@asm-agent/ai 0.8.4 → 0.8.6

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.
@@ -3935,7 +3935,7 @@ export const MODELS = {
3935
3935
  cacheWrite: 0,
3936
3936
  },
3937
3937
  contextWindow: 1310720,
3938
- maxTokens: 1310720,
3938
+ maxTokens: 1048576,
3939
3939
  },
3940
3940
  },
3941
3941
  "deepseek": {
@@ -4047,6 +4047,23 @@ export const MODELS = {
4047
4047
  contextWindow: 1000000,
4048
4048
  maxTokens: 131072,
4049
4049
  },
4050
+ "accounts/fireworks/models/glm-5p3-flash": {
4051
+ id: "accounts/fireworks/models/glm-5p3-flash",
4052
+ name: "GLM 5.3 Flash",
4053
+ api: "anthropic-messages",
4054
+ provider: "fireworks",
4055
+ baseUrl: "https://api.fireworks.ai/inference",
4056
+ reasoning: true,
4057
+ input: ["text", "image"],
4058
+ cost: {
4059
+ input: 0.15,
4060
+ output: 0.5,
4061
+ cacheRead: 0.029,
4062
+ cacheWrite: 0,
4063
+ },
4064
+ contextWindow: 1000000,
4065
+ maxTokens: 131072,
4066
+ },
4050
4067
  "accounts/fireworks/models/gpt-oss-120b": {
4051
4068
  id: "accounts/fireworks/models/gpt-oss-120b",
4052
4069
  name: "GPT OSS 120B",
@@ -9615,23 +9632,6 @@ export const MODELS = {
9615
9632
  contextWindow: 256000,
9616
9633
  maxTokens: 256000,
9617
9634
  },
9618
- "hy3-free": {
9619
- id: "hy3-free",
9620
- name: "Hy3 Free",
9621
- api: "openai-completions",
9622
- provider: "opencode",
9623
- baseUrl: "https://opencode.ai/zen/v1",
9624
- reasoning: true,
9625
- input: ["text"],
9626
- cost: {
9627
- input: 0,
9628
- output: 0,
9629
- cacheRead: 0,
9630
- cacheWrite: 0,
9631
- },
9632
- contextWindow: 190000,
9633
- maxTokens: 64000,
9634
- },
9635
9635
  "kimi-k2.5": {
9636
9636
  id: "kimi-k2.5",
9637
9637
  name: "Kimi K2.5",
@@ -10052,16 +10052,16 @@ export const MODELS = {
10052
10052
  },
10053
10053
  "hy3": {
10054
10054
  id: "hy3",
10055
- name: "Hy3 (8x usage)",
10055
+ name: "Hy3",
10056
10056
  api: "openai-completions",
10057
10057
  provider: "opencode-go",
10058
10058
  baseUrl: "https://opencode.ai/zen/go/v1",
10059
10059
  reasoning: true,
10060
10060
  input: ["text"],
10061
10061
  cost: {
10062
- input: 0.0175,
10063
- output: 0.0725,
10064
- cacheRead: 0.004375,
10062
+ input: 0.14,
10063
+ output: 0.58,
10064
+ cacheRead: 0.035,
10065
10065
  cacheWrite: 0,
10066
10066
  },
10067
10067
  contextWindow: 256000,
@@ -10792,13 +10792,13 @@ export const MODELS = {
10792
10792
  thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null },
10793
10793
  input: ["text"],
10794
10794
  cost: {
10795
- input: 0.22,
10796
- output: 0.85,
10795
+ input: 0.25,
10796
+ output: 0.7999999999999999,
10797
10797
  cacheRead: 0.06,
10798
10798
  cacheWrite: 0,
10799
10799
  },
10800
10800
  contextWindow: 262144,
10801
- maxTokens: 235929,
10801
+ maxTokens: 80000,
10802
10802
  },
10803
10803
  "auto": {
10804
10804
  id: "auto",
@@ -11102,13 +11102,13 @@ export const MODELS = {
11102
11102
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null },
11103
11103
  input: ["text"],
11104
11104
  cost: {
11105
- input: 0.26,
11106
- output: 0.38,
11107
- cacheRead: 0.13,
11105
+ input: 0.26899999999999996,
11106
+ output: 0.39999999999999997,
11107
+ cacheRead: 0.13449999999999998,
11108
11108
  cacheWrite: 0,
11109
11109
  },
11110
11110
  contextWindow: 163840,
11111
- maxTokens: 147456,
11111
+ maxTokens: 65536,
11112
11112
  },
11113
11113
  "deepseek/deepseek-v3.2-exp": {
11114
11114
  id: "deepseek/deepseek-v3.2-exp",
@@ -11140,9 +11140,9 @@ export const MODELS = {
11140
11140
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max", "max": null },
11141
11141
  input: ["text"],
11142
11142
  cost: {
11143
- input: 0.08512,
11144
- output: 0.17024,
11145
- cacheRead: 0.017024,
11143
+ input: 0.088606,
11144
+ output: 0.177212,
