genai-otel-instrument 0.1.24__py3-none-any.whl
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.
- genai_otel/__init__.py +132 -0
- genai_otel/__version__.py +34 -0
- genai_otel/auto_instrument.py +602 -0
- genai_otel/cli.py +92 -0
- genai_otel/config.py +333 -0
- genai_otel/cost_calculator.py +467 -0
- genai_otel/cost_enriching_exporter.py +207 -0
- genai_otel/cost_enrichment_processor.py +174 -0
- genai_otel/evaluation/__init__.py +76 -0
- genai_otel/evaluation/bias_detector.py +364 -0
- genai_otel/evaluation/config.py +261 -0
- genai_otel/evaluation/hallucination_detector.py +525 -0
- genai_otel/evaluation/pii_detector.py +356 -0
- genai_otel/evaluation/prompt_injection_detector.py +262 -0
- genai_otel/evaluation/restricted_topics_detector.py +316 -0
- genai_otel/evaluation/span_processor.py +962 -0
- genai_otel/evaluation/toxicity_detector.py +406 -0
- genai_otel/exceptions.py +17 -0
- genai_otel/gpu_metrics.py +516 -0
- genai_otel/instrumentors/__init__.py +71 -0
- genai_otel/instrumentors/anthropic_instrumentor.py +134 -0
- genai_otel/instrumentors/anyscale_instrumentor.py +27 -0
- genai_otel/instrumentors/autogen_instrumentor.py +394 -0
- genai_otel/instrumentors/aws_bedrock_instrumentor.py +94 -0
- genai_otel/instrumentors/azure_openai_instrumentor.py +69 -0
- genai_otel/instrumentors/base.py +919 -0
- genai_otel/instrumentors/bedrock_agents_instrumentor.py +398 -0
- genai_otel/instrumentors/cohere_instrumentor.py +140 -0
- genai_otel/instrumentors/crewai_instrumentor.py +311 -0
- genai_otel/instrumentors/dspy_instrumentor.py +661 -0
- genai_otel/instrumentors/google_ai_instrumentor.py +310 -0
- genai_otel/instrumentors/groq_instrumentor.py +106 -0
- genai_otel/instrumentors/guardrails_ai_instrumentor.py +510 -0
- genai_otel/instrumentors/haystack_instrumentor.py +503 -0
- genai_otel/instrumentors/huggingface_instrumentor.py +399 -0
- genai_otel/instrumentors/hyperbolic_instrumentor.py +236 -0
- genai_otel/instrumentors/instructor_instrumentor.py +425 -0
- genai_otel/instrumentors/langchain_instrumentor.py +340 -0
- genai_otel/instrumentors/langgraph_instrumentor.py +328 -0
- genai_otel/instrumentors/llamaindex_instrumentor.py +36 -0
- genai_otel/instrumentors/mistralai_instrumentor.py +315 -0
- genai_otel/instrumentors/ollama_instrumentor.py +197 -0
- genai_otel/instrumentors/ollama_server_metrics_poller.py +336 -0
- genai_otel/instrumentors/openai_agents_instrumentor.py +291 -0
- genai_otel/instrumentors/openai_instrumentor.py +260 -0
- genai_otel/instrumentors/pydantic_ai_instrumentor.py +362 -0
- genai_otel/instrumentors/replicate_instrumentor.py +87 -0
- genai_otel/instrumentors/sambanova_instrumentor.py +196 -0
- genai_otel/instrumentors/togetherai_instrumentor.py +146 -0
- genai_otel/instrumentors/vertexai_instrumentor.py +106 -0
- genai_otel/llm_pricing.json +1676 -0
- genai_otel/logging_config.py +45 -0
- genai_otel/mcp_instrumentors/__init__.py +14 -0
- genai_otel/mcp_instrumentors/api_instrumentor.py +144 -0
- genai_otel/mcp_instrumentors/base.py +105 -0
- genai_otel/mcp_instrumentors/database_instrumentor.py +336 -0
- genai_otel/mcp_instrumentors/kafka_instrumentor.py +31 -0
- genai_otel/mcp_instrumentors/manager.py +139 -0
- genai_otel/mcp_instrumentors/redis_instrumentor.py +31 -0
- genai_otel/mcp_instrumentors/vector_db_instrumentor.py +265 -0
- genai_otel/metrics.py +148 -0
- genai_otel/py.typed +2 -0
- genai_otel/server_metrics.py +197 -0
- genai_otel_instrument-0.1.24.dist-info/METADATA +1404 -0
- genai_otel_instrument-0.1.24.dist-info/RECORD +69 -0
- genai_otel_instrument-0.1.24.dist-info/WHEEL +5 -0
- genai_otel_instrument-0.1.24.dist-info/entry_points.txt +2 -0
- genai_otel_instrument-0.1.24.dist-info/licenses/LICENSE +680 -0
- genai_otel_instrument-0.1.24.dist-info/top_level.txt +1 -0
|
@@ -0,0 +1,1676 @@
|
|
|
1
|
+
{
|
|
2
|
+
"embeddings": {
|
|
3
|
+
"text-embedding-ada-002": 0.0001,
|
|
4
|
+
"text-embedding-3-small": 2e-05,
|
|
5
|
+
"text-embedding-3-large": 0.00013,
|
|
6
|
+
"ada": 0.0001,
|
|
7
|
+
"ada-v2": 0.0001,
|
|
8
|
+
"text-ada-001": 0.0001,
|
|
9
|
+
"azure_text-embedding-ada-002": 0.0001,
|
|
10
|
+
"azure_text-embedding-3-small": 2e-05,
|
|
11
|
+
"azure_text-embedding-3-large": 0.00013,
|
|
12
|
+
"azure_ada": 0.0001,
|
|
13
|
+
"azure_ada-v2": 0.0001,
|
|
14
|
+
"azure_text-ada-001": 0.0001,
|
|
15
|
+
"embed-english-v3.0": 0.0001,
|
|
16
|
+
"embed-multilingual-v3.0": 0.0001,
|
|
17
|
+
"embed-english-light-v3.0": 0.0001,
|
|
18
|
+
"embed-multilingual-light-v3.0": 0.0001,
|
|
19
|
+
"embed-english-v2.0": 0.0001,
|
|
20
|
+
"embed-english-light-v2.0": 0.0001,
|
|
21
|
+
"embed-multilingual-v2.0": 0.0001,
|
|
22
|
+
"mistral-embed": 0.0001,
|
|
23
|
+
"amazon.titan-embed-text-v1": 0.0001,
|
|
24
|
+
"amazon.titan-embed-text-v2": 2e-05,
|
|
25
|
+
"textembedding-gecko": 0.0001,
|
|
26
|
+
"textembedding-gecko@001": 0.0001,
|
|
27
|
+
"textembedding-gecko@002": 0.0001,
|
|
28
|
+
"textembedding-gecko@003": 0.0001,
|
|
29
|
+
"google/embeddinggemma-300m": {
|
|
30
|
+
"promptPrice": 2e-05,
|
|
31
|
+
"completionPrice": 2e-05,
|
|
32
|
+
"note": "Googles embedding model - already noted in earlier analysis"
|
|
33
|
+
},
|
|
34
|
+
"Snowflake/snowflake-arctic-embed-m": {
|
|
35
|
+
"promptPrice": 3e-05,
|
|
36
|
+
"completionPrice": 3e-05,
|
|
37
|
+
"note": "Medium Arctic embedding - 496K downloads"
|
|
38
|
+
},
|
|
39
|
+
"Snowflake/snowflake-arctic-embed-s": {
|
|
40
|
+
"promptPrice": 2e-05,
|
|
41
|
+
"completionPrice": 2e-05,
|
|
42
|
+
"note": "Small Arctic embedding"
|
|
43
|
+
},
|
|
44
|
+
"Snowflake/snowflake-arctic-embed-m-v2.0": {
|
|
45
|
+
"promptPrice": 3e-05,
|
|
46
|
+
"completionPrice": 3e-05,
|
|
47
|
+
"note": "Medium v2.0 Arctic embedding"
|
|
48
|
+
},
|
|
49
|
+
"Snowflake/snowflake-arctic-embed-xs": {
|
|
50
|
+
"promptPrice": 1e-05,
|
|
51
|
+
"completionPrice": 1e-05,
|
|
52
|
+
"note": "Extra small Arctic embedding"
|
|
53
|
+
},
|
|
54
|
+
"nvidia/NV-Embed-v2": {
|
|
55
|
+
"promptPrice": 5e-05,
|
|
56
|
+
"completionPrice": 5e-05,
|
|
57
|
+
"note": "NV-Embed v2 - high-quality text embeddings, 198K downloads"
|
|
58
|
+
},
|
|
59
|
+
"nvidia/llama-embed-nemotron-8b": {
|
|
60
|
+
"promptPrice": 6e-05,
|
|
61
|
+
"completionPrice": 6e-05,
|
|
62
|
+
"note": "Llama-based embedding model - multilingual"
|
|
63
|
+
},
|
|
64
|
+
"nvidia/omni-embed-nemotron-3b": {
|
|
65
|
+
"promptPrice": 4e-05,
|
|
66
|
+
"completionPrice": 4e-05,
|
|
67
|
+
"note": "Multimodal embedding - text, image, video, audio"
|
|
68
|
+
}
|
|
69
|
+
},
|
|
70
|
+
"images": {
|
|
71
|
+
"dall-e-3": {
|
|
72
|
+
"standard": {
|
|
73
|
+
"1024x1024": 0.04,
|
|
74
|
+
"1024x1792": 0.02,
|
|
75
|
+
"1792x1024": 0.08
|
|
76
|
+
},
|
|
77
|
+
"hd": {
|
|
78
|
+
"1024x1024": 0.08,
|
|
79
|
+
"1024x1792": 0.12,
|
|
80
|
+
"1792x1024": 0.12
|
|
81
|
+
}
|
|
82
|
+
},
|
|
83
|
+
"azure_dall-e-3": {
|
|
84
|
+
"standard": {
|
|
85
|
+
"1024x1024": 0.04,
|
|
86
|
+
"1024x1792": 0.02,
|
|
87
|
+
"1792x1024": 0.08
|
|
88
|
+
},
|
|
89
|
+
"hd": {
|
|
90
|
+
"1024x1024": 0.08,
|
|
91
|
+
"1024x1792": 0.12,
|
|
92
|
+
"1792x1024": 0.12
|
|
93
|
+
}
|
|
94
|
+
},
|
|
95
|
+
"dall-e-2": {
|
|
96
|
+
"standard": {
|
|
97
|
+
"1024x1024": 0.02,
|
|
98
|
+
"512x512": 0.018,
|
|
99
|
+
"256x256": 0.016
|
|
100
|
+
}
|
|
101
|
+
},
|
|
102
|
+
"black-forest-labs/FLUX.1-dev": {
|
|
103
|
+
"standard": {
|
|
104
|
+
"1000000": 0.025
|
|
105
|
+
}
|
|
106
|
+
},
|
|
107
|
+
"black-forest-labs/FLUX.1-canny": {
|
|
108
|
+
"standard": {
|
|
109
|
+
"1000000": 0.025
|
|
110
|
