5
5
"DeepSeek-R1-Distill-Llama-70B" : 131072 ,
6
6
"DeepSeek-V3-0324" : 32768 ,
7
7
"E5-Mistral-7B-Instruct" : 4096 ,
8
+ "Llama-3.3-Swallow-70B-Instruct-v0.4" : 131072 ,
8
9
"Llama-4-Maverick-17B-128E-Instruct" : 131072 ,
9
10
"Meta-Llama-3.1-8B-Instruct" : 16384 ,
10
11
"Meta-Llama-3.3-70B-Instruct" : 131072 ,
66
67
"stability-ai/sdxl" : 0
67
68
},
68
69
"novita" : {
69
- "deepseek/deepseek-r1-0528" : 163840 ,
70
70
"deepseek/deepseek-v3-0324" : 163840 ,
71
+ "moonshotai/kimi-k2-instruct" : 131072 ,
72
+ "deepseek/deepseek-r1-0528" : 163840 ,
71
73
"baidu/ernie-4.5-vl-424b-a47b" : 123000 ,
72
74
"baidu/ernie-4.5-300b-a47b-paddle" : 123000 ,
73
75
"qwen/qwen3-30b-a3b-fp8" : 40960 ,
74
- "minimaxai/minimax-m1-80k" : 128000 ,
76
+ "minimaxai/minimax-m1-80k" : 1000000 ,
75
77
"deepseek/deepseek-r1-0528-qwen3-8b" : 128000 ,
76
78
"qwen/qwen3-32b-fp8" : 40960 ,
77
79
"qwen/qwen2.5-vl-72b-instruct" : 32768 ,
78
80
"qwen/qwen3-235b-a22b-fp8" : 40960 ,
79
81
"deepseek/deepseek-v3-turbo" : 64000 ,
82
+ "thudm/glm-4.1v-9b-thinking" : 65536 ,
80
83
"meta-llama/llama-4-maverick-17b-128e-instruct-fp8" : 1048576 ,
81
84
"google/gemma-3-27b-it" : 32000 ,
82
85
"deepseek/deepseek-r1-turbo" : 64000 ,
111
114
"qwen/qwen2.5-7b-instruct" : 32000 ,
112
115
"meta-llama/llama-3.2-1b-instruct" : 131000 ,
113
116
"meta-llama/llama-3.2-3b-instruct" : 32768 ,
114
- "meta-llama/llama-3.1-8b-instruct-bf16" : 8192 ,
115
117
"sao10k/l31-70b-euryale-v2.2" : 8192
116
118
},
117
119
"fal" : {
158
160
"c4ai-aya-vision-32b" : 16384 ,
159
161
"command-r" : 132096 ,
160
162
"command-r7b-12-2024" : 132000 ,
163
+ "command-a-vision" : 128000 ,
161
164
"command-r7b-arabic-02-2025" : 128000 ,
162
165
"command-light-nightly" : 4096 ,
163
166
"embed-english-v3.0" : 512 ,
164
167
"embed-multilingual-light-v3.0-image" : 0 ,
165
168
"embed-multilingual-v3.0-image" : 0 ,
166
- "c4ai-aya-expanse-32b" : 128000 ,
167
- "command" : 4096
169
+ "c4ai-aya-expanse-32b" : 128000
168
170
},
169
171
"together" : {
170
- "meta-llama/Llama-Vision-Free" : 131072 ,
171
- "togethercomputer/m2-bert-80M-32k-retrieval" : 32768 ,
172
172
"cartesia/sonic" : 0 ,
173
- "meta-llama/Meta-Llama-3-8B-Instruct-Lite" : 8192 ,
174
- "intfloat/multilingual-e5-large-instruct" : 514 ,
173
+ "black-forest-labs/FLUX.1-kontext-pro" : 0 ,
175
174
"Alibaba-NLP/gte-modernbert-base" : 8192 ,
175
+ "Qwen/Qwen2.5-VL-72B-Instruct" : 32768 ,
176
+ "google/gemma-3-27b-it" : 65536 ,
176
177
"Qwen/Qwen3-235B-A22B-fp8-tput" : 40960 ,
177
- "meta-llama/LlamaGuard-2-8b" : 8192 ,
178
- "Qwen/Qwen2.5-Coder-32B-Instruct" : 16384 ,
178
+ "Salesforce/Llama-Rank-V1" : 8192 ,
179
+ "mistralai/Mistral-7B-Instruct-v0.3" : 32768 ,
180
+ "marin-community/marin-8b-instruct" : 4096 ,
179
181
