Spaces:
Running
Running
File size: 10,776 Bytes
c5a9402 d7c13d5 3c5cb2c d7c13d5 3c5cb2c d7c13d5 3c5cb2c d7c13d5 3c5cb2c d7c13d5 a2afbad e7f1125 a2afbad e7f1125 a2afbad e7f1125 a2afbad e7f1125 cf9d9a6 9bbfd57 cf9d9a6 174b7e2 a2afbad e7f1125 a2afbad 8613c25 3c5cb2c 6e42a29 8613c25 175435a 7e0dee8 9bbfd57 7e0dee8 9bbfd57 7e0dee8 175435a 9bbfd57 175435a 9bbfd57 175435a 8613c25 9bbfd57 8613c25 9bbfd57 8613c25 9bbfd57 8613c25 9bbfd57 8613c25 c5a9402 af413b3 c5a9402 88aceaf c5a9402 5931289 c5a9402 6e42a29 88aceaf 9e1a125 88aceaf |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 |
# aistudio gemini free, Rate Limits https://ai.google.dev/pricing#1_5pro
# gemini-1.5-pro: 2 rpm, 32,000 tpm, 1,500 RPD
# gemini-1.5-flash: 15 rpm, 1,000,000 tpm, 50 RPD
model_list:
# northflank
- model_name: gpt-4o-mini-northflank
litellm_params:
model: openai/gpt-4o-mini
api_base: https://yc--northflank-duckapi--b69bn8cbbs7k.code.run/v1
api_key: os.environ/NF_API_KEY
- model_name: gpt-4o-mini
litellm_params:
model: openai/gpt-4o-mini
api_base: https://yc--northflank-duckapi--b69bn8cbbs7k.code.run/v1
api_key: os.environ/NF_API_KEY
- model_name: gpt-3.5-turbo-northflank
litellm_params:
model: openai/gpt-3.5-turbo
api_base: https://yc--northflank-duckapi--b69bn8cbbs7k.code.run/v1
api_key: os.environ/NF_API_KEY
- model_name: gpt-3.5-turbo
litellm_params:
model: openai/gpt-3.5-turbo
api_base: https://yc--northflank-duckapi--b69bn8cbbs7k.code.run/v1
api_key: os.environ/NF_API_KEY
# github
- model_name: gpt-4o-k1
litellm_params:
model: github/gpt-4o
api_base: https://models.inference.ai.azure.com
api_key: os.environ/GITHUB_API_KEY1
- model_name: github/gpt-4o
litellm_params:
model: github/gpt-4o
api_key: os.environ/GITHUB_API_KEY1
rpm: 30 # 15 * # of keys
tpm: 2000000 # 1,000,000 * # of keys
- model_name: gpt-4o-k2
litellm_params:
model: github/gpt-4o
api_base: https://models.inference.ai.azure.com
api_key: os.environ/GITHUB_API_KEY2
- model_name: github/gpt-4o
litellm_params:
model: github/gpt-4o
api_key: os.environ/GITHUB_API_KEY2
rpm: 30 # 15 * # of keys
tpm: 2000000 # 1,000,000 * # of keys
- model_name: Mistral-large-2411-k1
litellm_params:
model: github/Mistral-large-2411
api_base: https://models.inference.ai.azure.com
api_key: os.environ/GITHUB_API_KEY1
- model_name: github/Mistral-large-2411
litellm_params:
model: github/Mistral-large-2411
api_key: os.environ/GITHUB_API_KEY1
rpm: 30 # 15 * # of keys
tpm: 2000000 # 1,000,000 * # of keys
- model_name: Mistral-large-2411-k2
litellm_params:
model: github/Mistral-large-2411
api_base: https://models.inference.ai.azure.com
api_key: os.environ/GITHUB_API_KEY2
- model_name: github/Mistral-large-2411
litellm_params:
model: github/Mistral-large-2411
api_key: os.environ/GITHUB_API_KEY2
rpm: 30 # 15 * # of keys
tpm: 2000000 # 1,000,000 * # of keys
- model_name: gpt-4o-mini-k1
litellm_params:
model: github/gpt-4o-mini
api_base: https://models.inference.ai.azure.com
api_key: os.environ/GITHUB_API_KEY1
- model_name: github/gpt-4o-mini
litellm_params:
model: github/gpt-4o-mini
api_key: os.environ/GITHUB_API_KEY1
rpm: 30 # 15 * # of keys
tpm: 2000000 # 1,000,000 * # of keys
- model_name: gpt-4o-mini-k2
litellm_params:
model: github/gpt-4o-mini
api_base: https://models.inference.ai.azure.com
api_key: os.environ/GITHUB_API_KEY2
- model_name: github/gpt-4o-mini
