
+ baseUrl: "https://openrouter.ai/api/v1",
1980
+ reasoning: false,
1981
+ input: ["text"],
1982
+ cost: {
1983
+ input: 0.09999999999999999,
1984
+ output: 0.19999999999999998,
1985
+ cacheRead: 0,
1986
+ cacheWrite: 0,
1987
+ },
1988
+ contextWindow: 65536,
1989
+ maxTokens: 65536,
1990
+ },
1957
1991
  "x-ai/grok-4.1-fast": {
1958
1992
  id: "x-ai/grok-4.1-fast",
1959
1993
  name: "xAI: Grok 4.1 Fast",
@@ -2184,8 +2218,8 @@ export const MODELS = {
2184
2218
  reasoning: true,
2185
2219
  input: ["text"],
2186
2220
  cost: {
2187
- input: 0.255,
2188
- output: 1.02,
2221
+ input: 0.24,
2222
+ output: 0.96,
2189
2223
  cacheRead: 0,
2190
2224
  cacheWrite: 0,
2191
2225
  },
@@ -2269,8 +2303,8 @@ export const MODELS = {
2269
2303
  reasoning: false,
2270
2304
  input: ["text", "image"],
2271
2305
  cost: {
2272
- input: 0.08,
2273
- output: 0.5,
2306
+ input: 0.064,
2307
+ output: 0.39999999999999997,
2274
2308
  cacheRead: 0,
2275
2309
  cacheWrite: 0,
2276
2310
  },
@@ -2354,8 +2388,8 @@ export const MODELS = {
2354
2388
  reasoning: true,
2355
2389
  input: ["text", "image"],
2356
2390
  cost: {
2357
- input: 0.19999999999999998,
2358
- output: 1,
2391
+ input: 0.16,
2392
+ output: 0.7999999999999999,
2359
2393
  cacheRead: 0,
2360
2394
  cacheWrite: 0,
2361
2395
  },
@@ -2456,13 +2490,13 @@ export const MODELS = {
2456
2490
  reasoning: true,
2457
2491
  input: ["text"],
2458
2492
  cost: {
2459
- input: 0.27,
2460
- output: 0.39999999999999997,
2493
+ input: 0.216,
2494
+ output: 0.328,
2461
2495
  cacheRead: 0,
2462
2496
  cacheWrite: 0,
2463
2497
  },
2464
2498
  contextWindow: 163840,
2465
- maxTokens: 4096,
2499
+ maxTokens: 65536,
2466
2500
  },
2467
2501
  "google/gemini-2.5-flash-preview-09-2025": {
2468
2502
  id: "google/gemini-2.5-flash-preview-09-2025",
@@ -2583,34 +2617,34 @@ export const MODELS = {
2583
2617
  contextWindow: 400000,
2584
2618
  maxTokens: 128000,
2585
2619
  },
2586
- "deepseek/deepseek-v3.1-terminus": {
2587
- id: "deepseek/deepseek-v3.1-terminus",
2588
- name: "DeepSeek: DeepSeek V3.1 Terminus",
2620
+ "deepseek/deepseek-v3.1-terminus:exacto": {
2621
+ id: "deepseek/deepseek-v3.1-terminus:exacto",
2622
+ name: "DeepSeek: DeepSeek V3.1 Terminus (exacto)",
2589
2623
  api: "openai-completions",
2590
2624
  provider: "openrouter",
2591
2625
  baseUrl: "https://openrouter.ai/api/v1",
2592
2626
  reasoning: true,
2593
2627
  input: ["text"],
2594
2628
  cost: {
2595
- input: 0.22999999999999998,
2596
- output: 0.8999999999999999,
2629
+ input: 0.216,
2630
+ output: 0.7999999999999999,
2597
2631
  cacheRead: 0,
2598
2632
  cacheWrite: 0,
2599
2633
  },
2600
- contextWindow: 163840,
2601
- maxTokens: 163840,
2634
