ask-llm-providers 0.1.2 → 0.8.2
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.
- checksums.yaml +4 -4
- data/CHANGELOG.md +181 -0
- data/lib/ask/llm/aliases.json +11 -0
- data/lib/ask/llm/aliases.rb +62 -0
- data/lib/ask/llm/catalog.rb +221 -0
- data/lib/ask/llm/cost_calculator.rb +114 -0
- data/lib/ask/llm/http.rb +68 -12
- data/lib/ask/llm/models/anthropic.json +872 -0
- data/lib/ask/llm/models/bedrock.json +3769 -0
- data/lib/ask/llm/models/deepseek.json +340 -0
- data/lib/ask/llm/models/gemini.json +1211 -0
- data/lib/ask/llm/models/meta.json +299 -0
- data/lib/ask/llm/models/mistral.json +1303 -0
- data/lib/ask/llm/models/moonshot.json +198 -0
- data/lib/ask/llm/models/nvidia_nim.json +289 -0
- data/lib/ask/llm/models/openai.json +2521 -0
- data/lib/ask/llm/models/opencode.json +552 -0
- data/lib/ask/llm/models/perplexity.json +148 -0
- data/lib/ask/llm/models/vertex_ai.json +1347 -0
- data/lib/ask/llm/models/xai.json +326 -0
- data/lib/ask/llm/models_schema.json +74 -0
- data/lib/ask/llm/openai_compatible.rb +100 -0
- data/lib/ask/llm/provider_config.rb +65 -0
- data/lib/ask/llm/sources/models_dev.rb +154 -0
- data/lib/ask/llm/sources/openrouter.rb +176 -0
- data/lib/ask/llm/sse_buffer.rb +43 -0
- data/lib/ask/llm/version.rb +1 -1
- data/lib/ask/provider/anthropic.rb +106 -103
- data/lib/ask/provider/bedrock.rb +84 -52
- data/lib/ask/provider/cloudflare.rb +62 -40
- data/lib/ask/provider/google.rb +112 -74
- data/lib/ask/provider/mistral.rb +156 -6
- data/lib/ask/provider/ollama.rb +83 -29
- data/lib/ask/provider/openai.rb +141 -68
- data/lib/ask/provider/openai_compatible.rb +91 -0
- data/lib/ask/skills/providers.model_select/SKILL.md +164 -0
- data/lib/ask-llm-providers.rb +22 -18
- metadata +35 -7
- data/lib/ask/llm/models/openai.rb +0 -69
|
@@ -0,0 +1,299 @@
|
|
|
1
|
+
[
|
|
2
|
+
{
|
|
3
|
+
"id": "llama-3.1-70b-instruct",
|
|
4
|
+
"name": "Meta: Llama 3.1 70B Instruct",
|
|
5
|
+
"provider": "meta",
|
|
6
|
+
"context_window": 131072,
|
|
7
|
+
"max_output_tokens": 16384,
|
|
8
|
+
"capabilities": [],
|
|
9
|
+
"modalities": {
|
|
10
|
+
"input": [
|
|
11
|
+
"text"
|
|
12
|
+
],
|
|
13
|
+
"output": [
|
|
14
|
+
"text"
|
|
15
|
+
]
|
|
16
|
+
},
|
|
17
|
+
"pricing": {
|
|
18
|
+
"text_tokens": {
|
|
19
|
+
"standard": {
|
|
20
|
+
"input_per_million": 0.4,
|
|
21
|
+
"output_per_million": 0.4
|
|
22
|
+
}
|
|
23
|
+
}
|
|
24
|
+
},
|
|
25
|
+