+
}
|
|
111
|
+
},
|
|
112
|
+
"black-forest-labs/FLUX.1-depth": {
|
|
113
|
+
"standard": {
|
|
114
|
+
"1000000": 0.025
|
|
115
|
+
}
|
|
116
|
+
},
|
|
117
|
+
"black-forest-labs/FLUX.1-redux": {
|
|
118
|
+
"standard": {
|
|
119
|
+
"1000000": 0.025
|
|
120
|
+
}
|
|
121
|
+
},
|
|
122
|
+
"black-forest-labs/FLUX.1-schnell": {
|
|
123
|
+
"standard": {
|
|
124
|
+
"1000000": 0.0027
|
|
125
|
+
}
|
|
126
|
+
},
|
|
127
|
+
"black-forest-labs/FLUX.1-pro": {
|
|
128
|
+
"standard": {
|
|
129
|
+
"1000000": 0.04
|
|
130
|
+
}
|
|
131
|
+
},
|
|
132
|
+
"black-forest-labs/FLUX.1.1-pro": {
|
|
133
|
+
"standard": {
|
|
134
|
+
"1000000": 0.05
|
|
135
|
+
}
|
|
136
|
+
},
|
|
137
|
+
"stabilityai/stable-diffusion-xl-base-1.0": {
|
|
138
|
+
"standard": {
|
|
139
|
+
"512X512": 0.001,
|
|
140
|
+
"1024x1024": 0.01
|
|
141
|
+
}
|
|
142
|
+
},
|
|
143
|
+
"amazon.titan-image-generator-v1": {
|
|
144
|
+
"standard": {
|
|
145
|
+
"512x512": 0.008,
|
|
146
|
+
"1024x1024": 0.01
|
|
147
|
+
},
|
|
148
|
+
"premium": {
|
|
149
|
+
"512x512": 0.01,
|
|
150
|
+
"1024x1024": 0.012
|
|
151
|
+
}
|
|
152
|
+
},
|
|
153
|
+
"grok-image": {
|
|
154
|
+
"standard": {
|
|
155
|
+
"per_image": 0.07
|
|
156
|
+
}
|
|
157
|
+
},
|
|
158
|
+
"xai-grok-image": {
|
|
159
|
+
"standard": {
|
|
160
|
+
"per_image": 0.07
|
|
161
|
+
}
|
|
162
|
+
}
|
|
163
|
+
},
|
|
164
|
+
"audio": {
|
|
165
|
+
"tts-1": 0.015,
|
|
166
|
+
"tts-1-hd": 0.03,
|
|
167
|
+
"eleven_multilingual_v2": 0.24,
|
|
168
|
+
"eleven_multilingual_v1": 0.24,
|
|
169
|
+
"eleven_monolingual_v1": 0.24,
|
|
170
|
+
"eleven_english_v1": 0.24,
|
|
171
|
+
"eleven_turbo_v2": 0.24,
|
|
172
|
+
"eleven_english_sts_v2": 0.24,
|
|
173
|
+
"eleven_multilingual_sts_v2": 0.24,
|
|
174
|
+
"best": 0.00010277777,
|
|
175
|
+
"nano": 3.333333e-05
|
|
176
|
+
},
|
|
177
|
+
"chat": {
|
|
178
|
+
"gpt-4.1-nano-2025-04-14": {
|
|
179
|
+
"promptPrice": 0.0001,
|
|
180
|
+
"completionPrice": 0.0004
|
|
181
|
+
},
|
|
182
|
+
"gpt-4.1-nano": {
|
|
183
|
+
"promptPrice": 0.0001,
|
|
184
|
+
"completionPrice": 0.0004
|
|
185
|
+
},
|
|
186
|
+
"gpt-4.1-mini-2025-04-14": {
|
|
187
|
+
"promptPrice": 0.0004,
|
|
188
|
+
"completionPrice": 0.0016
|
|
189
|
+
},
|
|
190
|
+
"gpt-4.1-mini": {
|
|
191
|
+
"promptPrice": 0.0004,
|
|
192
|
+
"completionPrice": 0.0016
|
|
193
|
+
},
|
|
194
|
+
"gpt-4.1-2025-04-14": {
|
|
195
|
+
"promptPrice": 0.002,
|
|
196
|
+
"completionPrice": 0.008
|
|
197
|
+
},
|
|
198
|
+
"gpt-4.1": {
|
|
199
|
+
"promptPrice": 0.002,
|
|
200
|
+
"completionPrice": 0.008
|
|
201
|
+
},
|
|
202
|
+
"gpt-5": {
|
|
203
|
+
"promptPrice": 0.00125,
|
|
204
|
+
"completionPrice": 0.01
|
|
205
|
+
},
|
|
206
|
+
"gpt-5-2025-08-07": {
|
|
207
|
+
"promptPrice": 0.00125,
|
|
208
|
+
"completionPrice": 0.01
|
|
209
|
+
},
|
|
210
|
+
"gpt-5-mini": {
|
|
211
|
+
"promptPrice": 0.00025,
|
|
212
|
+
"completionPrice": 0.002
|
|
213
|
+
},
|
|
214
|
+
"gpt-5-nano": {
|
|
215
|
+
"promptPrice": 0.0001,
|
|
216
|
+
"completionPrice": 0.0004
|
|
217
|
+
},
|
|
218
|
+
"gpt-4o": {
|
|
219
|
+
"promptPrice": 0.0005,
|
|
220
|
+
"completionPrice": 0.0015
|
|
221
|
+
},
|
|
222
|
+
"gpt-4o-2024-08-06": {
|
|
223
|
+
"promptPrice": 0.0025,
|
|
224
|
+
"completionPrice": 0.01
|
|
225
|
+
},
|
|
226
|
+
"gpt-4o-2024-05-13": {
|
|
227
|
+
"promptPrice": 0.005,
|
|
228
|
+
"completionPrice": 0.015
|
|
229
|
+
},
|
|
230
|
+
"gpt-4o-mini": {
|
|
231
|
+
"promptPrice": 0.00015,
|
|
232
|
+
"completionPrice": 0.0006
|
|
233
|
+
},
|
|
234
|
+
"gpt-4o-mini-2024-07-18": {
|
|
235
|
+
"promptPrice": 0.00015,
|
|
236
|
+
"completionPrice": 0.0006
|
|
237
|
+
},
|
|
238
|
+
"o1-mini": {
|
|
239
|
+
"promptPrice": 0.003,
|
|
240
|
+
"completionPrice": 0.012
|
|
241
|
+
},
|
|
242
|
+
"o1-mini-2024-09-12": {
|
|
243
|
+
"promptPrice": 0.003,
|
|
244
|
+
"completionPrice": 0.012
|
|
245
|
+
},
|
|
246
|
+
"o1-preview": {
|
|
247
|
+
"promptPrice": 0.015,
|
|
248
|
+
"completionPrice": 0.06
|
|
249
|
+
},
|
|
250
|
+
"o1-preview-2024-09-12": {
|
|
251
|
+
"promptPrice": 0.015,
|
|
252
|
+
"completionPrice": 0.06
|
|
253
|
+
},
|
|
254
|
+
"gpt-3.5-turbo": {
|
|
255
|
+
"promptPrice": 0.0005,
|
|
256
|
+
"completionPrice": 0.0015
|
|
257
|
+
},
|
|
258
|
+
"gpt-3.5-turbo-0125": {
|
|
259
|
+
"promptPrice": 0.0005,
|
|
260
|
+
"completionPrice": 0.0015
|
|
261
|
+
},
|
|
262
|
+
"azure_gpt-35-turbo": {
|
|
263
|
+
"promptPrice": 0.0005,
|
|
264
|
+
"completionPrice": 0.0015
|
|
265
|
+
},
|
|
266
|
+
"azure_gpt-35-turbo-16k": {
|
|
267
|
+
"promptPrice": 0.0005,
|
|
268
|
+
"completionPrice": 0.0015
|
|
269
|
+
},
|
|
270
|
+
"azure_gpt-35-turbo-instruct": {
|
|
271
|
+
"promptPrice": 0.0015,
|
|
272
|
+
"completionPrice": 0.002
|
|
273
|
+
},
|
|
274
|
+
"gpt-4": {
|
|
275
|
+
"promptPrice": 0.03,
|
|
276
|
+
"completionPrice": 0.06
|
|
277
|
+
},
|
|
278
|
+
"gpt-4-turbo": {
|
|
279
|
+
"promptPrice": 0.01,
|
|
280
|
+
"completionPrice": 0.03
|
|
281
|
+
},
|
|
282
|
+
"gpt-4-32k": {
|
|
283
|
+
"promptPrice": 0.06,
|
|
284
|
+
"completionPrice": 0.12
|
|
285
|
+
},
|
|
286
|
+
"gpt-4-1106-preview": {
|
|
287
|
+
"promptPrice": 0.01,
|
|
288
|
+
"completionPrice": 0.03
|
|
289
|
+
},
|
|
290
|
+
"gpt-4-0125-preview": {
|
|
291
|
+
"promptPrice": 0.01,
|
|
292
|
+
"completionPrice": 0.03
|
|
293
|
+
},
|
|
294
|
+
"gpt-4-preview": {
|
|
295
|
+
"promptPrice": 0.01,
|
|
296
|
+
"completionPrice": 0.03
|
|
297
|
+
},
|
|
298
|
+
"gpt-4-1106-vision-preview": {
|
|
299
|
+
"promptPrice": 0.01,
|
|
300
|
+
"completionPrice": 0.03
|
|
301
|
+
},
|
|
302
|
+
"gpt-4-vision-preview": {
|
|
303
|
+
"promptPrice": 0.01,
|
|
304
|
+
"completionPrice": 0.03
|
|
305
|
+
},
|
|
306
|
+
"azure_gpt-4": {
|
|
307
|
+
"promptPrice": 0.03,
|
|
308
|
+
"completionPrice": 0.06
|
|
309
|
+
},
|
|
310
|
+
"azure_gpt-4-32k": {
|
|
311
|
+
"promptPrice": 0.06,
|
|
312
|
+
"completionPrice": 0.12
|
|
313
|
+
},
|
|
314
|
+
"claude-3-opus-20240229": {
|
|
315
|
+
"promptPrice": 0.015,
|
|
316
|
+
"completionPrice": 0.075
|
|
317
|
+
},
|
|
318
|
+
"claude-4-opus": {
|
|
319
|
+
"promptPrice": 0.015,
|
|
320
|
+
"completionPrice": 0.075
|
|
321
|
+
},
|
|
322
|
+
"claude-opus-4": {
|
|
323
|
+
"promptPrice": 0.015,
|
|
324
|
+
"completionPrice": 0.075
|
|
325
|
+
},
|
|
326
|
+
"claude-opus-4-1": {
|
|
327
|
+
"promptPrice": 0.015,
|
|
328
|
+
"completionPrice": 0.075
|
|
329
|
+
},
|
|
330
|
+
"claude-opus-4.1": {
|
|
331
|
+
"promptPrice": 0.015,
|
|
332
|
+
"completionPrice": 0.075
|
|
333
|
+
},
|
|
334
|
+
"claude-3-sonnet-20240229": {
|
|
335
|
+
"promptPrice": 0.003,
|
|
336
|
+
"completionPrice": 0.015
|
|
337
|
+
},
|
|
338
|
+
"claude-3-haiku-20240307": {
|
|
339
|
+
"promptPrice": 0.00025,
|
|
340
|
+
"completionPrice": 0.00125
|
|
341
|
+
},
|
|
342
|
+
"claude-3-5-sonnet-20240620": {
|
|
343
|
+
"promptPrice": 0.003,
|
|
344
|
+
"completionPrice": 0.015
|
|
345
|
+
},
|
|
346
|
+
"claude-3-5-sonnet-20241022": {
|
|
347
|
+
"promptPrice": 0.003,
|
|
348
|
+
"completionPrice": 0.015
|
|
349
|
+
},
|
|
350
|
+
"claude-3-5-haiku-20241022": {
|
|
351
|
+
"promptPrice": 0.0008,
|
|
352
|
+
"completionPrice": 0.004
|
|
353
|
+
},
|
|
354
|
+
"claude-sonnet-4-5": {
|
|
355
|
+
"promptPrice": 0.003,
|
|
356
|
+
"completionPrice": 0.015
|
|
357
|
+
},
|
|
358
|
+
"claude-sonnet-4-5-20250929": {
|
|
359
|
+
"promptPrice": 0.003,
|
|
360
|
+
"completionPrice": 0.015
|
|
361
|
+
},
|
|
362
|
+
"claude-3-7-sonnet": {
|
|
363
|
+
"promptPrice": 0.003,
|
|
364
|
+
"completionPrice": 0.015
|
|
365
|
+
},
|
|
366
|
+
"claude-haiku-4-5": {
