/ mlflow / utils / model_catalog / deepinfra.json
deepinfra.json
   1  {
   2    "schema_version": "1.0",
   3    "models": {
   4      "Gryphe/MythoMax-L2-13b": {
   5        "mode": "chat",
   6        "context_window": {
   7          "max_input": 4096,
   8          "max_output": 4096,
   9          "max_tokens": 4096
  10        },
  11        "pricing": {
  12          "input_per_million_tokens": 0.08,
  13          "output_per_million_tokens": 0.09
  14        },
  15        "capabilities": {
  16          "function_calling": true,
  17          "vision": false,
  18          "reasoning": false,
  19          "prompt_caching": false,
  20          "response_schema": false
  21        },
  22        "last_updated_at": "2026-04-24"
  23      },
  24      "NousResearch/Hermes-3-Llama-3.1-405B": {
  25        "mode": "chat",
  26        "context_window": {
  27          "max_input": 131072,
  28          "max_output": 131072,
  29          "max_tokens": 131072
  30        },
  31        "pricing": {
  32          "input_per_million_tokens": 1.0,
  33          "output_per_million_tokens": 1.0
  34        },
  35        "capabilities": {
  36          "function_calling": true,
  37          "vision": false,
  38          "reasoning": false,
  39          "prompt_caching": false,
  40          "response_schema": false
  41        },
  42        "last_updated_at": "2026-04-24"
  43      },
  44      "NousResearch/Hermes-3-Llama-3.1-70B": {
  45        "mode": "chat",
  46        "context_window": {
  47          "max_input": 131072,
  48          "max_output": 131072,
  49          "max_tokens": 131072
  50        },
  51        "pricing": {
  52          "input_per_million_tokens": 0.3,
  53          "output_per_million_tokens": 0.3
  54        },
  55        "capabilities": {
  56          "function_calling": false,
  57          "vision": false,
  58          "reasoning": false,
  59          "prompt_caching": false,
  60          "response_schema": false
  61        },
  62        "last_updated_at": "2026-04-24"
  63      },
  64      "Qwen/QwQ-32B": {
  65        "mode": "chat",
  66        "context_window": {
  67          "max_input": 131072,
  68          "max_output": 131072,
  69          "max_tokens": 131072
  70        },
  71        "pricing": {
  72          "input_per_million_tokens": 0.15,
  73          "output_per_million_tokens": 0.4
  74        },
  75        "capabilities": {
  76          "function_calling": true,
  77          "vision": false,
  78          "reasoning": false,
  79          "prompt_caching": false,
  80          "response_schema": false
  81        },
  82        "last_updated_at": "2026-04-24"
  83      },
  84      "Qwen/Qwen2.5-72B-Instruct": {
  85        "mode": "chat",
  86        "context_window": {
  87          "max_input": 32768,
  88          "max_output": 32768,
  89          "max_tokens": 32768
  90        },
  91        "pricing": {
  92          "input_per_million_tokens": 0.12,
  93          "output_per_million_tokens": 0.39
  94        },
  95        "capabilities": {
  96          "function_calling": true,
  97          "vision": false,
  98          "reasoning": false,
  99          "prompt_caching": false,
 100          "response_schema": false
 101        },
 102        "last_updated_at": "2026-04-24"
 103      },
 104      "Qwen/Qwen2.5-7B-Instruct": {
 105        "mode": "chat",
 106        "context_window": {
 107          "max_input": 32768,
 108          "max_output": 32768,
 109          "max_tokens": 32768
 110        },
 111        "pricing": {
 112          "input_per_million_tokens": 0.04,
 113          "output_per_million_tokens": 0.1
 114        },
 115        "capabilities": {
 116          "function_calling": false,
 117          "vision": false,
 118          "reasoning": false,
 119          "prompt_caching": false,
 120          "response_schema": false
 121        },
 122        "last_updated_at": "2026-04-24"
 123      },
 124      "Qwen/Qwen2.5-VL-32B-Instruct": {
 125        "mode": "chat",
 126        "context_window": {
 127          "max_input": 128000,
 128          "max_output": 128000,
 129          "max_tokens": 128000
 130        },
 131        "pricing": {
 132          "input_per_million_tokens": 0.2,
 133          "output_per_million_tokens": 0.6
 134        },
 135        "capabilities": {
 136          "function_calling": true,
 137          "vision": true,
 138          "reasoning": false,
 139          "prompt_caching": false,
 140          "response_schema": false
 141        },
 142        "last_updated_at": "2026-04-24"
 143      },
 144      "Qwen/Qwen3-14B": {
 145        "mode": "chat",
 146        "context_window": {
 147          "max_input": 40960,
 148          "max_output": 40960,
 149          "max_tokens": 40960
 150        },
 151        "pricing": {
 152          "input_per_million_tokens": 0.06,
 153          "output_per_million_tokens": 0.24
 154        },
 155        "capabilities": {
 156          "function_calling": true,
 157          "vision": false,
 158          "reasoning": false,
 159          "prompt_caching": false,
 160          "response_schema": false