"architecture": "text->text",
|
|
26
|
+
"source": "openrouter"
|
|
27
|
+
},
|
|
28
|
+
{
|
|
29
|
+
"id": "llama-3.1-8b-instruct",
|
|
30
|
+
"name": "Meta: Llama 3.1 8B Instruct",
|
|
31
|
+
"provider": "meta",
|
|
32
|
+
"context_window": 131072,
|
|
33
|
+
"max_output_tokens": 131072,
|
|
34
|
+
"capabilities": [],
|
|
35
|
+
"modalities": {
|
|
36
|
+
"input": [
|
|
37
|
+
"text"
|
|
38
|
+
],
|
|
39
|
+
"output": [
|
|
40
|
+
"text"
|
|
41
|
+
]
|
|
42
|
+
},
|
|
43
|
+
"pricing": {
|
|
44
|
+
"text_tokens": {
|
|
45
|
+
"standard": {
|
|
46
|
+
"input_per_million": 0.05,
|
|
47
|
+
"output_per_million": 0.08,
|
|
48
|
+
"cache_read_input_per_million": 0.025
|
|
49
|
+
}
|
|
50
|
+
}
|
|
51
|
+
},
|
|
52
|
+
"architecture": "text->text",
|
|
53
|
+
"source": "openrouter"
|
|
54
|
+
},
|
|
55
|
+
{
|
|
56
|
+
"id": "llama-3.2-11b-vision-instruct",
|
|
57
|
+
"name": "Meta: Llama 3.2 11B Vision Instruct",
|
|
58
|
+
"provider": "meta",
|
|
59
|
+
"context_window": 131072,
|
|
60
|
+
"max_output_tokens": 16384,
|
|
61
|
+
"capabilities": [
|
|
62
|
+
"vision"
|
|
63
|
+
],
|
|
64
|
+
"modalities": {
|
|
65
|
+
"input": [
|
|
66
|
+
"text",
|
|
67
|
+
"image"
|
|
68
|
+
],
|
|
69
|
+
"output": [
|
|
70
|
+
"text"
|
|
71
|
+
]
|
|
72
|
+
},
|
|
73
|
+
"pricing": {
|
|
74
|
+
"text_tokens": {
|
|
75
|
+
"standard": {
|
|
76
|
+
"input_per_million": 0.345,
|
|
77
|
+
"output_per_million": 0.345
|
|
78
|
+
}
|
|
79
|
+
}
|
|
80
|
+
},
|
|
81
|
+
"architecture": "text+image->text",
|
|
82
|
+
"source": "openrouter"
|
|
83
|
+
},
|
|
84
|
+
{
|
|
85
|
+
"id": "llama-3.2-1b-instruct",
|
|
86
|
+
"name": "Meta: Llama 3.2 1B Instruct",
|
|
87
|
+
"provider": "meta",
|
|
88
|
+
"context_window": 131072,
|
|
89
|
+
"max_output_tokens": 60000,
|
|
90
|
+
"capabilities": [],
|
|
91
|
+
"modalities": {
|
|
92
|
+
"input": [
|
|
93
|
+
"text"
|
|
94
|
+
],
|
|
95
|
+
"output": [
|
|
96
|
+
"text"
|
|
97
|
+
]
|
|
98
|
+
},
|
|
99
|
+
"pricing": {
|
|
100
|
+
"text_tokens": {
|
|
101
|
+
"standard": {
|
|
102
|
+
"input_per_million": 0.027,
|
|
103
|
+
"output_per_million": 0.201
|
|
104
|
+
}
|
|
105
|
+
}
|
|
106
|
+
},
|
|
107
|
+
"architecture": "text->text",
|
|
108
|
+
"source": "openrouter"
|
|
109
|
+
},
|
|
110
|
+
{
|
|
111
|
+
"id": "llama-3.2-3b-instruct",
|
|
112
|
+
"name": "Meta: Llama 3.2 3B Instruct",
|
|
113
|
+
"provider": "meta",
|
|
114
|
+
"context_window": 131072,
|