11145
+ cacheRead: 0.017721200000000003,
11146
11146
  cacheWrite: 0,
11147
11147
  },
11148
11148
  contextWindow: 1048576,
@@ -11159,9 +11159,9 @@ export const MODELS = {
11159
11159
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max", "max": null },
11160
11160
  input: ["text"],
11161
11161
  cost: {
11162
- input: 0.045,
11163
- output: 0.09,
11164
- cacheRead: 0.009,
11162
+ input: 0.065,
11163
+ output: 0.18,
11164
+ cacheRead: 0.016,
11165
11165
  cacheWrite: 0,
11166
11166
  },
11167
11167
  contextWindow: 1310720,
@@ -11178,9 +11178,9 @@ export const MODELS = {
11178
11178
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max", "max": null },
11179
11179
  input: ["text", "image"],
11180
11180
  cost: {
11181
- input: 0.22,
11182
- output: 0.66,
11183
- cacheRead: 0.007,
11181
+ input: 0.44,
11182
+ output: 1.32,
11183
+ cacheRead: 0.014,
11184
11184
  cacheWrite: 0,
11185
11185
  },
11186
11186
  contextWindow: 1048576,
@@ -11197,13 +11197,13 @@ export const MODELS = {
11197
11197
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max", "max": null },
11198
11198
  input: ["text"],
11199
11199
  cost: {
11200
- input: 0.6909540000000001,
11201
- output: 1.3819080000000001,
11202
- cacheRead: 0.057579500000000006,
11200
+ input: 1.5999999999999999,
11201
+ output: 3.1999999999999997,
11202
+ cacheRead: 0.135,
11203
11203
  cacheWrite: 0,
11204
11204
  },
11205
11205
  contextWindow: 1048576,
11206
- maxTokens: 384000,
11206
+ maxTokens: 393216,
11207
11207
  },
11208
11208
  "deepseek/deepseek-v4-pro-0813": {
11209
11209
  id: "deepseek/deepseek-v4-pro-0813",
@@ -11216,9 +11216,9 @@ export const MODELS = {
11216
11216
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max", "max": null },
11217
11217
  input: ["text"],
11218
11218
  cost: {
11219
- input: 0.66,
11220
- output: 1.9800000000000002,
11221
- cacheRead: 0.022,
11219
+ input: 1.32,
11220
+ output: 3.9600000000000004,
11221
+ cacheRead: 0.044,
11222
11222
  cacheWrite: 0,
11223
11223
  },
11224
11224
  contextWindow: 1048576,
@@ -11852,12 +11852,12 @@ export const MODELS = {
11852
11852
  input: ["text", "image"],
11853
11853
  cost: {
11854
11854
  input: 0.19999999999999998,
11855
- output: 0.7999999999999999,
11855
+ output: 0.696,
11856
11856
  cacheRead: 0,
11857
11857
  cacheWrite: 0,
11858
11858
  },
11859
11859
  contextWindow: 1048576,
11860
- maxTokens: 16384,
11860
+ maxTokens: 115200,
11861
11861
  },
11862
11862
  "meta-llama/llama-4-scout": {
11863
11863
  id: "meta-llama/llama-4-scout",
@@ -12126,9 +12126,9 @@ export const MODELS = {
12126
12126
  reasoning: false,
12127
12127
  input: ["text"],
12128
12128
  cost: {
12129
- input: 0.44,
12130
- output: 2.2,
12131
- cacheRead: 0.044,
12129
+ input: 0.39999999999999997,
12130
+ output: 2,
12131
+ cacheRead: 0.04,
12132
12132
  cacheWrite: 0,
12133
12133
  },
12134
12134
  contextWindow: 262144,
@@ -12852,11 +12852,11 @@ export const MODELS = {
12852
12852
  cost: {
12853
12853
  input: 0.09999999999999999,
12854
12854
  output: 0.39999999999999997,
12855
- cacheRead: 0.03,
12855
+ cacheRead: 0.024999999999999998,
12856
12856
  cacheWrite: 0,
12857
12857
  },
12858
12858
  contextWindow: 1047576,
12859
- maxTokens: 942818,
12859
+ maxTokens: 32768,
12860
12860
  },
12861
12861
  "openai/gpt-4o": {
12862
12862
  id: "openai/gpt-4o",
@@ -14139,13 +14139,13 @@ export const MODELS = {
14139
14139
  reasoning: false,
14140
14140
  input: ["text"],
14141
14141
  cost: {
14142
- input: 0.09999999999999999,
14142
+ input: 0.09,
14143
14143
  output: 1.1,
14144
- cacheRead: 0.07,
14144
+ cacheRead: 0,
14145
14145
  cacheWrite: 0,
14146
14146
  },
14147
14147
  contextWindow: 262144,
14148
- maxTokens: 235929,
14148
+ maxTokens: 16384,