+ contextWindow: 131072,
2635
+ maxTokens: 65536,
2602
2636
  },
2603
- "deepseek/deepseek-v3.1-terminus:exacto": {
2604
- id: "deepseek/deepseek-v3.1-terminus:exacto",
2605
- name: "DeepSeek: DeepSeek V3.1 Terminus (exacto)",
2637
+ "deepseek/deepseek-v3.1-terminus": {
2638
+ id: "deepseek/deepseek-v3.1-terminus",
2639
+ name: "DeepSeek: DeepSeek V3.1 Terminus",
2606
2640
  api: "openai-completions",
2607
2641
  provider: "openrouter",
2608
2642
  baseUrl: "https://openrouter.ai/api/v1",
2609
2643
  reasoning: true,
2610
2644
  input: ["text"],
2611
2645
  cost: {
2612
- input: 0.27,
2613
- output: 1,
2646
+ input: 0.216,
2647
+ output: 0.7999999999999999,
2614
2648
  cacheRead: 0,
2615
2649
  cacheWrite: 0,
2616
2650
  },
@@ -2694,13 +2728,13 @@ export const MODELS = {
2694
2728
  reasoning: true,
2695
2729
  input: ["text"],
2696
2730
  cost: {
2697
- input: 0.15,
2731
+ input: 0.12,
2698
2732
  output: 1.2,
2699
2733
  cacheRead: 0,
2700
2734
  cacheWrite: 0,
2701
2735
  },
2702
- contextWindow: 262144,
2703
- maxTokens: 262144,
2736
+ contextWindow: 131072,
2737
+ maxTokens: 32768,
2704
2738
  },
2705
2739
  "qwen/qwen3-next-80b-a3b-instruct": {
2706
2740
  id: "qwen/qwen3-next-80b-a3b-instruct",
@@ -3017,8 +3051,8 @@ export const MODELS = {
3017
3051
  reasoning: false,
3018
3052
  input: ["text"],
3019
3053
  cost: {
3020
- input: 0.07,
3021
- output: 0.28,
3054
+ input: 0.056,
3055
+ output: 0.224,
3022
3056
  cacheRead: 0,
3023
3057
  cacheWrite: 0,
3024
3058
  },
@@ -3034,8 +3068,8 @@ export const MODELS = {
3034
3068
  reasoning: true,
3035
3069
  input: ["text", "image"],
3036
3070
  cost: {
3037
- input: 0.14,
3038
- output: 0.56,
3071
+ input: 0.112,
3072
+ output: 0.448,
3039
3073
  cacheRead: 0,
3040
3074
  cacheWrite: 0,
3041
3075
  },
@@ -3051,8 +3085,8 @@ export const MODELS = {
3051
3085
  reasoning: true,
3052
3086
  input: ["text", "image"],
3053
3087
  cost: {
3054
- input: 0.6,
3055
- output: 1.7999999999999998,
3088
+ input: 0.48,
3089
+ output: 1.44,
3056
3090
  cacheRead: 0.11,
3057
3091
  cacheWrite: 0,
3058
3092
  },
@@ -3144,9 +3178,9 @@ export const MODELS = {
3144
3178
  contextWindow: 400000,
3145
3179
  maxTokens: 128000,
3146
3180
  },
3147
- "openai/gpt-oss-120b": {
3148
- id: "openai/gpt-oss-120b",
3149
- name: "OpenAI: gpt-oss-120b",
3181
+ "openai/gpt-oss-120b:exacto": {
3182
+ id: "openai/gpt-oss-120b:exacto",
3183
+ name: "OpenAI: gpt-oss-120b (exacto)",
3150
3184
  api: "openai-completions",
3151
3185
  provider: "openrouter",
3152
3186
  baseUrl: "https://openrouter.ai/api/v1",
@@ -3154,29 +3188,29 @@ export const MODELS = {
3154
3188
  input: ["text"],
3155
3189
  cost: {
3156
3190
  input: 0.04,
3157