 161        },
 162        "last_updated_at": "2026-04-24"
 163      },
 164      "Qwen/Qwen3-235B-A22B": {
 165        "mode": "chat",
 166        "context_window": {
 167          "max_input": 40960,
 168          "max_output": 40960,
 169          "max_tokens": 40960
 170        },
 171        "pricing": {
 172          "input_per_million_tokens": 0.18,
 173          "output_per_million_tokens": 0.54
 174        },
 175        "capabilities": {
 176          "function_calling": true,
 177          "vision": false,
 178          "reasoning": false,
 179          "prompt_caching": false,
 180          "response_schema": false
 181        },
 182        "last_updated_at": "2026-04-24"
 183      },
 184      "Qwen/Qwen3-235B-A22B-Instruct-2507": {
 185        "mode": "chat",
 186        "context_window": {
 187          "max_input": 262144,
 188          "max_output": 262144,
 189          "max_tokens": 262144
 190        },
 191        "pricing": {
 192          "input_per_million_tokens": 0.09,
 193          "output_per_million_tokens": 0.6
 194        },
 195        "capabilities": {
 196          "function_calling": true,
 197          "vision": false,
 198          "reasoning": false,
 199          "prompt_caching": false,
 200          "response_schema": false
 201        },
 202        "last_updated_at": "2026-04-24"
 203      },
 204      "Qwen/Qwen3-235B-A22B-Thinking-2507": {
 205        "mode": "chat",
 206        "context_window": {
 207          "max_input": 262144,
 208          "max_output": 262144,
 209          "max_tokens": 262144
 210        },
 211        "pricing": {
 212          "input_per_million_tokens": 0.3,
 213          "output_per_million_tokens": 2.9
 214        },
 215        "capabilities": {
 216          "function_calling": true,
 217          "vision": false,
 218          "reasoning": false,
 219          "prompt_caching": false,
 220          "response_schema": false
 221        },
 222        "last_updated_at": "2026-04-24"
 223      },
 224      "Qwen/Qwen3-30B-A3B": {
 225        "mode": "chat",
 226        "context_window": {
 227          "max_input": 40960,
 228          "max_output": 40960,
 229          "max_tokens": 40960
 230        },
 231        "pricing": {
 232          "input_per_million_tokens": 0.08,
 233          "output_per_million_tokens": 0.29
 234        },
 235        "capabilities": {
 236          "function_calling": true,
 237          "vision": false,
 238          "reasoning": false,
 239          "prompt_caching": false,
 240          "response_schema": false
 241        },
 242        "last_updated_at": "2026-04-24"
 243      },
 244      "Qwen/Qwen3-32B": {
 245        "mode": "chat",
 246        "context_window": {
 247          "max_input": 40960,
 248          "max_output": 40960,
 249          "max_tokens": 40960
 250        },
 251        "pricing": {
 252          "input_per_million_tokens": 0.1,
 253          "output_per_million_tokens": 0.28
 254        },
 255        "capabilities": {
 256          "function_calling": true,
 257          "vision": false,
 258          "reasoning": false,
 259          "prompt_caching": false,
 260          "response_schema": false
 261        },
 262        "last_updated_at": "2026-04-24"
 263      },
 264      "Qwen/Qwen3-Coder-480B-A35B-Instruct": {
 265        "mode": "chat",
 266        "context_window": {
 267          "max_input": 262144,
 268          "max_output": 262144,
 269          "max_tokens": 262144
 270        },
 271        "pricing": {
 272          "input_per_million_tokens": 0.4,
 273          "output_per_million_tokens": 1.6
 274        },
 275        "capabilities": {
 276          "function_calling": true,
 277          "vision": false,
 278          "reasoning": false,
 279          "prompt_caching": false,
 280          "response_schema": false
 281        },
 282        "last_updated_at": "2026-04-24"
 283      },
 284      "Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": {
 285        "mode": "chat",
 286        "context_window": {
 287          "max_input": 262144,
 288          "max_output": 262144,
 289          "max_tokens": 262144
 290        },
 291        "pricing": {
 292          "input_per_million_tokens": 0.29,
 293          "output_per_million_tokens": 1.2
 294        },
 295        "capabilities": {
 296          "function_calling": true,
 297          "vision": false,
 298          "reasoning": false,
 299          "prompt_caching": false,
 300          "response_schema": false
 301        },
 302        "last_updated_at": "2026-04-24"
 303      },
 304      "Qwen/Qwen3-Next-80B-A3B-Instruct": {
 305        "mode": "chat",
 306        "context_window": {
 307          "max_input": 262144,
 308          "max_output": 262144,
 309          "max_tokens": 262144
 310        },
 311        "pricing": {
 312          "input_per_million_tokens": 0.14,
 313          "output_per_million_tokens": 1.4
 314        },
 315        "capabilities": {
 316          "function_calling": true,
 317          "vision": false,
 318          "reasoning": false,
 319          "prompt_caching": false,