|
115
|
+
"max_output_tokens": 80000,
|
|
116
|
+
"capabilities": [],
|
|
117
|
+
"modalities": {
|
|
118
|
+
"input": [
|
|
119
|
+
"text"
|
|
120
|
+
],
|
|
121
|
+
"output": [
|
|
122
|
+
"text"
|
|
123
|
+
]
|
|
124
|
+
},
|
|
125
|
+
"pricing": {
|
|
126
|
+
"text_tokens": {
|
|
127
|
+
"standard": {
|
|
128
|
+
"input_per_million": 0.0509,
|
|
129
|
+
"output_per_million": 0.335
|
|
130
|
+
}
|
|
131
|
+
}
|
|
132
|
+
},
|
|
133
|
+
"architecture": "text->text",
|
|
134
|
+
"source": "openrouter"
|
|
135
|
+
},
|
|
136
|
+
{
|
|
137
|
+
"id": "llama-3.2-3b-instruct:free",
|
|
138
|
+
"name": "Meta: Llama 3.2 3B Instruct (free)",
|
|
139
|
+
"provider": "meta",
|
|
140
|
+
"context_window": 131072,
|
|
141
|
+
"capabilities": [],
|
|
142
|
+
"modalities": {
|
|
143
|
+
"input": [
|
|
144
|
+
"text"
|
|
145
|
+
],
|
|
146
|
+
"output": [
|
|
147
|
+
"text"
|
|
148
|
+
]
|
|
149
|
+
},
|
|
150
|
+
"pricing": {
|
|
151
|
+
"text_tokens": {
|
|
152
|
+
"standard": {
|
|
153
|
+
"input_per_million": 0.0,
|
|
154
|
+
"output_per_million": 0.0
|
|
155
|
+
}
|
|
156
|
+
}
|
|
157
|
+
},
|
|
158
|
+
"architecture": "text->text",
|
|
159
|
+
"source": "openrouter"
|
|
160
|
+
},
|
|
161
|
+
{
|
|
162
|
+
"id": "llama-3.3-70b-instruct",
|
|
163
|
+
"name": "Meta: Llama 3.3 70B Instruct",
|
|
164
|
+
"provider": "meta",
|
|
165
|
+
"context_window": 131072,
|
|
166
|
+
"max_output_tokens": 128000,
|
|
167
|
+
"capabilities": [],
|
|
168
|
+
"modalities": {
|
|
169
|
+
"input": [
|
|
170
|
+
"text"
|
|
171
|
+
],
|
|
172
|
+
"output": [
|
|
173
|
+
"text"
|
|
174
|
+
]
|
|
175
|
+
},
|
|
176
|
+
"pricing": {
|
|
177
|
+
"text_tokens": {
|
|
178
|
+
"standard": {
|
|
179
|
+
"input_per_million": 0.13,
|
|
180
|
+
"output_per_million": 0.4
|
|
181
|
+
}
|
|
182
|
+
}
|
|
183
|
+
},
|
|
184
|
+
"architecture": "text->text",
|
|
185
|
+
"source": "openrouter"
|
|
186
|
+
},
|
|
187
|
+
{
|
|
188
|
+
"id": "llama-3.3-70b-instruct:free",
|
|
189
|
+
"name": "Meta: Llama 3.3 70B Instruct (free)",
|
|
190
|
+
"provider": "meta",
|
|
191
|
+
"context_window": 131072,
|
|
192
|
+
"capabilities": [],
|
|
193
|
+
"modalities": {
|
|
194
|
+
"input": [
|
|
195
|
+
"text"
|
|
196
|
+
],
|
|
197
|
+
"output": [
|
|
198
|
+
"text"
|
|
199
|
+
]
|
|
200
|
+
},
|
|
201
|
+
"pricing": {
|
|
202
|
+
"text_tokens": {
|
|
203
|
+
"standard": {
|
|
204
|
+
"input_per_million": 0.0,
|
|
205
|
+