litellm_params:
model: github/gpt-4o-mini
api_key: os.environ/GITHUB_API_KEY2
rpm: 30 # 15 * # of keys
tpm: 2000000 # 1,000,000 * # of keys
# --------------gemini-1.5-pro--------------------
- model_name: gemini-1.5-pro-k1
litellm_params:
model: gemini/gemini-1.5-pro
api_key: os.environ/GEMINI_API_KEY1
- model_name: gemini-1.5-pro
litellm_params:
model: gemini/gemini-1.5-pro
api_key: os.environ/GEMINI_API_KEY1
rpm: 4 # 2 * # of keys
tpm: 6400 # 32,000 * # of keys
- model_name: gemini-1.5-pro-k2
litellm_params:
model: gemini/gemini-1.5-pro
api_key: os.environ/GEMINI_API_KEY2
- model_name: gemini-1.5-pro
litellm_params:
model: gemini/gemini-1.5-pro
api_key: os.environ/GEMINI_API_KEY
rpm: 4 # 2 * # of keys
tpm: 6400 # 32,000 * # of keys
- model_name: gemini-1.5-pro-002-k1
litellm_params:
model: gemini/gemini-1.5-pro-002
api_key: os.environ/GEMINI_API_KEY1
- model_name: gemini-1.5-pro-002
litellm_params:
model: gemini/gemini-1.5-flash-002
api_key: os.environ/GEMINI_API_KEY1
rpm: 75 # 15 * # of keys
tpm: 5000000 # 1,000,000 * # of keys
- model_name: gemini-1.5-pro-002-k2
litellm_params:
model: gemini/gemini-1.5-pro-002
api_key: os.environ/GEMINI_API_KEY2
- model_name: gemini-1.5-pro-002
litellm_params:
model: gemini/gemini-1.5-pro-002
api_key: os.environ/GEMINI_API_KEY2
rpm: 75 # 15 * # of keys
tpm: 5000000 # 1,000,000 * # of keys
- model_name: gemini-1.5-pro-exp-k1
litellm_params:
model: gemini/gemini-1.5-pro-exp
api_key: os.environ/GEMINI_API_KEY1
- model_name: gemini-1.5-pro-exp
litellm_params:
model: gemini/gemini-1.5-pro-exp
api_key: os.environ/GEMINI_API_KEY1
rpm: 75 # 15 * # of keys
tpm: 5000000 # 1,000,000 * # of keys
- model_name: gemini-1.5-pro-exp-k2
litellm_params:
model: gemini/gemini-1.5-pro-exp
api_key: os.environ/GEMINI_API_KEY2
- model_name: gemini-1.5-pro-exp
litellm_params:
model: gemini/gemini-1.5-pro-exp
api_key: os.environ/GEMINI_API_KEY2
rpm: 75 # 15 * # of keys
tpm: 5000000 # 1,000,000 * # of keys
# --------------gemini-2.0-flash-exp--------------------
- model_name: gemini-2.0-flash-exp-k1
litellm_params:
model: gemini/gemini-2.0-flash-exp
api_key: os.environ/GEMINI_API_KEY1
- model_name: gemini-2.0-flash-exp
litellm_params:
model: gemini/gemini-2.0-flash-exp
api_key: os.environ/GEMINI_API_KEY1
rpm: 50 # 2 * # of keys
tpm: 5000000 # 32,000 * # of keys
- model_name: gemini-2.0-flash-exp-k2
litellm_params:
model: gemini/gemini-2.0-flash-exp
api_key: os.environ/GEMINI_API_KEY2
- model_name: gemini-2.0-flash-exp
litellm_params:
model: gemini/gemini-2.0-flash-exp
api_key: os.environ/GEMINI_API_KEY2
rpm: 50 # 2 * # of keys
tpm: 5000000 # 32,000 * # of keys
- model_name: gemini-2.0-flash-thinking-exp-k1
litellm_params:
model: gemini/gemini-2.0-flash-thinking-exp
api_key: os.environ/GEMINI_API_KEY1
- model_name: gemini-2.0-flash-thinking-exp
litellm_params:
model: gemini/gemini-2.0-flash-thinking-exp
api_key: os.environ/GEMINI_API_KEY1
rpm: 50 # 2 * # of keys
tpm: 5000000 # 32,000 * # of keys
- model_name: gemini-2.0-flash-thinking-exp-k2
litellm_params:
model: gemini/gemini-2.0-flash-thinking-exp
api_key: os.environ/GEMINI_API_KEY2
- model_name: gemini-2.0-flash-thinking-exp
litellm_params:
model: gemini/gemini-2.0-flash-thinking-exp
api_key: os.environ/GEMINI_API_KEY2
rpm: 50 # 2 * # of keys
tpm: 5000000 # 32,000 * # of keys
- model_name: gemini-2.0-flash-thinking-exp-1219-k1