- output: 0.39999999999999997,
3191
+ output: 0.19999999999999998,
3158
3192
  cacheRead: 0,
3159
3193
  cacheWrite: 0,
3160
3194
  },
3161
3195
  contextWindow: 131072,
3162
- maxTokens: 131072,
3196
+ maxTokens: 32768,
3163
3197
  },
3164
- "openai/gpt-oss-120b:exacto": {
3165
- id: "openai/gpt-oss-120b:exacto",
3166
- name: "OpenAI: gpt-oss-120b (exacto)",
3198
+ "openai/gpt-oss-120b": {
3199
+ id: "openai/gpt-oss-120b",
3200
+ name: "OpenAI: gpt-oss-120b",
3167
3201
  api: "openai-completions",
3168
3202
  provider: "openrouter",
3169
3203
  baseUrl: "https://openrouter.ai/api/v1",
3170
3204
  reasoning: true,
3171
3205
  input: ["text"],
3172
3206
  cost: {
3173
- input: 0.049999999999999996,
3174
- output: 0.24,
3207
+ input: 0.04,
3208
+ output: 0.19999999999999998,
3175
3209
  cacheRead: 0,
3176
3210
  cacheWrite: 0,
3177
3211
  },
3178
3212
  contextWindow: 131072,
3179
- maxTokens: 4096,
3213
+ maxTokens: 32768,
3180
3214
  },
3181
3215
  "openai/gpt-oss-20b:free": {
3182
3216
  id: "openai/gpt-oss-20b:free",
@@ -3323,8 +3357,8 @@ export const MODELS = {
3323
3357
  reasoning: true,
3324
3358
  input: ["text"],
3325
3359
  cost: {
3326
- input: 0.13,
3327
- output: 0.85,
3360
+ input: 0.10400000000000001,
3361
+ output: 0.6799999999999999,
3328
3362
  cacheRead: 0,
3329
3363
  cacheWrite: 0,
3330
3364
  },
@@ -3408,13 +3442,13 @@ export const MODELS = {
3408
3442
  reasoning: true,
3409
3443
  input: ["text"],
3410
3444
  cost: {
3411
- input: 0.38,
3412
- output: 1.53,
3445
+ input: 1,
3446
+ output: 4,
3413
3447
  cacheRead: 0,
3414
3448
  cacheWrite: 0,
3415
3449
  },
3416
3450
  contextWindow: 262144,
3417
- maxTokens: 262144,
3451
+ maxTokens: 32768,
3418
3452
  },
3419
3453
  "google/gemini-2.5-flash-lite": {
3420
3454
  id: "google/gemini-2.5-flash-lite",
@@ -3442,13 +3476,13 @@ export const MODELS = {
3442
3476
  reasoning: true,
3443
3477
  input: ["text"],
3444
3478
  cost: {
3445
- input: 0.08,
3446
- output: 0.55,
3479
+ input: 0.072,
3480
+ output: 0.464,
3447
3481
  cacheRead: 0,
3448
3482
  cacheWrite: 0,
3449
3483
  },
3450
- contextWindow: 262144,
3451
- maxTokens: 262144,
3484
+ contextWindow: 131072,
3485
+ maxTokens: 16384,
3452
3486
  },
3453
3487
  "moonshotai/kimi-k2": {
3454
3488
  id: "moonshotai/kimi-k2",
@@ -3459,13 +3493,13 @@ export const MODELS = {
3459
3493
  reasoning: false,
3460
3494
  input: ["text"],
3461
3495
  cost: {
3462
- input: 0.5,
3463
- output: 2.4,
3496
+ input: 0.456,
3497
+ output: 1.8399999999999999,
3464
3498
  cacheRead: 0,
3465
3499
  cacheWrite: 0,
3466
3500
  },
3467
3501
  contextWindow: 131072,
3468
- maxTokens: 4096,
3502
+ maxTokens: 131072,
3469
3503
  },
3470
3504