14149
14149
  },
14150
14150
  "qwen/qwen3-next-80b-a3b-thinking": {
14151
14151
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -14873,13 +14873,13 @@ export const MODELS = {
14873
14873
  thinkingLevelMap: { "minimal": "minimal", "low": "low", "medium": "medium", "high": "high", "xhigh": null, "max": "max" },
14874
14874
  input: ["text", "image"],
14875
14875
  cost: {
14876
- input: 0.95,
14876
+ input: 1,
14877
14877
  output: 4.05,
14878
- cacheRead: 0.16,
14878
+ cacheRead: 0.16999999999999998,
14879
14879
  cacheWrite: 0,
14880
14880
  },
14881
14881
  contextWindow: 1048576,
14882
- maxTokens: 262144,
14882
+ maxTokens: 471859,
14883
14883
  },
14884
14884
  "thinkingmachines/inkling-small": {
14885
14885
  id: "thinkingmachines/inkling-small",
@@ -15285,13 +15285,13 @@ export const MODELS = {
15285
15285
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null },
15286
15286
  input: ["text"],
15287
15287
  cost: {
15288
- input: 1.26,
15289
- output: 3.9600000000000004,
15290
- cacheRead: 0.234,
15288
+ input: 0.966,
15289
+ output: 3.036,
15290
+ cacheRead: 0.1794,
15291
15291
  cacheWrite: 0,
15292
15292
  },
15293
15293
  contextWindow: 204800,
15294
- maxTokens: 182476,
15294
+ maxTokens: 128000,
15295
15295
  },
15296
15296
  "z-ai/glm-5.2": {
15297
15297
  id: "z-ai/glm-5.2",
@@ -15469,12 +15469,12 @@ export const MODELS = {
15469
15469
  input: ["text"],
15470
15470
  cost: {
15471
15471
  input: 0.03,
15472
- output: 0.09999999999999999,
15473
- cacheRead: 0.007,
15472
+ output: 0.16,
15473
+ cacheRead: 0.013000000000000001,
15474
15474
  cacheWrite: 0,
15475
15475
  },
15476
15476
  contextWindow: 1310720,
15477
- maxTokens: 131072,
15477
+ maxTokens: 393216,
15478
15478
  },
15479
15479
  "~google/gemini-flash-latest": {
15480
15480
  id: "~google/gemini-flash-latest",
@@ -15594,13 +15594,13 @@ export const MODELS = {
15594
15594
  thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max" },
15595
15595
  input: ["text"],
15596
15596
  cost: {
15597
- input: 1.2,
15598
- output: 4,
15599
- cacheRead: 0.24,
15597
+ input: 1.1875,
15598
+ output: 4.18,
15599
+ cacheRead: 0.24699999999999997,
15600
15600
  cacheWrite: 0,
15601
15601
  },
15602
15602
  contextWindow: 1310720,
15603
- maxTokens: 943718,
15603
+ maxTokens: 131072,
15604
15604
  },
15605
15605
  },
15606
15606
  "prime-inference": {
@@ -15931,7 +15931,7 @@ export const MODELS = {
15931
15931
  cacheWrite: 0,
15932
15932
  },
15933
15933
  contextWindow: 163840,
15934
- maxTokens: 147456,
15934
+ maxTokens: 65536,
15935
15935
  featured: true,
15936
15936
  },
15937
15937
  "deepseek/deepseek-v3.2-exp": {
@@ -16009,7 +16009,7 @@ export const MODELS = {
16009
16009
  cacheWrite: 0,
16010
16010
  },
16011
16011
  contextWindow: 1048576,
16012
- maxTokens: 384000,
16012
+ maxTokens: 393216,
16013
16013
  featured: true,
16014
16014
  },
16015
16015
  "google/gemini-2.5-flash": {
@@ -16252,7 +16252,7 @@ export const MODELS = {
16252
16252
  cacheWrite: 0,
16253
16253
  },
16254
16254
  contextWindow: 1048576,
16255
- maxTokens: 16384,
16255
+ maxTokens: 115200,
16256
16256
  },
16257
16257
  "meta/muse-spark-1.2": {
16258
16258
  id: "meta/muse-spark-1.2",
@@ -16592,7 +16592,7 @@ export const MODELS = {
16592
16592
  cacheWrite: 0,
16593
16593
  },
16594
16594
  contextWindow: 1047576,
16595
- maxTokens: 942818,
16595
+ maxTokens: 32768,
16596
16596
  },
16597
16597
  "openai/gpt-4o": {
16598
16598
  id: "openai/gpt-4o",
@@ -17602,7 +17602,7 @@ export const MODELS = {
17602
17602
  cacheWrite: 0,
17603
17603
  },
17604
17604
  contextWindow: 204800,
17605
- maxTokens: 182476,
17605
+ maxTokens: 128000,
17606
17606
  featured: true,
17607
17607
  },
17608
17608
  "z-ai/glm-5.2": {