litellm_params:
model: gemini/gemini-2.0-flash-thinking-exp-1219
api_key: os.environ/GEMINI_API_KEY1
- model_name: gemini-2.0-flash-thinking-exp-1219
litellm_params:
model: gemini/gemini-2.0-flash-thinking-exp-1219
api_key: os.environ/GEMINI_API_KEY1
rpm: 50 # 2 * # of keys
tpm: 5000000 # 32,000 * # of keys
- model_name: gemini-2.0-flash-thinking-exp-1219-k2
litellm_params:
model: gemini/gemini-2.0-flash-thinking-exp-1219
api_key: os.environ/GEMINI_API_KEY2
- model_name: gemini-2.0-flash-thinking-exp-1219
litellm_params:
model: gemini/gemini-2.0-flash-thinking-exp-1219
api_key: os.environ/GEMINI_API_KEY2
rpm: 50 # 2 * # of keys
tpm: 5000000 # 32,000 * # of keys
# --------------gemini-exp-1206--------------------
- model_name: gemini-exp-1206-k1
litellm_params:
model: gemini/gemini-exp-1206
api_key: os.environ/GEMINI_API_KEY1
- model_name: gemini-exp-1206
litellm_params:
model: gemini/gemini-exp-1206
api_key: os.environ/GEMINI_API_KEY1
rpm: 20 # 2 * # of keys
tpm: 5000000 # 32,000 * # of keys
- model_name: gemini-exp-1206-k2
litellm_params:
model: gemini/gemini-exp-1206
api_key: os.environ/GEMINI_API_KEY2
- model_name: gemini-exp-1206
litellm_params:
model: gemini/gemini-exp-1206
api_key: os.environ/GEMINI_API_KEY2
rpm: 20 # 2 * # of keys
tpm: 5000000 # 32,000 * # of keys
# --------------gemini-exp-1121--------------------
- model_name: gemini-exp-1121-k1
litellm_params:
model: gemini/gemini-exp-1121
api_key: os.environ/GEMINI_API_KEY1
- model_name: gemini-exp-1121
litellm_params:
model: gemini/gemini-exp-1121
api_key: os.environ/GEMINI_API_KEY1
rpm: 20 # 2 * # of keys
tpm: 5000000 # 32,000 * # of keys
- model_name: gemini-exp-1121-k2
litellm_params:
model: gemini/gemini-exp-1121
api_key: os.environ/GEMINI_API_KEY2
- model_name: gemini-exp-1121
litellm_params:
model: gemini/gemini-exp-1121
api_key: os.environ/GEMINI_API_KEY2
rpm: 20 # 2 * # of keys
tpm: 5000000 # 32,000 * # of keys
# --------------gemini-exp-1114--------------------
- model_name: gemini-exp-1114-k1
litellm_params:
model: gemini/gemini-exp-1114
api_key: os.environ/GEMINI_API_KEY1
- model_name: gemini-exp-1114
litellm_params:
model: gemini/gemini-exp-1114
api_key: os.environ/GEMINI_API_KEY1
rpm: 20 # 2 * # of keys
tpm: 5000000 # 32,000 * # of keys
- model_name: gemini-exp-1114-k2
litellm_params:
model: gemini/gemini-exp-1114
api_key: os.environ/GEMINI_API_KEY2
- model_name: gemini-exp-1114
litellm_params:
model: gemini/gemini-exp-1114
api_key: os.environ/GEMINI_API_KEY2
rpm: 20 # 2 * # of keys
tpm: 5000000 # 32,000 * # of keys
litellm_settings:
# Networking settings
request_timeout: 20 # (int) llm request timeout in seconds. Raise Timeout error if call takes longer than 10s. Sets litellm.request_timeout
num_retries: 3
fallbacks: [{"gemini-1.5-pro": ["gemini-1.5-flash"]}]
allowed_fails: 3 # cooldown model if it fails > 1 call in a minute.
cooldown_time: 30 # how long to cooldown model if fails/min > allowed_fails
drop_params: true
general_settings:
master_key: os.environ/MASTER_KEY # sk-1234 # [OPTIONAL] Only use this if you require all calls to contain this key (Authorization: Bearer sk-1234)
router_settings:
fallbacks: [{"gpt-4o-mini": ["gemini-1.5-flash"]}, {"gpt-3.5-turbo": ["gemini-1.5-flash"]}]
model_group_alias: {"gpt-4": "gemini-1.5-pro"}
routing_strategy: simple-shuffle |