"output_per_million": 0.0
|
|
206
|
+
}
|
|
207
|
+
}
|
|
208
|
+
},
|
|
209
|
+
"architecture": "text->text",
|
|
210
|
+
"source": "openrouter"
|
|
211
|
+
},
|
|
212
|
+
{
|
|
213
|
+
"id": "llama-4-maverick",
|
|
214
|
+
"name": "Meta: Llama 4 Maverick",
|
|
215
|
+
"provider": "meta",
|
|
216
|
+
"context_window": 1048576,
|
|
217
|
+
"max_output_tokens": 16384,
|
|
218
|
+
"capabilities": [
|
|
219
|
+
"vision"
|
|
220
|
+
],
|
|
221
|
+
"modalities": {
|
|
222
|
+
"input": [
|
|
223
|
+
"text",
|
|
224
|
+
"image"
|
|
225
|
+
],
|
|
226
|
+
"output": [
|
|
227
|
+
"text"
|
|
228
|
+
]
|
|
229
|
+
},
|
|
230
|
+
"pricing": {
|
|
231
|
+
"text_tokens": {
|
|
232
|
+
"standard": {
|
|
233
|
+
"input_per_million": 0.2,
|
|
234
|
+
"output_per_million": 0.8
|
|
235
|
+
}
|
|
236
|
+
}
|
|
237
|
+
},
|
|
238
|
+
"architecture": "text+image->text",
|
|
239
|
+
"source": "openrouter"
|
|
240
|
+
},
|
|
241
|
+
{
|
|
242
|
+
"id": "llama-4-scout",
|
|
243
|
+
"name": "Meta: Llama 4 Scout",
|
|
244
|
+
"provider": "meta",
|
|
245
|
+
"context_window": 10000000,
|
|
246
|
+
"max_output_tokens": 16384,
|
|
247
|
+
"capabilities": [
|
|
248
|
+
"vision"
|
|
249
|
+
],
|
|
250
|
+
"modalities": {
|
|
251
|
+
"input": [
|
|
252
|
+
"text",
|
|
253
|
+
"image"
|
|
254
|
+
],
|
|
255
|
+
"output": [
|
|
256
|
+
"text"
|
|
257
|
+
]
|
|
258
|
+
},
|
|
259
|
+
"pricing": {
|
|
260
|
+
"text_tokens": {
|
|
261
|
+
"standard": {
|
|
262
|
+
"input_per_million": 0.1,
|
|
263
|
+
"output_per_million": 0.3
|
|
264
|
+
}
|
|
265
|
+
}
|
|
266
|
+
},
|
|
267
|
+
"architecture": "text+image->text",
|
|
268
|
+
"source": "openrouter"
|
|
269
|
+
},
|
|
270
|
+
{
|
|
271
|
+
"id": "llama-guard-4-12b",
|
|
272
|
+
"name": "Meta: Llama Guard 4 12B",
|
|
273
|
+
"provider": "meta",
|
|
274
|
+
"context_window": 163840,
|
|
275
|
+
"max_output_tokens": 16384,
|
|
276
|
+
"capabilities": [
|
|
277
|
+
"vision"
|
|
278
|
+
],
|
|
279
|
+
"modalities": {
|
|
280
|
+
"input": [
|
|
281
|
+
"text",
|
|
282
|
+
"image"
|
|
283
|
+
],
|
|
284
|
+
"output": [
|
|
285
|
+
"text"
|
|
286
|
+
]
|
|
287
|
+
},
|
|
288
|
+
"pricing": {
|
|
289
|
+
"text_tokens": {
|
|
290
|
+
"standard": {
|
|
291
|
+
"input_per_million": 0.18,
|
|
292
|
+
"output_per_million": 0.18
|
|
293
|
+
}
|
|
294
|
+
}
|
|
295
|
+
},
|
|
296
|
+
"architecture": "text+image->text",
|
|
297
|
+
"source": "openrouter"
|
|
298
|
+
}
|
|
299
|
+
]
|