  "mistralai/devstral-medium": {
3471
3505
  id: "mistralai/devstral-medium",
@@ -3969,8 +4003,8 @@ export const MODELS = {
3969
4003
  reasoning: true,
3970
4004
  input: ["text"],
3971
4005
  cost: {
3972
- input: 0.035,
3973
- output: 0.13799999999999998,
4006
+ input: 0.028,
4007
+ output: 0.1104,
3974
4008
  cacheRead: 0,
3975
4009
  cacheWrite: 0,
3976
4010
  },
@@ -4003,8 +4037,8 @@ export const MODELS = {
4003
4037
  reasoning: true,
4004
4038
  input: ["text"],
4005
4039
  cost: {
4006
- input: 0.049999999999999996,
4007
- output: 0.19999999999999998,
4040
+ input: 0.08,
4041
+ output: 0.24,
4008
4042
  cacheRead: 0,
4009
4043
  cacheWrite: 0,
4010
4044
  },
@@ -4190,13 +4224,13 @@ export const MODELS = {
4190
4224
  reasoning: false,
4191
4225
  input: ["text", "image"],
4192
4226
  cost: {
4193
- input: 0.15,
4194
- output: 0.6,
4227
+ input: 0.136,
4228
+ output: 0.6799999999999999,
4195
4229
  cacheRead: 0,
4196
4230
  cacheWrite: 0,
4197
4231
  },
4198
4232
  contextWindow: 1048576,
4199
- maxTokens: 16384,
4233
+ maxTokens: 8192,
4200
4234
  },
4201
4235
  "meta-llama/llama-4-scout": {
4202
4236
  id: "meta-llama/llama-4-scout",
@@ -4241,9 +4275,9 @@ export const MODELS = {
4241
4275
  reasoning: true,
4242
4276
  input: ["text"],
4243
4277
  cost: {
4244
- input: 0.24,
4245
- output: 0.84,
4246
- cacheRead: 0,
4278
+ input: 0.216,
4279
+ output: 0.896,
4280
+ cacheRead: 0.135,
4247
4281
  cacheWrite: 0,
4248
4282
  },
4249
4283
  contextWindow: 163840,
@@ -4649,13 +4683,13 @@ export const MODELS = {
4649
4683
  reasoning: false,
4650
4684
  input: ["text"],
4651
4685
  cost: {
4652
- input: 0.13,
4653
- output: 0.38,
4686
+ input: 0.10400000000000001,
4687
+ output: 0.312,
4654
4688
  cacheRead: 0,
4655
4689
  cacheWrite: 0,
4656
4690
  },
4657
4691
  contextWindow: 131072,
4658
- maxTokens: 16384,
4692
+ maxTokens: 120000,
4659
4693
  },
4660
4694
  "amazon/nova-lite-v1": {
4661
4695
  id: "amazon/nova-lite-v1",
@@ -4980,34 +5014,34 @@ export const MODELS = {
4980
5014
  contextWindow: 32768,
4981
5015
  maxTokens: 4096,
4982
5016
  },
4983
- "cohere/command-r-08-2024": {
4984
- id: "cohere/command-r-08-2024",
4985
- name: "Cohere: Command R (08-2024)",
5017
+ "cohere/command-r-plus-08-2024": {
5018
+ id: "cohere/command-r-plus-08-2024",
5019
+ name: "Cohere: Command R+ (08-2024)",
4986
5020
  api: "openai-completions",
4987
5021
  provider: "openrouter",
4988
5022
  baseUrl: "https://openrouter.ai/api/v1",
4989
5023
  reasoning: false,
4990
5024
  input: ["text"],
4991
5025
  cost: {
4992
- input: 0.15,
4993
- output: 0.6,
5026
+ input: 2.5,
5027
+ output: 10,
4994
5028
  cacheRead: 0,
4995
5029
  cacheWrite: 0,
4996
5030
  },
4997
5031