|
|
367
|
+
"promptPrice": 0.001,
|
|
368
|
+
"completionPrice": 0.005
|
|
369
|
+
},
|
|
370
|
+
"command": {
|
|
371
|
+
"promptPrice": 0.001,
|
|
372
|
+
"completionPrice": 0.002
|
|
373
|
+
},
|
|
374
|
+
"command-nightly": {
|
|
375
|
+
"promptPrice": 0.001,
|
|
376
|
+
"completionPrice": 0.002
|
|
377
|
+
},
|
|
378
|
+
"command-light": {
|
|
379
|
+
"promptPrice": 0.0003,
|
|
380
|
+
"completionPrice": 0.0006
|
|
381
|
+
},
|
|
382
|
+
"command-light-nightly": {
|
|
383
|
+
"promptPrice": 0.0003,
|
|
384
|
+
"completionPrice": 0.0006
|
|
385
|
+
},
|
|
386
|
+
"command-r-plus": {
|
|
387
|
+
"promptPrice": 0.0025,
|
|
388
|
+
"completionPrice": 0.01
|
|
389
|
+
},
|
|
390
|
+
"command-r+": {
|
|
391
|
+
"promptPrice": 0.0025,
|
|
392
|
+
"completionPrice": 0.01
|
|
393
|
+
},
|
|
394
|
+
"command-r": {
|
|
395
|
+
"promptPrice": 0.00015,
|
|
396
|
+
"completionPrice": 0.0006
|
|
397
|
+
},
|
|
398
|
+
"command-r7b": {
|
|
399
|
+
"promptPrice": 3.75e-05,
|
|
400
|
+
"completionPrice": 0.00015
|
|
401
|
+
},
|
|
402
|
+
"command-a": {
|
|
403
|
+
"promptPrice": 0.0025,
|
|
404
|
+
"completionPrice": 0.01
|
|
405
|
+
},
|
|
406
|
+
"open-mistral-7b": {
|
|
407
|
+
"promptPrice": 0.00025,
|
|
408
|
+
"completionPrice": 0.00025
|
|
409
|
+
},
|
|
410
|
+
"open-mixtral-8x7b": {
|
|
411
|
+
"promptPrice": 0.0007,
|
|
412
|
+
"completionPrice": 0.0007
|
|
413
|
+
},
|
|
414
|
+
"mistral-small-latest": {
|
|
415
|
+
"promptPrice": 0.002,
|
|
416
|
+
"completionPrice": 0.006
|
|
417
|
+
},
|
|
418
|
+
"mistral-medium-latest": {
|
|
419
|
+
"promptPrice": 0.0027,
|
|
420
|
+
"completionPrice": 0.0081
|
|
421
|
+
},
|
|
422
|
+
"mistral-large-latest": {
|
|
423
|
+
"promptPrice": 0.008,
|
|
424
|
+
"completionPrice": 0.024
|
|
425
|
+
},
|
|
426
|
+
"amazon.titan-text-express-v1": {
|
|
427
|
+
"promptPrice": 0.0008,
|
|
428
|
+
"completionPrice": 0.0016
|
|
429
|
+
},
|
|
430
|
+
"amazon.titan-text-lite-v1": {
|
|
431
|
+
"promptPrice": 0.0003,
|
|
432
|
+
"completionPrice": 0.0004
|
|
433
|
+
},
|
|
434
|
+
"mistral.mistral-7b-instruct-v0:2": {
|
|
435
|
+
"promptPrice": 0.00015,
|
|
436
|
+
"completionPrice": 0.0002
|
|
437
|
+
},
|
|
438
|
+
"mistral.mixtral-8x7b-instruct-v0:1": {
|
|
439
|
+
"promptPrice": 0.00045,
|
|
440
|
+
"completionPrice": 0.0007
|
|
441
|
+
},
|
|
442
|
+
"mistral.mistral-large-2402-v1:0": {
|
|
443
|
+
"promptPrice": 0.008,
|
|
444
|
+
"completionPrice": 0.024
|
|
445
|
+
},
|
|
446
|
+
"anthropic.claude-3-haiku-20240307-v1:0": {
|
|
447
|
+
"promptPrice": 0.00025,
|
|
448
|
+
"completionPrice": 0.00125
|
|
449
|
+
},
|
|
450
|
+
"anthropic.claude-v2": {
|
|
451
|
+
"promptPrice": 0.008,
|
|
452
|
+
"completionPrice": 0.024
|
|
453
|
+
},
|
|
454
|
+
"anthropic.claude-3-sonnet-20240229-v1:0": {
|
|
455
|
+
"promptPrice": 0.003,
|
|
456
|
+
"completionPrice": 0.015
|
|
457
|
+
},
|
|
458
|
+
"anthropic.claude-3-opus-20240229-v1:0": {
|
|
459
|
+
"promptPrice": 0.015,
|
|
460
|
+
"completionPrice": 0.075
|
|
461
|
+
},
|
|
462
|
+
"meta.llama3-8b-instruct-v1:0": {
|
|
463
|
+
"promptPrice": 0.0004,
|
|
464
|
+
"completionPrice": 0.0006
|
|
465
|
+
},
|
|
466
|
+
"meta.llama3-70b-instruct-v1:0": {
|
|
467
|
+
"promptPrice": 0.00265,
|
|
468
|
+
"completionPrice": 0.0035
|
|
469
|
+
},
|
|
470
|
+
"meta.llama2-13b-chat-v1": {
|
|
471
|
+
"promptPrice": 0.00075,
|
|
472
|
+
"completionPrice": 0.001
|
|
473
|
+
},
|
|
474
|
+
"meta.llama2-70b-chat-v1": {
|
|
475
|
+
"promptPrice": 0.00195,
|
|
476
|
+
"completionPrice": 0.00256
|
|
477
|
+
},
|
|
478
|
+
"cohere.command-text-v14": {
|
|
479
|
+
"promptPrice": 0.0015,
|
|
480
|
+
"completionPrice": 0.002
|
|
481
|
+
},
|
|
482
|
+
"cohere.command-light-text-v14": {
|
|
483
|
+
"promptPrice": 0.0003,
|
|
484
|
+
"completionPrice": 0.0006
|
|
485
|
+
},
|
|
486
|
+
"ai21.j2-mid-v1": {
|
|
487
|
+
"promptPrice": 0.0125,
|
|
488
|
+
"completionPrice": 0.0125
|
|
489
|
+
},
|
|
490
|
+
"ai21.j2-ultra-v1": {
|
|
491
|
+
"promptPrice": 0.0188,
|
|
492
|
+
"completionPrice": 0.0188
|
|
493
|
+
},
|
|
494
|
+
"gemini-1.0-pro": {
|
|
495
|
+
"promptPrice": 0.0005,
|
|
496
|
+
"completionPrice": 0.0015
|
|
497
|
+
},
|
|
498
|
+
"gemini-1.5-flash": {
|
|
499
|
+
"promptPrice": 7.5e-05,
|
|
500
|
+
"completionPrice": 0.0003
|
|
501
|
+
},
|
|
502
|
+
"gemini-1.5-pro": {
|
|
503
|
+
"promptPrice": 0.00125,
|
|
504
|
+
"completionPrice": 0.005
|
|
505
|
+
},
|
|
506
|
+
"gemini-1.0-pro-002": {
|
|
507
|
+
"promptPrice": 0.0005,
|
|
508
|
+
"completionPrice": 0.0015
|
|
509
|
+
},
|
|
510
|
+
"gemini-1.0-pro-001": {
|
|
511
|
+
"promptPrice": 0.0005,
|
|
512
|
+
"completionPrice": 0.0015
|
|
513
|
+
},
|
|
514
|
+
"gemini-1.5-pro-preview-0409": {
|
|
515
|
+
"promptPrice": 0.005,
|
|
516
|
+
"completionPrice": 0.015
|
|
517
|
+
},
|
|
518
|
+
"gemini-1.5-pro-preview-0514": {
|
|
519
|
+
"promptPrice": 0.005,
|
|
520
|
+
"completionPrice": 0.015
|
|
521
|
+
},
|
|
522
|
+
"gemini-1.5-flash-preview-0514": {
|
|
523
|
+
"promptPrice": 0.0005,
|
|
524
|
+
"completionPrice": 0.0015
|
|
525
|
+
},
|
|
526
|
+
"gemini-2.0-flash": {
|
|
527
|
+
"promptPrice": 0.0001,
|
|
528
|
+
"completionPrice": 0.0004
|
|
529
|
+
},
|
|
530
|
+
"gemini-2.0-flash-lite": {
|
|
531
|
+
"promptPrice": 7.5e-05,
|
|
532
|
+
"completionPrice": 0.0003
|
|
533
|
+
},
|
|
534
|
+
"gemini-2.5-flash": {
|
|
535
|
+
"promptPrice": 0.0003,
|
|
536
|
+
"completionPrice": 0.0025
|
|
537
|
+
},
|
|
538
|
+
"gemini-2.5-flash-preview": {
|
|
539
|
+
"promptPrice": 0.0003,
|
|
540
|
+
"completionPrice": 0.0025
|
|
541
|
+
},
|
|
542
|
+
"gemini-2.5-flash-lite": {
|
|
543
|
+
"promptPrice": 0.0001,
|
|
544
|
+
"completionPrice": 0.0004
|
|
545
|
+
},
|
|
546
|
+
"gemini-2.5-flash-lite-preview": {
|
|
547
|
+
"promptPrice": 0.0001,
|
|
548
|
+
"completionPrice": 0.0004
|
|
549
|
+
},
|
|
550
|
+
"gemini-2.5-pro": {
|
|
551
|
+
"promptPrice": 0.00125,
|
|
552
|
+
"completionPrice": 0.01
|
|
553
|
+
},
|
|
554
|
+
"gemini-2-5-flash-image": {
|
|
555
|
+
"promptPrice": 0.0003,
|
|
556
|
+
"completionPrice": 0.03
|
|
557
|
+
},
|
|
558
|
+
"nano-banana": {
|
|
559
|
+
"promptPrice": 0.0003,
|
|
560
|
+
"completionPrice": 0.03
|
|
561
|
+
},
|
|
562
|
+
"text-bison": {
|
|
563
|
+
"promptPrice": 0.001,
|
|
564
|
+
"completionPrice": 0.002
|
|
565
|
+
},
|
|
566
|
+
"text-bison@002": {
|
|
567
|
+
"promptPrice": 0.001,
|
|
568
|
+
"completionPrice": 0.002
|
|
569
|
+
},
|
|
570
|
+
"text-bison-32k": {
|
|
571
|
+
"promptPrice": 0.001,
|
|
572
|
+
"completionPrice": 0.002
|
|
573
|
+
},
|
|
574
|
+
"text-bison-32k@002": {
|
|
575
|
+
"promptPrice": 0.001,
|
|
576
|
+
"completionPrice": 0.002
|
|
577
|
+
},
|
|
578
|
+
"text-unicorn": {
|
|
579
|
+
"promptPrice": 0.01,
|
|
580
|
+
"completionPrice": 0.03
|
|
581
|
+
},
|
|
582
|
+
"text-unicorn@001": {
|
|
583
|
+
"promptPrice": 0.01,
|
|
584
|
+
"completionPrice": 0.03
|
|
585
|
+
},
|
|
586
|
+
"chat-bison": {
|
|
587
|
+
"promptPrice": 0.001,
|
|
588
|
+
"completionPrice": 0.002
|
|
589
|
+
},
|
|
590
|
+
"chat-bison@002": {
|
|
591
|
+
"promptPrice": 0.001,
|
|
592
|
+
"completionPrice": 0.002
|
|
593
|
+
},
|
|
594
|
+
"chat-bison-32k": {
|
|
595
|
+
"promptPrice": 0.001,
|
|
596
|
+
"completionPrice": 0.002
|
|
597
|
+
},
|
|
598
|
+
"chat-bison-32k@002": {
|
|
599
|
+
"promptPrice": 0.001,
|
|
600
|
+
"completionPrice": 0.002
|
|
601
|
+
},
|
|
602
|
+
"llama3-8b-8192": {
|
|
603
|
+
"promptPrice": 5e-05,
|
|
604
|
+
"completionPrice": 0.0001
|
|
605
|
+
},
|
|
606
|
+
"llama3-70b-8192": {
|
|
607
|
+
"promptPrice": 0.00059,
|
|
608