"cartesia/sonic-2" : 0 ,
180
182
"togethercomputer/MoA-1" : 32768 ,
181
- "meta-llama/Meta-Llama-3-70B-Instruct-Turbo" : 8192 ,
182
- "eddie/Qwen3-32B" : 32768 ,
183
- "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo" : 131072 ,
184
- "Qwen/QwQ-32B" : 131072 ,
185
- "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" : 131072 ,
186
183
"meta-llama/Meta-Llama-Guard-3-8B" : 8192 ,
187
- "arcee_ai/arcee-spotlight" : 131072 ,
188
- "google/gemma-3-27b-it" : 65536 ,
189
- "arcee-ai/AFM-4.5B-Preview" : 65536 ,
190
- "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo" : 130815 ,
184
+ "mistralai/Mistral-Small-24B-Instruct-2501" : 32768 ,
185
+ "Qwen/Qwen2-VL-72B-Instruct" : 32768 ,
186
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B-free" : 8192 ,
187
+ "togethercomputer/m2-bert-80M-32k-retrieval" : 32768 ,
188
+ "deepseek-ai/DeepSeek-R1" : 163840 ,
189
+ "mixedbread-ai/Mxbai-Rerank-Large-V2" : 32768 ,
190
+ "meta-llama/Meta-Llama-3-8B-Instruct-Lite" : 8192 ,
191
191
"deepseek-ai/DeepSeek-V3" : 131072 ,
192
- "lgai/exaone-3-5-32b-instruct" : 32768 ,
192
+ "togethercomputer/Refuel-Llm-V2" : 16384 ,
193
+ "moonshotai/Kimi-K2-Instruct" : 131072 ,
194
+ "togethercomputer/MoA-1-Turbo" : 32768 ,
195
+ "eddiehou/meta-llama/Llama-3.1-405B" : 12000 ,
193
196
"deepseek-ai/DeepSeek-R1-0528-tput" : 163840 ,
194
- "mistralai/Mixtral-8x7B-Instruct-v0.1" : 32768 ,
195
- "meta-llama/Llama-3-8b-chat-hf" : 8192 ,
197
+ "mistralai/Mistral-7B-Instruct-v0.2" : 32768 ,
196
198
"mistralai/Mistral-7B-Instruct-v0.1" : 32768 ,
197
- "meta-llama/Llama-2-70b-hf" : 4096 ,
198
- "togethercomputer/MoA-1-Turbo" : 32768 ,
199
- "black-forest-labs/FLUX.1-kontext-max" : 0 ,
199
+ "serverless-qwen-qwen3-32b-fp8" : 40960 ,
200
+ "moz-llama-3-3-70b-instruct-turbo" : 131072 ,
201
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B" : 131072 ,
202
+ "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF" : 32768 ,
203
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free" : 131072 ,
204
+ "meta-llama/Llama-Vision-Free" : 131072 ,
205
+ "meta-llama/Meta-Llama-3-70B-Instruct-Turbo" : 8192 ,
206
+ "google/gemma-3n-E4B-it" : 32768 ,
207
+ "arcee-ai/AFM-4.5B-Preview" : 65536 ,
208
+ "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo" : 131072 ,
209
+ "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo" : 131072 ,
210
+ "lgai/exaone-3-5-32b-instruct" : 32768 ,
211
+ "lgai/exaone-deep-32b" : 32768 ,
212
+ "meta-llama/Llama-3-70b-chat-hf" : 8192 ,
213
+ "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo" : 131072 ,
200
214
"perplexity-ai/r1-1776" : 163840 ,
201
- "mistralai/Mistral-7B-Instruct-v0.2" : 32768 ,
202
- "deepseek-ai/DeepSeek-V3-p-dp" : 131072 ,
203
- "Qwen/Qwen2-72B-Instruct" : 32768 ,