  contextWindow: 128000,
4998
5032
  maxTokens: 4000,
4999
5033
  },
5000
- "cohere/command-r-plus-08-2024": {
5001
- id: "cohere/command-r-plus-08-2024",
5002
- name: "Cohere: Command R+ (08-2024)",
5034
+ "cohere/command-r-08-2024": {
5035
+ id: "cohere/command-r-08-2024",
5036
+ name: "Cohere: Command R (08-2024)",
5003
5037
  api: "openai-completions",
5004
5038
  provider: "openrouter",
5005
5039
  baseUrl: "https://openrouter.ai/api/v1",
5006
5040
  reasoning: false,
5007
5041
  input: ["text"],
5008
5042
  cost: {
5009
- input: 2.5,
5010
- output: 10,
5043
+ input: 0.15,
5044
+ output: 0.6,
5011
5045
  cacheRead: 0,
5012
5046
  cacheWrite: 0,
5013
5047
  },
@@ -5082,22 +5116,22 @@ export const MODELS = {
5082
5116
  contextWindow: 128000,
5083
5117
  maxTokens: 16384,
5084
5118
  },
5085
- "meta-llama/llama-3.1-8b-instruct": {
5086
- id: "meta-llama/llama-3.1-8b-instruct",
5087
- name: "Meta: Llama 3.1 8B Instruct",
5119
+ "meta-llama/llama-3.1-405b-instruct": {
5120
+ id: "meta-llama/llama-3.1-405b-instruct",
5121
+ name: "Meta: Llama 3.1 405B Instruct",
5088
5122
  api: "openai-completions",
5089
5123
  provider: "openrouter",
5090
5124
  baseUrl: "https://openrouter.ai/api/v1",
5091
5125
  reasoning: false,
5092
5126
  input: ["text"],
5093
5127
  cost: {
5094
- input: 0.02,
5095
- output: 0.03,
5128
+ input: 3.5,
5129
+ output: 3.5,
5096
5130
  cacheRead: 0,
5097
5131
  cacheWrite: 0,
5098
5132
  },
5099
- contextWindow: 131072,
5100
- maxTokens: 16384,
5133
+ contextWindow: 130815,
5134
+ maxTokens: 4096,
5101
5135
  },
5102
5136
  "meta-llama/llama-3.1-70b-instruct": {
5103
5137
  id: "meta-llama/llama-3.1-70b-instruct",
@@ -5116,22 +5150,22 @@ export const MODELS = {
5116
5150
  contextWindow: 131072,
5117
5151
  maxTokens: 4096,
5118
5152
  },
5119
- "meta-llama/llama-3.1-405b-instruct": {
5120
- id: "meta-llama/llama-3.1-405b-instruct",
5121
- name: "Meta: Llama 3.1 405B Instruct",
5153
+ "meta-llama/llama-3.1-8b-instruct": {
5154
+ id: "meta-llama/llama-3.1-8b-instruct",
5155
+ name: "Meta: Llama 3.1 8B Instruct",
5122
5156
  api: "openai-completions",
5123
5157
  provider: "openrouter",
5124
5158
  baseUrl: "https://openrouter.ai/api/v1",
5125
5159
  reasoning: false,
5126
5160
  input: ["text"],
5127
5161
  cost: {
5128
- input: 3.5,
5129
- output: 3.5,
5162
+ input: 0.02,
5163
+ output: 0.03,
5130
5164
  cacheRead: 0,
5131
5165
  cacheWrite: 0,
5132
5166
  },
5133
- contextWindow: 130815,
5134
- maxTokens: 4096,
5167
+ contextWindow: 131072,
5168
+ maxTokens: 16384,
5135
5169
  },
5136
5170
  "mistralai/mistral-nemo": {
5137
5171
  id: "mistralai/mistral-nemo",
@@ -5150,9 +5184,9 @@ export const MODELS = {
5150
5184