|
+
"completionPrice": 0.00079
|
|
609
|
+
},
|
|
610
|
+
"mixtral-8x7b-32768": {
|
|
611
|
+
"promptPrice": 0.00024,
|
|
612
|
+
"completionPrice": 0.00024
|
|
613
|
+
},
|
|
614
|
+
"gemma-7b-it": {
|
|
615
|
+
"promptPrice": 0.0001,
|
|
616
|
+
"completionPrice": 0.0001
|
|
617
|
+
},
|
|
618
|
+
"reka-core": {
|
|
619
|
+
"promptPrice": 0.002,
|
|
620
|
+
"completionPrice": 0.002
|
|
621
|
+
},
|
|
622
|
+
"reka-core-20240415": {
|
|
623
|
+
"promptPrice": 0.002,
|
|
624
|
+
"completionPrice": 0.002
|
|
625
|
+
},
|
|
626
|
+
"reka-core-20240501": {
|
|
627
|
+
"promptPrice": 0.002,
|
|
628
|
+
"completionPrice": 0.002
|
|
629
|
+
},
|
|
630
|
+
"reka-flash": {
|
|
631
|
+
"promptPrice": 0.0002,
|
|
632
|
+
"completionPrice": 0.0008
|
|
633
|
+
},
|
|
634
|
+
"reka-flash-20240226": {
|
|
635
|
+
"promptPrice": 0.0002,
|
|
636
|
+
"completionPrice": 0.0008
|
|
637
|
+
},
|
|
638
|
+
"reka-edge": {
|
|
639
|
+
"promptPrice": 0.0001,
|
|
640
|
+
"completionPrice": 0.0001
|
|
641
|
+
},
|
|
642
|
+
"reka-edge-20240208": {
|
|
643
|
+
"promptPrice": 0.0001,
|
|
644
|
+
"completionPrice": 0.0001
|
|
645
|
+
},
|
|
646
|
+
"reka-spark": {
|
|
647
|
+
"promptPrice": 5e-05,
|
|
648
|
+
"completionPrice": 5e-05
|
|
649
|
+
},
|
|
650
|
+
"grok-beta": {
|
|
651
|
+
"promptPrice": 0.0005,
|
|
652
|
+
"completionPrice": 0.0015
|
|
653
|
+
},
|
|
654
|
+
"grok-vision-beta": {
|
|
655
|
+
"promptPrice": 0.0005,
|
|
656
|
+
"completionPrice": 0.0015
|
|
657
|
+
},
|
|
658
|
+
"grok-2-1212": {
|
|
659
|
+
"promptPrice": 0.002,
|
|
660
|
+
"completionPrice": 0.01
|
|
661
|
+
},
|
|
662
|
+
"grok-2-vision-1212": {
|
|
663
|
+
"promptPrice": 0.002,
|
|
664
|
+
"completionPrice": 0.01
|
|
665
|
+
},
|
|
666
|
+
"grok-3": {
|
|
667
|
+
"promptPrice": 0.003,
|
|
668
|
+
"completionPrice": 0.015
|
|
669
|
+
},
|
|
670
|
+
"grok-3-mini": {
|
|
671
|
+
"promptPrice": 0.0003,
|
|
672
|
+
"completionPrice": 0.0005
|
|
673
|
+
},
|
|
674
|
+
"grok-3-fast": {
|
|
675
|
+
"promptPrice": 0.005,
|
|
676
|
+
"completionPrice": 0.025
|
|
677
|
+
},
|
|
678
|
+
"grok-3-mini-fast": {
|
|
679
|
+
"promptPrice": 0.0006,
|
|
680
|
+
"completionPrice": 0.004
|
|
681
|
+
},
|
|
682
|
+
"grok-4": {
|
|
683
|
+
"promptPrice": 0.003,
|
|
684
|
+
"completionPrice": 0.015
|
|
685
|
+
},
|
|
686
|
+
"grok-4-fast": {
|
|
687
|
+
"promptPrice": 0.0002,
|
|
688
|
+
"completionPrice": 0.0005
|
|
689
|
+
},
|
|
690
|
+
"jamba-1.5-mini": {
|
|
691
|
+
"promptPrice": 0.0002,
|
|
692
|
+
"completionPrice": 0.0004
|
|
693
|
+
},
|
|
694
|
+
"jamba-1.5-large": {
|
|
695
|
+
"promptPrice": 0.002,
|
|
696
|
+
"completionPrice": 0.008
|
|
697
|
+
},
|
|
698
|
+
"meta-llama/Llama-3.3-70B-Instruct-Turbo": {
|
|
699
|
+
"promptPrice": 0.00088,
|
|
700
|
+
"completionPrice": 0.00088
|
|
701
|
+
},
|
|
702
|
+
"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo-vLLM-json": {
|
|
703
|
+
"promptPrice": 0.00088,
|
|
704
|
+
"completionPrice": 0.00088
|
|
705
|
+
},
|
|
706
|
+
"meta-llama/Meta-Llama-3.1-405B-Instruct-Lite-Pro-lora": {
|
|
707
|
+
"promptPrice": 0.00088,
|
|
708
|
+
"completionPrice": 0.00088
|
|
709
|
+
},
|
|
710
|
+
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
|
|
711
|
+
"promptPrice": 0.00088,
|
|
712
|
+
"completionPrice": 0.00088
|
|
713
|
+
},
|
|
714
|
+
"Qwen/QwQ-32B-Preview": {
|
|
715
|
+
"promptPrice": 0.0012,
|
|
716
|
+
"completionPrice": 0.0012
|
|
717
|
+
},
|
|
718
|
+
"qwen3-next-80b-a3b-instruct": {
|
|
719
|
+
"promptPrice": 0.000525,
|
|
720
|
+
"completionPrice": 0.0021
|
|
721
|
+
},
|
|
722
|
+
"qwen3-next-80b-a3b-thinking": {
|
|
723
|
+
"promptPrice": 0.000525,
|
|
724
|
+
"completionPrice": 0.0063
|
|
725
|
+
},
|
|
726
|
+
"qwen3-coder-480b-a35b-instruct": {
|
|
727
|
+
"promptPrice": 0.001,
|
|
728
|
+
"completionPrice": 0.005
|
|
729
|
+
},
|
|
730
|
+
"qwen3-max": {
|
|
731
|
+
"promptPrice": 0.0012,
|
|
732
|
+
"completionPrice": 0.006
|
|
733
|
+
},
|
|
734
|
+
"qwen-qwen3-max": {
|
|
735
|
+
"promptPrice": 0.0012,
|
|
736
|
+
"completionPrice": 0.006
|
|
737
|
+
},
|
|
738
|
+
"codellama/CodeLlama-34b-Instruct-hf": {
|
|
739
|
+
"promptPrice": 0.0008,
|
|
740
|
+
"completionPrice": 0.0008
|
|
741
|
+
},
|
|
742
|
+
"databricks/dbrx-instruct": {
|
|
743
|
+
"promptPrice": 0.0012,
|
|
744
|
+
"completionPrice": 0.0012
|
|
745
|
+
},
|
|
746
|
+
"deepseek-ai/deepseek-llm-67b-chat": {
|
|
747
|
+
"promptPrice": 0.0009,
|
|
748
|
+
"completionPrice": 0.0009
|
|
749
|
+
},
|
|
750
|
+
"google/gemma-2b-it": {
|
|
751
|
+
"promptPrice": 0.0001,
|
|
752
|
+
"completionPrice": 0.0001
|
|
753
|
+
},
|
|
754
|
+
"google/gemma-2-27b-it": {
|
|
755
|
+
"promptPrice": 0.0008,
|
|
756
|
+
"completionPrice": 0.0008
|
|
757
|
+
},
|
|
758
|
+
"google/gemma-2-9b-it": {
|
|
759
|
+
"promptPrice": 0.0003,
|
|
760
|
+
"completionPrice": 0.0003
|
|
761
|
+
},
|
|
762
|
+
"Gryphe/MythoMax-L2-13b-Lite": {
|
|
763
|
+
"promptPrice": 0.0003,
|
|
764
|
+
"completionPrice": 0.0003
|
|
765
|
+
},
|
|
766
|
+
"nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
|
|
767
|
+
"promptPrice": 0.0088,
|
|
768
|
+
"completionPrice": 0.0088
|
|
769
|
+
},
|
|
770
|
+
"deepseek-chat": {
|
|
771
|
+
"promptPrice": 0.00014,
|
|
772
|
+
"completionPrice": 0.00028
|
|
773
|
+
},
|
|
774
|
+
"deepseek-reasoner": {
|
|
775
|
+
"promptPrice": 0.00055,
|
|
776
|
+
"completionPrice": 0.00219
|
|
777
|
+
},
|
|
778
|
+
"llama-3.1-8b-instant": {
|
|
779
|
+
"promptPrice": 5e-05,
|
|
780
|
+
"completionPrice": 8e-05
|
|
781
|
+
},
|
|
782
|
+
"llama-3.3-70b-versatile": {
|
|
783
|
+
"promptPrice": 0.00059,
|
|
784
|
+
"completionPrice": 0.00079
|
|
785
|
+
},
|
|
786
|
+
"llama-4-scout": {
|
|
787
|
+
"promptPrice": 0.00015,
|
|
788
|
+
"completionPrice": 0.0005
|
|
789
|
+
},
|
|
790
|
+
"llama-4-scout-17bx16e-128k": {
|
|
791
|
+
"promptPrice": 0.00015,
|
|
792
|
+
"completionPrice": 0.0005
|
|
793
|
+
},
|
|
794
|
+
"llama-4-maverick": {
|
|
795
|
+
"promptPrice": 0.00022,
|
|
796
|
+
"completionPrice": 0.00085
|
|
797
|
+
},
|
|
798
|
+
"llama-4-maverick-17bx128e-128k": {
|
|
799
|
+
"promptPrice": 0.00022,
|
|
800
|
+
"completionPrice": 0.00085
|
|
801
|
+
},
|
|
802
|
+
"meta-llama/Llama-4-Scout": {
|
|
803
|
+
"promptPrice": 0.00018,
|
|
804
|
+
"completionPrice": 0.00059
|
|
805
|
+
},
|
|
806
|
+
"meta-llama/Llama-4-Maverick": {
|
|
807
|
+
"promptPrice": 0.00027,
|
|
808
|
+
"completionPrice": 0.00085
|
|
809
|
+
},
|
|
810
|
+
"llama-guard-4-12b": {
|
|
811
|
+
"promptPrice": 0.0002,
|
|
812
|
+
"completionPrice": 0.0002
|
|
813
|
+
},
|
|
814
|
+
"qwen3-32b": {
|
|
815
|
+
"promptPrice": 0.00029,
|
|
816
|
+
"completionPrice": 0.00059
|
|
817
|
+
},
|
|
818
|
+
"gpt-oss-20b": {
|
|
819
|
+
"promptPrice": 7.5e-05,
|
|
820
|
+
"completionPrice": 0.0003
|
|
821
|
+
},
|
|
822
|
+
"gpt-oss-120b": {
|
|
823
|
+
"promptPrice": 0.00015,
|
|
824
|
+
"completionPrice": 0.0006
|
|
825
|
+
},
|
|
826
|
+
"kimi-k2-0905": {
|
|
827
|
+
"promptPrice": 0.001,
|
|
828
|
+
"completionPrice": 0.003
|
|
829
|
+
},
|
|
830
|
+
"meta-llama/Llama-3.2-3B-Instruct-Turbo": {
|
|
831
|
+
"promptPrice": 6e-05,
|
|
832
|
+
"completionPrice": 6e-05
|
|
833
|
+
},
|
|
834
|
+
"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": {
|
|
835
|
+
"promptPrice": 0.00018,
|
|
836
|
+
"completionPrice": 0.00018
|
|
837
|
+
},
|
|
838
|
+
"meta-llama/Llama-3-8B-Instruct-Lite": {
|
|
839
|
+
"promptPrice": 0.0001,
|
|
840
|
+
"completionPrice": 0.0001
|
|
841
|
+
},
|
|
842
|
+
"DeepSeek-R1": {
|
|
843
|
+
"promptPrice": 0.003,
|
|
844
|
+
"completionPrice": 0.007
|
|