204
- "mistralai/Mistral-7B-Instruct-v0.3" : 32768 ,
205
- "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO" : 32768 ,
206
- "meta-llama/Llama-Guard-3-11B-Vision-Turbo" : 131072 ,
207
- "Qwen/Qwen2-VL-72B-Instruct" : 32768 ,
215
+ "mistralai/Mixtral-8x7B-Instruct-v0.1" : 32768 ,
208
216
"scb10x/scb10x-llama3-1-typhoon2-70b-instruct" : 8192 ,
217
+ "meta-llama/Llama-Guard-3-11B-Vision-Turbo" : 131072 ,
218
+ "google/gemma-2-27b-it" : 8192 ,
219
+ "arcee-ai/arcee-blitz" : 32768 ,
220
+ "Qwen/QwQ-32B" : 131072 ,
209
221
"arcee-ai/maestro-reasoning" : 131072 ,
222
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B" : 131072 ,
223
+ "Qwen/Qwen2-72B-Instruct" : 32768 ,
224
+ "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo" : 130815 ,
225
+ "arcee-ai/virtuoso-large" : 131072 ,
226
+ "arcee_ai/arcee-spotlight" : 131072 ,
227
+ "arcee-ai/caller" : 32768 ,
228
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo" : 131072 ,
229
+ "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" : 131072 ,
230
+ "togethercomputer/Refuel-Llm-V2-Small" : 8192 ,
231
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B" : 131072 ,
210
232
"meta-llama/Llama-3.2-3B-Instruct-Turbo" : 131072 ,
211
233
"arcee-ai/virtuoso-medium-v2" : 131072 ,
234
+ "meta-llama/Llama-3-8b-chat-hf" : 8192 ,
235
+ "Qwen/Qwen2.5-Coder-32B-Instruct" : 16384 ,
212
236
"arcee-ai/coder-large" : 32768 ,
213
- "meta-llama/Llama-Guard-4-12B" : 1048576 ,
214
- "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B" : 131072 ,
215
- "arcee-ai/virtuoso-large" : 131072 ,
216
- "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B" : 131072 ,
217
- "deepseek-ai/DeepSeek-R1-Distill-Llama-70B" : 131072 ,
218
- "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF" : 32768 ,
219
- "deepseek-ai/DeepSeek-R1-Distill-Llama-70B-free" : 8192 ,
237
+ "meta-llama/Llama-2-70b-hf" : 4096 ,
238
+ "Qwen/Qwen2.5-72B-Instruct-Turbo" : 131072 ,
239
+ "Qwen/Qwen2.5-7B-Instruct-Turbo" : 32768 ,
240
+ "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO" : 32768 ,
220
241
"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8" : 1048576 ,
221
- "togethercomputer/Refuel-Llm-V2-Small" : 8192 ,
222
- "togethercomputer/Refuel-Llm-V2" : 16384 ,
223
- "Qwen/Qwen2.5-VL-72B-Instruct" : 32768 ,
224
242
"scb10x/scb10x-typhoon-2-1-gemma3-12b" : 131072 ,
225
- "arcee-ai/caller " : 32768 ,
226
- "lgai/exaone-deep -32b" : 32768 ,
227
- "black-forest-labs/FLUX.1-kontext-pro " : 0 ,
228
- "google/gemma-3n-E4B-it " : 32768 ,
243
+ "meta-llama/Llama-Guard-4-12B " : 1048576 ,
244
+ "qwen-qwen3 -32b-fp8-serverless " : 40960 ,
245
+ "meta-llama/LlamaGuard-2-8b " : 8192 ,
246
+ "intfloat/multilingual-e5-large-instruct " : 514 ,
229
247