  contextWindow: 131072,
5151
5185
  maxTokens: 16384,
5152
5186
  },
5153
- "openai/gpt-4o-mini": {
5154
- id: "openai/gpt-4o-mini",
5155
- name: "OpenAI: GPT-4o-mini",
5187
+ "openai/gpt-4o-mini-2024-07-18": {
5188
+ id: "openai/gpt-4o-mini-2024-07-18",
5189
+ name: "OpenAI: GPT-4o-mini (2024-07-18)",
5156
5190
  api: "openai-completions",
5157
5191
  provider: "openrouter",
5158
5192
  baseUrl: "https://openrouter.ai/api/v1",
@@ -5167,9 +5201,9 @@ export const MODELS = {
5167
5201
  contextWindow: 128000,
5168
5202
  maxTokens: 16384,
5169
5203
  },
5170
- "openai/gpt-4o-mini-2024-07-18": {
5171
- id: "openai/gpt-4o-mini-2024-07-18",
5172
- name: "OpenAI: GPT-4o-mini (2024-07-18)",
5204
+ "openai/gpt-4o-mini": {
5205
+ id: "openai/gpt-4o-mini",
5206
+ name: "OpenAI: GPT-4o-mini",
5173
5207
  api: "openai-completions",
5174
5208
  provider: "openrouter",
5175
5209
  baseUrl: "https://openrouter.ai/api/v1",
@@ -5269,6 +5303,23 @@ export const MODELS = {
5269
5303
  contextWindow: 128000,
5270
5304
  maxTokens: 4096,
5271
5305
  },
5306
+ "openai/gpt-4o-2024-05-13": {
5307
+ id: "openai/gpt-4o-2024-05-13",
5308
+ name: "OpenAI: GPT-4o (2024-05-13)",
5309
+ api: "openai-completions",
5310
+ provider: "openrouter",
5311
+ baseUrl: "https://openrouter.ai/api/v1",
5312
+ reasoning: false,
5313
+ input: ["text", "image"],
5314
+ cost: {
5315
+ input: 5,
5316
+ output: 15,
5317
+ cacheRead: 0,
5318
+ cacheWrite: 0,
5319
+ },
5320
+ contextWindow: 128000,
5321
+ maxTokens: 4096,
5322
+ },
5272
5323
  "openai/gpt-4o": {
5273
5324
  id: "openai/gpt-4o",
5274
5325
  name: "OpenAI: GPT-4o",
@@ -5303,23 +5354,6 @@ export const MODELS = {
5303
5354
  contextWindow: 128000,
5304
5355
  maxTokens: 64000,
5305
5356
  },
5306
- "openai/gpt-4o-2024-05-13": {
5307
- id: "openai/gpt-4o-2024-05-13",
5308
- name: "OpenAI: GPT-4o (2024-05-13)",
5309
- api: "openai-completions",
5310
- provider: "openrouter",
5311
- baseUrl: "https://openrouter.ai/api/v1",
5312
- reasoning: false,
5313
- input: ["text", "image"],
5314
- cost: {
5315
- input: 5,
5316
- output: 15,
5317
- cacheRead: 0,
5318
- cacheWrite: 0,
5319
- },
5320
- contextWindow: 128000,
5321
- maxTokens: 4096,
5322
- },
5323
5357
  "meta-llama/llama-3-70b-instruct": {
5324
5358
  id: "meta-llama/llama-3-70b-instruct",
5325
5359
  name: "Meta: Llama 3 70B Instruct",
@@ -5439,38 +5473,38 @@ export const MODELS = {
5439
5473
  contextWindow: 128000,
5440
5474
  maxTokens: 4096,
5441
5475
  },
5442
- "openai/gpt-4-turbo-preview": {
5443
- id: "openai/gpt-4-turbo-preview",
5444
- name: "OpenAI: GPT-4 Turbo Preview",
5476
+ "openai/gpt-3.5-turbo-0613": {
5477
+ id: "openai/gpt-3.5-turbo-0613",
5478
+ name: "OpenAI: GPT-3.5 Turbo (older v0613)",