845
|
+
},
|
|
846
|
+
"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
|
|
847
|
+
"promptPrice": 0.00018,
|
|
848
|
+
"completionPrice": 0.00018
|
|
849
|
+
},
|
|
850
|
+
"deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
|
|
851
|
+
"promptPrice": 0.002,
|
|
852
|
+
"completionPrice": 0.002
|
|
853
|
+
},
|
|
854
|
+
"deepseek-ai/DeepSeek-V3": {
|
|
855
|
+
"promptPrice": 0.00125,
|
|
856
|
+
"completionPrice": 0.00125
|
|
857
|
+
},
|
|
858
|
+
"deepseek-ai/DeepSeek-V3-1": {
|
|
859
|
+
"promptPrice": 0.0006,
|
|
860
|
+
"completionPrice": 0.0017
|
|
861
|
+
},
|
|
862
|
+
"Qwen/Qwen3-235B-A22B-Instruct-2507-FP8": {
|
|
863
|
+
"promptPrice": 0.0002,
|
|
864
|
+
"completionPrice": 0.0006
|
|
865
|
+
},
|
|
866
|
+
"Qwen/Qwen3-235B-A22B-Thinking-2507-FP8": {
|
|
867
|
+
"promptPrice": 0.00065,
|
|
868
|
+
"completionPrice": 0.003
|
|
869
|
+
},
|
|
870
|
+
"Qwen/Qwen2.5-72B-Instruct": {
|
|
871
|
+
"promptPrice": 0.0012,
|
|
872
|
+
"completionPrice": 0.0012
|
|
873
|
+
},
|
|
874
|
+
"Qwen/Qwen2.5-Coder-32B-Instruct": {
|
|
875
|
+
"promptPrice": 0.0008,
|
|
876
|
+
"completionPrice": 0.0008
|
|
877
|
+
},
|
|
878
|
+
"Qwen/Qwen2.5-7B-Instruct-Turbo": {
|
|
879
|
+
"promptPrice": 0.0003,
|
|
880
|
+
"completionPrice": 0.0003
|
|
881
|
+
},
|
|
882
|
+
"mistralai/Mistral-7B-Instruct-v0.2": {
|
|
883
|
+
"promptPrice": 0.0002,
|
|
884
|
+
"completionPrice": 0.0002
|
|
885
|
+
},
|
|
886
|
+
"mistralai/Mistral-Small-3": {
|
|
887
|
+
"promptPrice": 0.0008,
|
|
888
|
+
"completionPrice": 0.0008
|
|
889
|
+
},
|
|
890
|
+
"mistralai/Mixtral-8x7B-Instruct-v0.1": {
|
|
891
|
+
"promptPrice": 0.0006,
|
|
892
|
+
"completionPrice": 0.0006
|
|
893
|
+
},
|
|
894
|
+
"THUDM/GLM-4.5-Air": {
|
|
895
|
+
"promptPrice": 0.0002,
|
|
896
|
+
"completionPrice": 0.0011
|
|
897
|
+
},
|
|
898
|
+
"Kimi-K2-Instruct": {
|
|
899
|
+
"promptPrice": 0.001,
|
|
900
|
+
"completionPrice": 0.003
|
|
901
|
+
},
|
|
902
|
+
"smollm2:135m": {
|
|
903
|
+
"promptPrice": 0.0001,
|
|
904
|
+
"completionPrice": 0.0002
|
|
905
|
+
},
|
|
906
|
+
"smollm2:360m": {
|
|
907
|
+
"promptPrice": 0.0001,
|
|
908
|
+
"completionPrice": 0.0002
|
|
909
|
+
},
|
|
910
|
+
"tinyllama": {
|
|
911
|
+
"promptPrice": 0.0003,
|
|
912
|
+
"completionPrice": 0.0006
|
|
913
|
+
},
|
|
914
|
+
"llama3.2:1b": {
|
|
915
|
+
"promptPrice": 0.0003,
|
|
916
|
+
"completionPrice": 0.0006
|
|
917
|
+
},
|
|
918
|
+
"llama3.2:3b": {
|
|
919
|
+
"promptPrice": 0.0003,
|
|
920
|
+
"completionPrice": 0.0006
|
|
921
|
+
},
|
|
922
|
+
"gemma:2b": {
|
|
923
|
+
"promptPrice": 0.0003,
|
|
924
|
+
"completionPrice": 0.0006
|
|
925
|
+
},
|
|
926
|
+
"gemma2:2b": {
|
|
927
|
+
"promptPrice": 0.0003,
|
|
928
|
+
"completionPrice": 0.0006
|
|
929
|
+
},
|
|
930
|
+
"phi3:3.8b": {
|
|
931
|
+
"promptPrice": 0.0003,
|
|
932
|
+
"completionPrice": 0.0006
|
|
933
|
+
},
|
|
934
|
+
"phi4:14b": {
|
|
935
|
+
"promptPrice": 0.0005,
|
|
936
|
+
"completionPrice": 0.001
|
|
937
|
+
},
|
|
938
|
+
"qwen2.5:0.5b": {
|
|
939
|
+
"promptPrice": 0.0001,
|
|
940
|
+
"completionPrice": 0.0002
|
|
941
|
+
},
|
|
942
|
+
"qwen2.5:1.5b": {
|
|
943
|
+
"promptPrice": 0.0003,
|
|
944
|
+
"completionPrice": 0.0006
|
|
945
|
+
},
|
|
946
|
+
"qwen2.5:3b": {
|
|
947
|
+
"promptPrice": 0.0003,
|
|
948
|
+
"completionPrice": 0.0006
|
|
949
|
+
},
|
|
950
|
+
"qwen2.5:7b": {
|
|
951
|
+
"promptPrice": 0.0003,
|
|
952
|
+
"completionPrice": 0.0006
|
|
953
|
+
},
|
|
954
|
+
"qwen3:4b": {
|
|
955
|
+
"promptPrice": 0.0003,
|
|
956
|
+
"completionPrice": 0.0006
|
|
957
|
+
},
|
|
958
|
+
"qwen3:8b": {
|
|
959
|
+
"promptPrice": 0.0003,
|
|
960
|
+
"completionPrice": 0.0006
|
|
961
|
+
},
|
|
962
|
+
"llama2:7b": {
|
|
963
|
+
"promptPrice": 0.0003,
|
|
964
|
+
"completionPrice": 0.0006
|
|
965
|
+
},
|
|
966
|
+
"llama3:8b": {
|
|
967
|
+
"promptPrice": 0.0003,
|
|
968
|
+
"completionPrice": 0.0006
|
|
969
|
+
},
|
|
970
|
+
"llama3.1:8b": {
|
|
971
|
+
"promptPrice": 0.0003,
|
|
972
|
+
"completionPrice": 0.0006
|
|
973
|
+
},
|
|
974
|
+
"mistral:7b": {
|
|
975
|
+
"promptPrice": 0.0003,
|
|
976
|
+
"completionPrice": 0.0006
|
|
977
|
+
},
|
|
978
|
+
"gemma:7b": {
|
|
979
|
+
"promptPrice": 0.0003,
|
|
980
|
+
"completionPrice": 0.0006
|
|
981
|
+
},
|
|
982
|
+
"gemma2:9b": {
|
|
983
|
+
"promptPrice": 0.0003,
|
|
984
|
+
"completionPrice": 0.0006
|
|
985
|
+
},
|
|
986
|
+
"codellama:7b": {
|
|
987
|
+
"promptPrice": 0.0003,
|
|
988
|
+
"completionPrice": 0.0006
|
|
989
|
+
},
|
|
990
|
+
"llama2:13b": {
|
|
991
|
+
"promptPrice": 0.0005,
|
|
992
|
+
"completionPrice": 0.001
|
|
993
|
+
},
|
|
994
|
+
"codellama:13b": {
|
|
995
|
+
"promptPrice": 0.0005,
|
|
996
|
+
"completionPrice": 0.001
|
|
997
|
+
},
|
|
998
|
+
"llama2:70b": {
|
|
999
|
+
"promptPrice": 0.0008,
|
|
1000
|
+
"completionPrice": 0.0008
|
|
1001
|
+
},
|
|
1002
|
+
"llama3:70b": {
|
|
1003
|
+
"promptPrice": 0.0008,
|
|
1004
|
+
"completionPrice": 0.0008
|
|
1005
|
+
},
|
|
1006
|
+
"llama3.1:70b": {
|
|
1007
|
+
"promptPrice": 0.0008,
|
|
1008
|
+
"completionPrice": 0.0008
|
|
1009
|
+
},
|
|
1010
|
+
"qwen2.5:72b": {
|
|
1011
|
+
"promptPrice": 0.0008,
|
|
1012
|
+
"completionPrice": 0.0008
|
|
1013
|
+
},
|
|
1014
|
+
"codellama:34b": {
|
|
1015
|
+
"promptPrice": 0.0008,
|
|
1016
|
+
"completionPrice": 0.0008
|
|
1017
|
+
},
|
|
1018
|
+
"mixtral:8x7b": {
|
|
1019
|
+
"promptPrice": 0.0008,
|
|
1020
|
+
"completionPrice": 0.0008
|
|
1021
|
+
},
|
|
1022
|
+
"deepseek-r1:7b": {
|
|
1023
|
+
"promptPrice": 0.0003,
|
|
1024
|
+
"completionPrice": 0.0006
|
|
1025
|
+
},
|
|
1026
|
+
"deepseek-r1:14b": {
|
|
1027
|
+
"promptPrice": 0.0005,
|
|
1028
|
+
"completionPrice": 0.001
|
|
1029
|
+
},
|
|
1030
|
+
"deepseek-r1:32b": {
|
|
1031
|
+
"promptPrice": 0.0008,
|
|
1032
|
+
"completionPrice": 0.0008
|
|
1033
|
+
},
|
|
1034
|
+
"deepseek-r1:70b": {
|
|
1035
|
+
"promptPrice": 0.0008,
|
|
1036
|
+
"completionPrice": 0.0008
|
|
1037
|
+
},
|
|
1038
|
+
"ibm-granite-3-1-8b-instruct": {
|
|
1039
|
+
"promptPrice": 0.0002,
|
|
1040
|
+
"completionPrice": 0.0002
|
|
1041
|
+
},
|
|
1042
|
+
"ibm-granite-3-8b-instruct": {
|
|
1043
|
+
"promptPrice": 0.0002,
|
|
1044
|
+
"completionPrice": 0.0002
|
|
1045
|
+
},
|
|
1046
|
+
"granite-3-8b-instruct": {
|
|
1047
|
+
"promptPrice": 0.0002,
|
|
1048
|
+
"completionPrice": 0.0002
|
|
1049
|
+
},
|
|
1050
|
+
"granite-embedding-107m-multilingual": {
|
|
1051
|
+
"promptPrice": 0.0001,
|
|
1052
|
+
"completionPrice": 0.0001
|
|
1053
|
+
},
|
|
1054
|
+
"granite-embedding-278m-multilingual": {
|
|
1055
|
+
"promptPrice": 0.0001,
|
|
1056
|
+
"completionPrice": 0.0001
|
|
1057
|
+
},
|
|
1058
|
+
"deepseek-v3.1": {
|
|
1059
|
+
"promptPrice": 0.00056,
|
|
1060
|
+
"completionPrice": 0.00168
|
|
1061
|
+
},
|
|
1062
|
+
"sarvam-m": {
|
|
1063
|
+
"promptPrice": 0,
|
|
1064
|
+
"completionPrice": 0
|
|
1065
|
+
},
|
|
1066
|
+
"sarvamai/sarvam-m": {
|
|
1067
|
+
"promptPrice": 0,
|
|
1068
|
+
"completionPrice": 0
|
|
1069
|
+
},
|
|
1070
|
+
"sarvam-chat": {
|
|
1071
|
+
"promptPrice": 0,
|
|
1072
|
+
"completionPrice": 0
|
|
1073
|
+
},
|
|
1074
|
+
"granite-4-0-h-small": {
|
|
1075
|
+
"promptPrice": 0.0002,
|
|
1076
|
+
"completionPrice": 0.0002
|
|
1077
|
+
},
|
|
1078
|
+
"granite-4-0-h-tiny": {
|
|
1079
|
+
"promptPrice": 0.0002,
|
|
1080
|
+
"completionPrice": 0.0002
|
|
1081
|
+
},
|
|
1082
|
+
"granite-4-0-h-micro": {
|
|
1083
|
+
"promptPrice": 0.0002,
|
|
1084
|
+
"completionPrice": 0.0002
|
|
1085
|
+
},
|
|
1086
|
+
"granite-4-0-micro": {
|
|
1087
|
+
"promptPrice": 0.0002,