"meta-llama/Llama-4-Scout-17B-16E-Instruct" : 1048576 ,
230
- "deepseek-ai/DeepSeek-R1" : 163840 ,
231
- "Qwen/Qwen2.5-72B-Instruct-Turbo" : 131072 ,
232
- "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo" : 131072 ,
233
- "arcee-ai/arcee-blitz" : 32768 ,
234
- "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo" : 131072 ,
235
- "meta-llama/Llama-3-70b-chat-hf" : 8192 ,
236
- "google/gemma-2-27b-it" : 8192 ,
237
- "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free" : 131072 ,
238
- "Qwen/Qwen2.5-7B-Instruct-Turbo" : 32768 ,
239
- "mistralai/Mistral-Small-24B-Instruct-2501" : 32768 ,
240
- "Salesforce/Llama-Rank-V1" : 8192 ,
241
- "meta-llama/Llama-3.3-70B-Instruct-Turbo" : 131072 ,
242
- "marin-community/marin-8b-instruct" : 4096 ,
243
- "Qwen/Qwen3-32B-FP8" : 0
248
+ "yan/deepseek-ai-deepseek-v3" : 163839 ,
249
+ "black-forest-labs/FLUX.1-kontext-max" : 0 ,
250
+ "moz/Llama-3.3-70B-Instruct-Turbo" : 131072
244
251
},
245
252
"fireworks-ai" : {
246
- "accounts/perplexity/models/r1-1776" : 163840 ,
247
253
"accounts/fireworks/models/deepseek-r1-0528" : 163840 ,
248
- "accounts/fireworks /models/qwen3-30b-a3b " : 40000 ,
249
- "accounts/fireworks/models/llama-guard-3-8b " : 131072 ,
254
+ "accounts/perplexity /models/r1-1776 " : 163840 ,
255
+ "accounts/fireworks/models/qwen3-30b-a3b " : 131072 ,
250
256
"accounts/fireworks/models/llama4-scout-instruct-basic" : 10485760 ,
251
257
"accounts/fireworks/models/llama4-maverick-instruct-basic" : 1048576 ,
252
258
"accounts/fireworks/models/llama-v3p1-8b-instruct" : 131072 ,
253
259
"accounts/fireworks/models/firesearch-ocr-v6" : 8192 ,
254
260
"accounts/fireworks/models/llama-v3p1-405b-instruct" : 131072 ,
255
- "accounts/fireworks/models/qwen2-vl-72b-instruct" : 32768 ,
256
261
"accounts/fireworks/models/mixtral-8x22b-instruct" : 65536 ,
257
- "accounts/fireworks/models/qwen2p5-72b-instruct" : 32768 ,
258
262
"accounts/fireworks/models/deepseek-r1-basic" : 163840 ,
259
263
"accounts/fireworks/models/llama-v3p1-70b-instruct" : 131072 ,
260
- "accounts/fireworks/models/qwen3-235b-a22b" : 128000 ,
264
+ "accounts/fireworks/models/qwen3-235b-a22b" : 131072 ,
261
265
"accounts/fireworks/models/llama-v3p3-70b-instruct" : 131072 ,
262
266
"accounts/fireworks/models/deepseek-r1" : 163840 ,
263
267
"accounts/sentientfoundation/models/dobby-unhinged-llama-3-3-70b-new" : 131072 ,
264
268
"accounts/sentientfoundation-serverless/models/dobby-mini-unhinged-plus-llama-3-1-8b" : 131072 ,
265
269
"accounts/fireworks/models/deepseek-v3" : 131072 ,
266
270
"accounts/fireworks/models/deepseek-v3-0324" : 163840 ,
267
- "accounts/fireworks/models/qwq-32b" : 131072 ,
268
271
"accounts/fireworks/models/qwen2p5-vl-32b-instruct" : 128000
269
272
}
270
273
}
0 commit comments