5445
5479
  api: "openai-completions",
5446
5480
  provider: "openrouter",
5447
5481
  baseUrl: "https://openrouter.ai/api/v1",
5448
5482
  reasoning: false,
5449
5483
  input: ["text"],
5450
5484
  cost: {
5451
- input: 10,
5452
- output: 30,
5485
+ input: 1,
5486
+ output: 2,
5453
5487
  cacheRead: 0,
5454
5488
  cacheWrite: 0,
5455
5489
  },
5456
- contextWindow: 128000,
5490
+ contextWindow: 4095,
5457
5491
  maxTokens: 4096,
5458
5492
  },
5459
- "openai/gpt-3.5-turbo-0613": {
5460
- id: "openai/gpt-3.5-turbo-0613",
5461
- name: "OpenAI: GPT-3.5 Turbo (older v0613)",
5493
+ "openai/gpt-4-turbo-preview": {
5494
+ id: "openai/gpt-4-turbo-preview",
5495
+ name: "OpenAI: GPT-4 Turbo Preview",
5462
5496
  api: "openai-completions",
5463
5497
  provider: "openrouter",
5464
5498
  baseUrl: "https://openrouter.ai/api/v1",
5465
5499
  reasoning: false,
5466
5500
  input: ["text"],
5467
5501
  cost: {
5468
- input: 1,
5469
- output: 2,
5502
+ input: 10,
5503
+ output: 30,
5470
5504
  cacheRead: 0,
5471
5505
  cacheWrite: 0,
5472
5506
  },
5473
- contextWindow: 4095,
5507
+ contextWindow: 128000,
5474
5508
  maxTokens: 4096,
5475
5509
  },
5476
5510
  "mistralai/mistral-small": {
@@ -5558,38 +5592,38 @@ export const MODELS = {
5558
5592
  contextWindow: 16385,
5559
5593
  maxTokens: 4096,
5560
5594
  },
5561
- "openai/gpt-4-0314": {
5562
- id: "openai/gpt-4-0314",
5563
- name: "OpenAI: GPT-4 (older v0314)",
5595
+ "openai/gpt-3.5-turbo": {
5596
+ id: "openai/gpt-3.5-turbo",
5597
+ name: "OpenAI: GPT-3.5 Turbo",
5564
5598
  api: "openai-completions",
5565
5599
  provider: "openrouter",
5566
5600
  baseUrl: "https://openrouter.ai/api/v1",
5567
5601
  reasoning: false,
5568
5602
  input: ["text"],
5569
5603
  cost: {
5570
- input: 30,
5571
- output: 60,
5604
+ input: 0.5,
5605
+ output: 1.5,
5572
5606
  cacheRead: 0,
5573
5607
  cacheWrite: 0,
5574
5608
  },
5575
- contextWindow: 8191,
5609
+ contextWindow: 16385,
5576
5610
  maxTokens: 4096,
5577
5611
  },
5578
- "openai/gpt-3.5-turbo": {
5579
- id: "openai/gpt-3.5-turbo",
5580
- name: "OpenAI: GPT-3.5 Turbo",
5612
+ "openai/gpt-4-0314": {
5613
+ id: "openai/gpt-4-0314",
5614
+ name: "OpenAI: GPT-4 (older v0314)",
5581
5615
  api: "openai-completions",
5582
5616
  provider: "openrouter",
5583
5617
  baseUrl: "https://openrouter.ai/api/v1",
5584
5618
  reasoning: false,
5585
5619
  input: ["text"],
5586
5620
  cost: {
5587
- input: 0.5,
5588
- output: 1.5,
5621
+ input: 30,
5622
+ output: 60,
5589
5623
  cacheRead: 0,
5590
5624
  cacheWrite: 0,
5591
5625
  },
5592
- contextWindow: 16385,
5626
+ contextWindow: 8191,
5593
5627
  maxTokens: 4096,
5594
5628
  },
5595
5629
  "openai/gpt-4": {