|
|
1088
|
+
"completionPrice": 0.0002
|
|
1089
|
+
},
|
|
1090
|
+
"ibm-granite/granite-4.0-h-small": {
|
|
1091
|
+
"promptPrice": 0.0002,
|
|
1092
|
+
"completionPrice": 0.0002
|
|
1093
|
+
},
|
|
1094
|
+
"ibm-granite/granite-4.0-h-tiny": {
|
|
1095
|
+
"promptPrice": 0.0002,
|
|
1096
|
+
"completionPrice": 0.0002
|
|
1097
|
+
},
|
|
1098
|
+
"ibm-granite/granite-4.0-h-micro": {
|
|
1099
|
+
"promptPrice": 0.0002,
|
|
1100
|
+
"completionPrice": 0.0002
|
|
1101
|
+
},
|
|
1102
|
+
"granite:3b": {
|
|
1103
|
+
"promptPrice": 0.0002,
|
|
1104
|
+
"completionPrice": 0.0002
|
|
1105
|
+
},
|
|
1106
|
+
"granite:8b": {
|
|
1107
|
+
"promptPrice": 0.0002,
|
|
1108
|
+
"completionPrice": 0.0002
|
|
1109
|
+
},
|
|
1110
|
+
"mistral-large-24-11": {
|
|
1111
|
+
"promptPrice": 0.008,
|
|
1112
|
+
"completionPrice": 0.024
|
|
1113
|
+
},
|
|
1114
|
+
"mistral-large-2411": {
|
|
1115
|
+
"promptPrice": 0.008,
|
|
1116
|
+
"completionPrice": 0.024
|
|
1117
|
+
},
|
|
1118
|
+
"mistral-small-3-1": {
|
|
1119
|
+
"promptPrice": 0.001,
|
|
1120
|
+
"completionPrice": 0.003
|
|
1121
|
+
},
|
|
1122
|
+
"mistral-small-3.1": {
|
|
1123
|
+
"promptPrice": 0.001,
|
|
1124
|
+
"completionPrice": 0.003
|
|
1125
|
+
},
|
|
1126
|
+
"mistral-medium-3": {
|
|
1127
|
+
"promptPrice": 0.0004,
|
|
1128
|
+
"completionPrice": 0.002
|
|
1129
|
+
},
|
|
1130
|
+
"mistral-medium-2025": {
|
|
1131
|
+
"promptPrice": 0.0004,
|
|
1132
|
+
"completionPrice": 0.002
|
|
1133
|
+
},
|
|
1134
|
+
"magistral-small": {
|
|
1135
|
+
"promptPrice": 0.001,
|
|
1136
|
+
"completionPrice": 0.003
|
|
1137
|
+
},
|
|
1138
|
+
"magistral-medium": {
|
|
1139
|
+
"promptPrice": 0.003,
|
|
1140
|
+
"completionPrice": 0.009
|
|
1141
|
+
},
|
|
1142
|
+
"codestral-25-01": {
|
|
1143
|
+
"promptPrice": 0.001,
|
|
1144
|
+
"completionPrice": 0.003
|
|
1145
|
+
},
|
|
1146
|
+
"codestral-2501": {
|
|
1147
|
+
"promptPrice": 0.001,
|
|
1148
|
+
"completionPrice": 0.003
|
|
1149
|
+
},
|
|
1150
|
+
"lfm-7b": {
|
|
1151
|
+
"promptPrice": 0.0003,
|
|
1152
|
+
"completionPrice": 0.0006
|
|
1153
|
+
},
|
|
1154
|
+
"liquid/lfm-7b": {
|
|
1155
|
+
"promptPrice": 0.0003,
|
|
1156
|
+
"completionPrice": 0.0006
|
|
1157
|
+
},
|
|
1158
|
+
"snowflake-arctic": {
|
|
1159
|
+
"promptPrice": 0.0008,
|
|
1160
|
+
"completionPrice": 0.0024
|
|
1161
|
+
},
|
|
1162
|
+
"snowflake-arctic-instruct": {
|
|
1163
|
+
"promptPrice": 0.0008,
|
|
1164
|
+
"completionPrice": 0.0024
|
|
1165
|
+
},
|
|
1166
|
+
"snowflake/snowflake-arctic-instruct": {
|
|
1167
|
+
"promptPrice": 0.0008,
|
|
1168
|
+
"completionPrice": 0.0024
|
|
1169
|
+
},
|
|
1170
|
+
"snowflake-arctic-embed-l-v2.0": {
|
|
1171
|
+
"promptPrice": 5e-05,
|
|
1172
|
+
"completionPrice": 5e-05
|
|
1173
|
+
},
|
|
1174
|
+
"nvidia-nemotron-4-340b-instruct": {
|
|
1175
|
+
"promptPrice": 0.003,
|
|
1176
|
+
"completionPrice": 0.009
|
|
1177
|
+
},
|
|
1178
|
+
"nvidia/nemotron-4-340b-instruct": {
|
|
1179
|
+
"promptPrice": 0.003,
|
|
1180
|
+
"completionPrice": 0.009
|
|
1181
|
+
},
|
|
1182
|
+
"nvidia-nemotron-mini": {
|
|
1183
|
+
"promptPrice": 0.0002,
|
|
1184
|
+
"completionPrice": 0.0004
|
|
1185
|
+
},
|
|
1186
|
+
"nvidia/llama-3.1-nemotron-70b-instruct": {
|
|
1187
|
+
"promptPrice": 0.0008,
|
|
1188
|
+
"completionPrice": 0.0008
|
|
1189
|
+
},
|
|
1190
|
+
"servicenow-now-assist": {
|
|
1191
|
+
"promptPrice": 0.001,
|
|
1192
|
+
"completionPrice": 0.003
|
|
1193
|
+
},
|
|
1194
|
+
"llama3.1:405b": {
|
|
1195
|
+
"promptPrice": 0.0012,
|
|
1196
|
+
"completionPrice": 0.0012
|
|
1197
|
+
},
|
|
1198
|
+
"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
|
|
1199
|
+
"promptPrice": 0.0008,
|
|
1200
|
+
"completionPrice": 0.0024,
|
|
1201
|
+
"note": "R1 distilled into Qwen-32B - VERY POPULAR (1.7M downloads)"
|
|
1202
|
+
},
|
|
1203
|
+
"deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
|
|
1204
|
+
"promptPrice": 0.0002,
|
|
1205
|
+
"completionPrice": 0.0004,
|
|
1206
|
+
"note": "Tiny R1 distillation - 1M+ downloads"
|
|
1207
|
+
},
|
|
1208
|
+
"deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
|
|
1209
|
+
"promptPrice": 0.0005,
|
|
1210
|
+
"completionPrice": 0.001,
|
|
1211
|
+
"note": "R1 distilled into Llama-8B"
|
|
1212
|
+
},
|
|
1213
|
+
"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
|
|
1214
|
+
"promptPrice": 0.0004,
|
|
1215
|
+
"completionPrice": 0.0008,
|
|
1216
|
+
"note": "R1 distilled into Qwen-7B"
|
|
1217
|
+
},
|
|
1218
|
+
"deepseek-ai/DeepSeek-R1-0528": {
|
|
1219
|
+
"promptPrice": 0.0014,
|
|
1220
|
+
"completionPrice": 0.0028,
|
|
1221
|
+
"note": "Latest R1 release from May 2025"
|
|
1222
|
+
},
|
|
1223
|
+
"deepseek-ai/DeepSeek-V3.1": {
|
|
1224
|
+
"promptPrice": 0.0006,
|
|
1225
|
+
"completionPrice": 0.0017,
|
|
1226
|
+
"note": "V3.1 - improved version, similar to your existing deepseek-v3.1 entry"
|
|
1227
|
+
},
|
|
1228
|
+
"deepseek-ai/DeepSeek-V3-0324": {
|
|
1229
|
+
"promptPrice": 0.0006,
|
|
1230
|
+
"completionPrice": 0.0017,
|
|
1231
|
+
"note": "V3 March 2025 release"
|
|
1232
|
+
},
|
|
1233
|
+
"deepseek-ai/DeepSeek-R1-0528-Qwen3-8B": {
|
|
1234
|
+
"promptPrice": 0.0005,
|
|
1235
|
+
"completionPrice": 0.001,
|
|
1236
|
+
"note": "R1 based on Qwen3-8B backbone"
|
|
1237
|
+
},
|
|
1238
|
+
"deepseek-ai/DeepSeek-V3.2-Exp": {
|
|
1239
|
+
"promptPrice": 0.0008,
|
|
1240
|
+
"completionPrice": 0.002,
|
|
1241
|
+
"note": "V3.2 experimental release"
|
|
1242
|
+
},
|
|
1243
|
+
"deepseek-ai/DeepSeek-V3.1-Terminus": {
|
|
1244
|
+
"promptPrice": 0.0006,
|
|
1245
|
+
"completionPrice": 0.0017,
|
|
1246
|
+
"note": "V3.1 Terminus variant"
|
|
1247
|
+
},
|
|
1248
|
+
"deepseek-ai/DeepSeek-OCR": {
|
|
1249
|
+
"promptPrice": 0.001,
|
|
1250
|
+
"completionPrice": 0.003,
|
|
1251
|
+
"note": "HIGHEST PRIORITY - OCR specialist, 3.6M downloads - already noted in earlier analysis"
|
|
1252
|
+
},
|
|
1253
|
+
"deepseek-ai/deepseek-vl2": {
|
|
1254
|
+
"promptPrice": 0.0008,
|
|
1255
|
+
"completionPrice": 0.0024,
|
|
1256
|
+
"note": "Vision-language model v2"
|
|
1257
|
+
},
|
|
1258
|
+
"deepseek-ai/Janus-Pro-7B": {
|
|
1259
|
+
"promptPrice": 0.0008,
|
|
1260
|
+
"completionPrice": 0.0024,
|
|
1261
|
+
"note": "Multimodal any-to-any model including text-to-image"
|
|
1262
|
+
},
|
|
1263
|
+
"LiquidAI/LFM2-1.2B": {
|
|
1264
|
+
"promptPrice": 0.0002,
|
|
1265
|
+
"completionPrice": 0.0004,
|
|
1266
|
+
"note": "MOST POPULAR LiquidAI model - 506K downloads, edge-optimized"
|
|
1267
|
+
},
|
|
1268
|
+
"LiquidAI/LFM2-2.6B": {
|
|
1269
|
+
"promptPrice": 0.0003,
|
|
1270
|
+
"completionPrice": 0.0006,
|
|
1271
|
+
"note": "Larger LFM2 variant"
|
|
1272
|
+
},
|
|
1273
|
+
"LiquidAI/LFM2-350M": {
|
|
1274
|
+
"promptPrice": 0.0001,
|
|
1275
|
+
"completionPrice": 0.0002,
|
|
1276
|
+
"note": "Smallest LFM2 variant, edge-optimized"
|
|
1277
|
+
},
|
|
1278
|
+
"LiquidAI/LFM2-700M": {
|
|
1279
|
+
"promptPrice": 0.00015,
|
|
1280
|
+
"completionPrice": 0.0003,
|
|
1281
|
+
"note": "Mid-size LFM2 variant"
|
|
1282
|
+
},
|
|
1283
|
+
"LiquidAI/LFM2-8B-A1B": {
|
|
1284
|
+
"promptPrice": 0.0003,
|
|
1285
|
+
"completionPrice": 0.0009,
|
|
1286
|
+
"note": "MoE model with 8B total, 1B active parameters"
|
|
1287
|
+
},
|
|
1288
|
+
"LiquidAI/LFM2-VL-450M": {
|
|
1289
|
+
"promptPrice": 0.0002,
|
|
1290
|
+
"completionPrice": 0.0006,
|
|
1291
|
+
"note": "Vision-language 450M model"
|
|
1292
|
+
},
|
|
1293
|
+
"LiquidAI/LFM2-VL-1.6B": {
|
|
1294
|
+
"promptPrice": 0.0003,
|
|
1295
|
+
"completionPrice": 0.0009,
|
|
1296
|
+
"note": "Vision-language 1.6B model"
|
|
1297
|
+
},
|
|
1298
|
+
"LiquidAI/LFM2-VL-3B": {
|
|
1299
|
+
"promptPrice": 0.0004,
|
|
1300
|
+
"completionPrice": 0.0012,
|
|
1301
|
+
"note": "Largest LiquidAI vision model"
|
|
1302
|
+
},
|
|
1303
|
+
"HuggingFaceTB/SmolLM2-135M": {
|
|
1304
|
+
"promptPrice": 5e-05,
|
|
1305
|
+
"completionPrice": 0.0001,
|
|
1306
|
+
"note": "MOST POPULAR SmolLM - 733K downloads, tiny edge model"
|
|
1307
|
+
},
|
|
1308
|
+
"HuggingFaceTB/SmolLM2-360M-Instruct": {
|
|
1309
|
+
"promptPrice": 0.0001,
|
|
1310
|
+
"completionPrice": 0.0002,
|
|
1311
|
+
"note": "360M instruct variant - very popular"
|
|
1312
|
+
},
|
|
1313
|
+
"HuggingFaceTB/SmolLM-135M": {
|
|
1314
|
+
"promptPrice": 5e-05,
|
|
1315
|
+
"completionPrice": 0.0001,
|
|
1316
|
+
"note": "Original SmolLM v1 - 135M"
|
|
1317
|
+
},
|
|
1318
|
+
"HuggingFaceTB/SmolLM2-360M": {
|
|
1319
|
+
"promptPrice": 0.0001,
|
|
1320
|
+
"completionPrice": 0.0002,
|
|
1321
|
+
"note": "360M base model"
|
|
1322
|
+
},
|
|
1323
|
+
"HuggingFaceTB/SmolLM2-135M-Instruct": {
|
|
1324
|
+
"promptPrice": 5e-05,
|
|
1325
|
+
"completionPrice": 0.0001,
|
|
1326
|
+
"note": "135M instruct variant"
|
|
1327
|
+
},
|
|
1328
|
+
"HuggingFaceTB/SmolLM3-3B": {
|
|
1329
|
+
"promptPrice": 0.0003,
|
|
1330
|
+
"completionPrice": 0.0006,
|
|
1331
|
+
"note": "Latest SmolLM3 3B model - LARGEST in series"
|
|
1332
|
+
},
|
|
1333
|
+
"HuggingFaceTB/SmolLM2-1.7B-Instruct": {
|
|
1334
|
+
"promptPrice": 0.0002,
|
|
1335
|
+
"completionPrice": 0.0004,
|
|
1336
|
+
"note": "1.7B instruct variant"
|
|
1337
|
+
},
|
|
1338
|
+
"HuggingFaceTB/SmolLM2-1.7B": {
|
|
1339
|
+
"promptPrice": 0.0002,
|
|
1340
|
+
"completionPrice": 0.0004,
|
|
1341
|
+
"note": "1.7B base model"
|
|
1342
|
+
},
|
|
1343
|
+
"meta-llama/Llama-3.1-8B-Instruct": {
|
|
1344
|
+
"promptPrice": 0.0005,
|
|
1345
|
+
"completionPrice": 0.0015,
|
|
1346
|
+
"note": "HIGHEST PRIORITY - Most popular Llama 3.1 model with 5M downloads"
|
|
1347
|
+
},
|
|
1348
|
+
"meta-llama/Llama-3.2-1B-Instruct": {
|
|
1349
|
+
"promptPrice": 0.0001,
|
|
1350
|
+
"completionPrice": 0.0003,
|
|
1351
|
+
"note": "Small edge-optimized model - 3.7M downloads"
|
|
1352
|
+
},
|
|
1353
|
+
"meta-llama/Llama-3.2-3B-Instruct": {
|
|
1354
|
+
"promptPrice": 0.0003,
|
|
1355
|
+
"completionPrice": 0.0006,
|
|
1356
|
+
"note": "Mid-size edge model - 1.8M downloads"
|
|
1357
|
+
},
|
|
1358
|
+
"meta-llama/Llama-3.2-1B": {
|
|
1359
|
+
"promptPrice": 0.0001,
|
|
1360
|
+
"completionPrice": 0.0003,
|
|
1361
|
+
"note": "Base 1B model - 1.7M downloads"
|
|
1362
|
+
},
|
|
1363
|
+
"meta-llama/Llama-3.1-70B-Instruct": {
|
|
1364
|
+
"promptPrice": 0.002,
|
|
1365
|
+
"completionPrice": 0.006,
|
|
1366
|
+
"note": "Large 70B model - 725K downloads"
|
|
1367
|
+
},
|
|
1368
|
+
"meta-llama/Llama-3.3-70B-Instruct": {
|
|
1369
|
+
"promptPrice": 0.002,
|
|
1370
|
+
"completionPrice": 0.006,
|
|
1371
|
+
"note": "Latest Llama 3.3 70B - 659K downloads"
|
|
1372
|
+
},
|
|
1373
|
+
"meta-llama/Llama-3.2-3B": {
|
|
1374
|
+
"promptPrice": 0.0003,
|
|
1375
|
+
"completionPrice": 0.0006,
|
|
1376
|
+
"note": "Base 3B model"
|
|
1377
|
+
},
|
|
1378
|
+
"meta-llama/Llama-Guard-3-8B": {
|
|
1379
|
+
"promptPrice": 0.0005,
|
|
1380
|
+
"completionPrice": 0.0015,
|
|
1381
|
+
"note": "Safety/moderation model - 183K downloads"
|
|
1382
|
+
},
|
|
1383
|
+
"meta-llama/Llama-Guard-3-1B": {
|
|
1384
|
+
"promptPrice": 0.0001,
|
|
1385
|
+
"completionPrice": 0.0003,
|
|
1386
|
+
"note": "Small safety model"
|
|
1387
|
+
},
|
|
1388
|
+
"meta-llama/Llama-3.2-11B-Vision-Instruct": {
|
|
1389
|
+
"promptPrice": 0.001,
|
|
1390
|
+
"completionPrice": 0.003,
|
|
1391
|
+
"note": "Llama 3.2 vision model - 257K downloads"
|
|
1392
|
+
},
|
|
1393
|
+
"meta-llama/Llama-4-Scout-17B-16E-Instruct": {
|
|
1394
|
+
"promptPrice": 0.0012,
|
|
1395
|
+
"completionPrice": 0.0036,
|
|
1396
|
+
"note": "NEW LLAMA 4 vision model - 199K downloads"
|
|
1397
|
+
},
|
|
1398
|
+
"google/gemma-3-1b-it": {
|
|
1399
|
+
"promptPrice": 0.0001,
|
|
1400
|
+
"completionPrice": 0.0002,
|
|
1401
|
+
"note": "HIGHEST PRIORITY - Most popular Gemma 3, already noted in earlier analysis"
|
|
1402
|
+
},
|
|
1403
|
+
"google/gemma-2-2b-it": {
|
|
1404
|
+
"promptPrice": 0.0002,
|
|
1405
|
+
"completionPrice": 0.0004,
|
|
1406
|
+
"note": "Gemma 2 2B instruct"
|
|
1407
|
+
},
|
|
1408
|
+
"google/gemma-3-12b-it": {
|
|
1409
|
+
"promptPrice": 0.001,
|
|
1410
|
+
"completionPrice": 0.003,
|
|
1411
|
+
"note": "Gemma 3 12B with vision capabilities - 1.5M downloads"
|
|
1412
|
+
},
|
|
1413
|
+
"google/gemma-3-4b-it": {
|
|
1414
|
+
"promptPrice": 0.0005,
|
|
1415
|
+
"completionPrice": 0.0015,
|
|
1416
|
+
"note": "Gemma 3 4B with vision"
|
|
1417
|
+
},
|
|
1418
|
+
"google/gemma-3-27b-it": {
|
|
1419
|
+
"promptPrice": 0.0015,
|
|
1420
|
+
"completionPrice": 0.0045,
|
|
1421
|
+
"note": "Large Gemma 3 27B with vision"
|
|
1422
|
+
},
|
|
1423
|
+
"google/medgemma-4b-it": {
|
|
1424
|
+
"promptPrice": 0.0005,
|
|
1425
|
+
"completionPrice": 0.0015,
|
|
1426
|
+
"note": "Medical-specialized vision model - radiology, clinical reasoning, dermatology"
|
|
1427
|
+
},
|
|
1428
|
+
"ServiceNow-AI/Apriel-5B-Instruct": {
|
|
1429
|
+
"promptPrice": 0.0005,
|
|
1430
|
+
"completionPrice": 0.0015,
|
|
1431
|
+
"note": "ServiceNow 5B instruct model"
|
|
1432
|
+
},
|
|
1433
|
+
"ServiceNow-AI/Apriel-Nemotron-15b-Thinker": {
|
|
1434
|
+
"promptPrice": 0.001,
|
|
1435
|
+
"completionPrice": 0.003,
|
|
1436
|
+
"note": "ServiceNow reasoning model based on Nemotron"
|
|
1437
|
+
},
|
|
1438
|
+
"ServiceNow-AI/Apriel-1.5-15b-Thinker": {
|
|
1439
|
+
"promptPrice": 0.001,
|
|
1440
|
+
"completionPrice": 0.003,
|
|
1441
|
+
"note": "ServiceNows vision-language reasoning model - 49K downloads"
|
|
1442
|
+
},
|
|
1443
|
+
"nvidia/NVIDIA-Nemotron-Nano-9B-v2": {
|
|
1444
|
+
"promptPrice": 0.0005,
|
|
1445
|
+
"completionPrice": 0.0015,
|
|
1446
|
+
"note": "Nano series 9B v2 - efficient edge model"
|
|
1447
|
+
},
|
|
1448
|
+
"nvidia/Llama-3_3-Nemotron-Super-49B-v1_5": {
|
|
1449
|
+
"promptPrice": 0.0015,
|
|
1450
|
+
"completionPrice": 0.0045,
|
|
1451
|
+
"note": "Nemotron Super 49B - high-performance model"
|
|
1452
|
+
},
|
|
1453
|
+
"nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1": {
|
|
1454
|
+
"promptPrice": 0.0003,
|
|
1455
|
+
"completionPrice": 0.0009,
|
|
1456
|
+
"note": "Nano 4B - small efficient model"
|
|
1457
|
+
},
|
|
1458
|
+
"nvidia/OpenReasoning-Nemotron-7B": {
|
|
1459
|
+
"promptPrice": 0.0004,
|
|
1460
|
+
"completionPrice": 0.0012,
|
|
1461
|
+
"note": "Reasoning-focused 7B model based on Qwen2.5"
|
|
1462
|
+
},
|
|
1463
|
+
"nvidia/NVIDIA-Nemotron-Nano-12B-v2": {
|
|
1464
|
+
"promptPrice": 0.0007,
|
|
1465
|
+
"completionPrice": 0.0021,
|
|
1466
|
+
"note": "Nano series 12B v2"
|
|
1467
|
+
},
|
|
1468
|
+
"nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1": {
|
|
1469
|
+
"promptPrice": 0.001,
|
|
1470
|
+
"completionPrice": 0.003,
|
|
1471
|
+
"note": "HIGHEST PRIORITY - Most popular Nvidia vision model, 747K downloads"
|
|
1472
|
+
},
|
|
1473
|
+
"nvidia/Cosmos-Reason1-7B": {
|
|
1474
|
+
"promptPrice": 0.0008,
|
|
1475
|
+
"completionPrice": 0.0024,
|
|
1476
|
+
"note": "Cosmos reasoning vision model - 413K downloads"
|
|
1477
|
+
},
|
|
1478
|
+
"nvidia/NVLM-D-72B": {
|
|
1479
|
+
"promptPrice": 0.002,
|
|
1480
|
+
"completionPrice": 0.006,
|
|
1481
|
+
"note": "Large 72B vision-language model"
|
|
1482
|
+
},
|
|
1483
|
+
"Qwen/Qwen3-0.6B": {
|
|
1484
|
+
"promptPrice": 5e-05,
|
|
1485
|
+
"completionPrice": 0.0001,
|
|
1486
|
+
"note": "600M parameter model, smallest Qwen3 variant"
|
|
1487
|
+
},
|
|
1488
|
+
"Qwen/Qwen3-1.7B": {
|
|
1489
|
+
"promptPrice": 0.0001,
|
|
1490
|
+
"completionPrice": 0.0002,
|
|
1491
|
+
"note": "1.7B parameter model"
|
|
1492
|
+
},
|
|
1493
|
+
"Qwen/Qwen3-4B": {
|
|
1494
|
+
"promptPrice": 0.0003,
|
|
1495
|
+
"completionPrice": 0.0006,
|
|
1496
|
+
"note": "4B parameter base model"
|
|
1497
|
+
},
|
|
1498
|
+
"Qwen/Qwen3-8B": {
|
|
1499
|
+
"promptPrice": 0.0005,
|
|
1500
|
+
"completionPrice": 0.001,
|
|
1501
|
+
"note": "8B parameter base model"
|
|
1502
|
+
},
|
|
1503
|
+
"Qwen/Qwen3-14B": {
|
|
1504
|
+
"promptPrice": 0.0008,
|
|
1505
|
+
"completionPrice": 0.0016,
|
|
1506
|
+
"note": "14B parameter base model"
|
|
1507
|
+
},
|
|
1508
|
+
"Qwen/Qwen3-32B": {
|
|
1509
|
+
"promptPrice": 0.0012,
|
|
1510
|
+
"completionPrice": 0.0024,
|
|
1511
|
+
"note": "32B parameter base model"
|
|
1512
|
+
},
|
|
1513
|
+
"Qwen/Qwen3-4B-Instruct-2507": {
|
|
1514
|
+
"promptPrice": 0.0003,
|
|
1515
|
+
"completionPrice": 0.0006,
|
|
1516
|
+
"note": "4B instruct model, very popular (5M+ downloads)"
|
|
1517
|
+
},
|
|
1518
|
+
"Qwen/Qwen3-4B-Thinking-2507": {
|
|
1519
|
+
"promptPrice": 0.0006,
|
|
1520
|
+
"completionPrice": 0.0018,
|
|
1521
|
+
"note": "4B reasoning model with thinking process"
|
|
1522
|
+
},
|
|
1523
|
+
"Qwen/Qwen3-30B-A3B-Instruct-2507": {
|
|
1524
|
+
"promptPrice": 0.0004,
|
|
1525
|
+
"completionPrice": 0.0012,
|
|
1526
|
+
"note": "MoE model with 30B total, 3B active params"
|
|
1527
|
+
},
|
|
1528
|
+
"Qwen/Qwen3-30B-A3B-Thinking-2507": {
|
|
1529
|
+
"promptPrice": 0.0008,
|
|
1530
|
+
"completionPrice": 0.0024,
|
|
1531
|
+
"note": "MoE reasoning model with 30B total, 3B active"
|
|
1532
|
+
},
|
|
1533
|
+
"Qwen/Qwen3-Next-80B-A3B-Instruct": {
|
|
1534
|
+
"promptPrice": 0.0006,
|
|
1535
|
+
"completionPrice": 0.0018,
|
|
1536
|
+
"note": "Large MoE model with 80B total, 3B active"
|
|
1537
|
+
},
|
|
1538
|
+
"Qwen/Qwen3-235B-A22B": {
|
|
1539
|
+
"promptPrice": 0.0005,
|
|
1540
|
+
"completionPrice": 0.0015,
|
|
1541
|
+
"note": "Largest Qwen3 MoE with 235B total, 22B active - similar to existing Qwen3-235B-A22B models in your list"
|
|
1542
|
+
},
|
|
1543
|
+
"Qwen/Qwen3-Coder-30B-A3B-Instruct": {
|
|
1544
|
+
"promptPrice": 0.0004,
|
|
1545
|
+
"completionPrice": 0.0012,
|
|
1546
|
+
"note": "Code-specialized MoE model"
|
|
1547
|
+
},
|
|
1548
|
+
"Qwen/Qwen3-Omni-30B-A3B-Instruct": {
|
|
1549
|
+
"promptPrice": 0.0006,
|
|
1550
|
+
"completionPrice": 0.0018,
|
|
1551
|
+
"note": "Multimodal model with text-to-audio, any-to-any capabilities"
|
|
1552
|
+
},
|
|
1553
|
+
"gemma3:1b": {
|
|
1554
|
+
"promptPrice": 0.0001,
|
|
1555
|
+
"completionPrice": 0.0002,
|
|
1556
|
+
"note": "Ollama variant of google/gemma-3-1b-it - 2.6M downloads"
|
|
1557
|
+
},
|
|
1558
|
+
"gemma3:4b": {
|
|
1559
|
+
"promptPrice": 0.0005,
|
|
1560
|
+
"completionPrice": 0.0015,
|
|
1561
|
+
"note": "Ollama variant of google/gemma-3-4b-it - vision capable"
|
|
1562
|
+
},
|
|
1563
|
+
"gemma3:12b": {
|
|
1564
|
+
"promptPrice": 0.001,
|
|
1565
|
+
"completionPrice": 0.003,
|
|
1566
|
+
"note": "Ollama variant of google/gemma-3-12b-it - vision capable"
|
|
1567
|
+
},
|
|
1568
|
+
"deepseek-r1:1.5b": {
|
|
1569
|
+
"promptPrice": 0.0002,
|
|
1570
|
+
"completionPrice": 0.0004,
|
|
1571
|
+
"note": "Ollama variant of deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B - 1.0M downloads"
|
|
1572
|
+
},
|
|
1573
|
+
"deepseek-r1:671b": {
|
|
1574
|
+
"promptPrice": 0.0014,
|
|
1575
|
+
"completionPrice": 0.0028,
|
|
1576
|
+
"note": "Ollama variant of deepseek-ai/DeepSeek-R1"
|
|
1577
|
+
},
|
|
1578
|
+
"llama3.3:70b": {
|
|
1579
|
+
"promptPrice": 0.002,
|
|
1580
|
+
"completionPrice": 0.006,
|
|
1581
|
+
"note": "Ollama variant of meta-llama/Llama-3.3-70B-Instruct - 659K downloads"
|
|
1582
|
+
},
|
|
1583
|
+
"granite3.1:8b": {
|
|
1584
|
+
"promptPrice": 0.0005,
|
|
1585
|
+
"completionPrice": 0.0015,
|
|
1586
|
+
"note": "Ollama variant of ibm-granite/granite-3.1-8b-instruct"
|
|
1587
|
+
},
|
|
1588
|
+
"granite3.1:3b": {
|
|
1589
|
+
"promptPrice": 0.0003,
|
|
1590
|
+
"completionPrice": 0.0009,
|
|
1591
|
+
"note": "Ollama variant of ibm-granite/granite-3.1-3b-instruct"
|
|
1592
|
+
},
|
|
1593
|
+
"granite3.1:1b": {
|
|
1594
|
+
"promptPrice": 0.0001,
|
|
1595
|
+
"completionPrice": 0.0003,
|
|
1596
|
+
"note": "Ollama variant of ibm-granite/granite-3.1-1b-instruct"
|
|
1597
|
+
},
|
|
1598
|
+
"phi4": {
|
|
1599
|
+
"promptPrice": 0.0008,
|
|
1600
|
+
"completionPrice": 0.0024,
|
|
1601
|
+
"note": "Ollama variant of microsoft/Phi-4"
|
|
1602
|
+
},
|
|
1603
|
+
"qwen3:14b": {
|
|
1604
|
+
"promptPrice": 0.0007,
|
|
1605
|
+
"completionPrice": 0.0021,
|
|
1606
|
+
"note": "Ollama variant of Qwen/Qwen3-14B-Instruct"
|
|
1607
|
+
},
|
|
1608
|
+
"qwen3:32b": {
|
|
1609
|
+
"promptPrice": 0.0015,
|
|
1610
|
+
"completionPrice": 0.0045,
|
|
1611
|
+
"note": "Ollama variant of Qwen/Qwen3-32B-Instruct"
|
|
1612
|
+
},
|
|
1613
|
+
"mistral-small": {
|
|
1614
|
+
"promptPrice": 0.001,
|
|
1615
|
+
"completionPrice": 0.003,
|
|
1616
|
+
"note": "Ollama variant of mistralai/Mistral-Small-Instruct-2409"
|
|
1617
|
+
},
|
|
1618
|
+
"mistral-large": {
|
|
1619
|
+
"promptPrice": 0.002,
|
|
1620
|
+
"completionPrice": 0.006,
|
|
1621
|
+
"note": "Ollama variant of mistralai/Mistral-Large-Instruct-2407"
|
|
1622
|
+
}
|
|
1623
|
+
},
|
|
1624
|
+
"speech_to_text": {
|
|
1625
|
+
"nvidia/parakeet-tdt-0.6b-v2": {
|
|
1626
|
+
"promptPrice": 0.00015,
|
|
1627
|
+
"completionPrice": 0.00015,
|
|
1628
|
+
"note": "HIGHEST PRIORITY - Most popular ASR model, 3.7M downloads"
|
|
1629
|
+
},
|
|
1630
|
+
"nvidia/parakeet-rnnt-0.6b": {
|
|
1631
|
+
"promptPrice": 0.00015,
|
|
1632
|
+
"completionPrice": 0.00015,
|
|
1633
|
+
"note": "Parakeet RNNT ASR - 3.1M downloads"
|
|
1634
|
+
},
|
|
1635
|
+
"nvidia/parakeet-tdt-0.6b-v3": {
|
|
1636
|
+
"promptPrice": 0.00015,
|
|
1637
|
+
"completionPrice": 0.00015,
|
|
1638
|
+
"note": "Multilingual ASR v3 - 49 languages"
|
|
1639
|
+
},
|
|
1640
|
+
"nvidia/canary-1b-v2": {
|
|
1641
|
+
"promptPrice": 0.0002,
|
|
1642
|
+
"completionPrice": 0.0002,
|
|
1643
|
+
"note": "ASR + Translation - 30+ languages"
|
|
1644
|
+
},
|
|
1645
|
+
"Llama-4-Maverick-17B-128E-Instruct": {
|
|
1646
|
+
"promptPrice": 0.0001,
|
|
1647
|
+
"completionPrice": 0.0002,
|
|
1648
|
+
"note": "SambaNova - Maverick model (estimated pricing)"
|
|
1649
|
+
},
|
|
1650
|
+
"Qwen/Qwen3-Next-80B-A3B-Thinking": {
|
|
1651
|
+
"promptPrice": 0.0004,
|
|
1652
|
+
"completionPrice": 0.0004,
|
|
1653
|
+
"note": "Hyperbolic - Qwen3 Next 80B"
|
|
1654
|
+
},
|
|
1655
|
+
"Qwen/Qwen3-235B": {
|
|
1656
|
+
"promptPrice": 0.0004,
|
|
1657
|
+
"completionPrice": 0.0004,
|
|
1658
|
+
"note": "Hyperbolic - Qwen3 235B"
|
|
1659
|
+
},
|
|
1660
|
+
"deepseek-ai/DeepSeek-R1": {
|
|
1661
|
+
"promptPrice": 0.002,
|
|
1662
|
+
"completionPrice": 0.002,
|
|
1663
|
+
"note": "Hyperbolic - DeepSeek R1"
|
|
1664
|
+
},
|
|
1665
|
+
"deepseek-ai/DeepSeek-V3": {
|
|
1666
|
+
"promptPrice": 0.00025,
|
|
1667
|
+
"completionPrice": 0.00025,
|
|
1668
|
+
"note": "Hyperbolic - DeepSeek V3"
|
|
1669
|
+
},
|
|
1670
|
+
"openai/gpt-oss-120b": {
|
|
1671
|
+
"promptPrice": 0.0005,
|
|
1672
|
+
"completionPrice": 0.0015,
|
|
1673
|
+
"note": "Nebius - GPT OSS 120B (estimated pricing)"
|
|
1674
|
+
}
|
|
1675
|
+
}
|
|
1676
|
+
}
|