 320          "response_schema": false
 321        },
 322        "last_updated_at": "2026-04-24"
 323      },
 324      "Qwen/Qwen3-Next-80B-A3B-Thinking": {
 325        "mode": "chat",
 326        "context_window": {
 327          "max_input": 262144,
 328          "max_output": 262144,
 329          "max_tokens": 262144
 330        },
 331        "pricing": {
 332          "input_per_million_tokens": 0.14,
 333          "output_per_million_tokens": 1.4
 334        },
 335        "capabilities": {
 336          "function_calling": true,
 337          "vision": false,
 338          "reasoning": false,
 339          "prompt_caching": false,
 340          "response_schema": false
 341        },
 342        "last_updated_at": "2026-04-24"
 343      },
 344      "Sao10K/L3-8B-Lunaris-v1-Turbo": {
 345        "mode": "chat",
 346        "context_window": {
 347          "max_input": 8192,
 348          "max_output": 8192,
 349          "max_tokens": 8192
 350        },
 351        "pricing": {
 352          "input_per_million_tokens": 0.04,
 353          "output_per_million_tokens": 0.05
 354        },
 355        "capabilities": {
 356          "function_calling": false,
 357          "vision": false,
 358          "reasoning": false,
 359          "prompt_caching": false,
 360          "response_schema": false
 361        },
 362        "last_updated_at": "2026-04-24"
 363      },
 364      "Sao10K/L3.1-70B-Euryale-v2.2": {
 365        "mode": "chat",
 366        "context_window": {
 367          "max_input": 131072,
 368          "max_output": 131072,
 369          "max_tokens": 131072
 370        },
 371        "pricing": {
 372          "input_per_million_tokens": 0.65,
 373          "output_per_million_tokens": 0.75
 374        },
 375        "capabilities": {
 376          "function_calling": false,
 377          "vision": false,
 378          "reasoning": false,
 379          "prompt_caching": false,
 380          "response_schema": false
 381        },
 382        "last_updated_at": "2026-04-24"
 383      },
 384      "Sao10K/L3.3-70B-Euryale-v2.3": {
 385        "mode": "chat",
 386        "context_window": {
 387          "max_input": 131072,
 388          "max_output": 131072,
 389          "max_tokens": 131072
 390        },
 391        "pricing": {
 392          "input_per_million_tokens": 0.65,
 393          "output_per_million_tokens": 0.75
 394        },
 395        "capabilities": {
 396          "function_calling": false,
 397          "vision": false,
 398          "reasoning": false,
 399          "prompt_caching": false,
 400          "response_schema": false
 401        },
 402        "last_updated_at": "2026-04-24"
 403      },
 404      "allenai/olmOCR-7B-0725-FP8": {
 405        "mode": "chat",
 406        "context_window": {
 407          "max_input": 16384,
 408          "max_output": 16384,
 409          "max_tokens": 16384
 410        },
 411        "pricing": {
 412          "input_per_million_tokens": 0.27,
 413          "output_per_million_tokens": 1.5
 414        },
 415        "capabilities": {
 416          "function_calling": false,
 417          "vision": false,
 418          "reasoning": false,
 419          "prompt_caching": false,
 420          "response_schema": false
 421        },
 422        "last_updated_at": "2026-04-24"
 423      },
 424      "anthropic/claude-3-7-sonnet-latest": {
 425        "mode": "chat",
 426        "context_window": {
 427          "max_input": 200000,
 428          "max_output": 200000,
 429          "max_tokens": 200000
 430        },
 431        "pricing": {
 432          "input_per_million_tokens": 3.3,
 433          "output_per_million_tokens": 16.5,
 434          "cache_read_per_million_tokens": 0.33
 435        },
 436        "capabilities": {
 437          "function_calling": true,
 438          "vision": false,
 439          "reasoning": false,
 440          "prompt_caching": false,
 441          "response_schema": false
 442        },
 443        "last_updated_at": "2026-04-24"
 444      },
 445      "anthropic/claude-4-opus": {
 446        "mode": "chat",
 447        "context_window": {
 448          "max_input": 200000,
 449          "max_output": 200000,
 450          "max_tokens": 200000
 451        },
 452        "pricing": {
 453          "input_per_million_tokens": 16.5,
 454          "output_per_million_tokens": 82.5
 455        },
 456        "capabilities": {
 457          "function_calling": true,
 458          "vision": false,
 459          "reasoning": false,
 460          "prompt_caching": false,
 461          "response_schema": false
 462        },
 463        "last_updated_at": "2026-04-24"
 464      },
 465      "anthropic/claude-4-sonnet": {
 466        "mode": "chat",
 467        "context_window": {
 468          "max_input": 200000,
 469          "max_output": 200000,
 470          "max_tokens": 200000
 471        },
 472        "pricing": {
 473          "input_per_million_tokens": 3.3,
 474          "output_per_million_tokens": 16.5
 475        },
 476        "capabilities": {
 477          "function_calling": true,
 478          "vision": false,
 479          "reasoning": false,
 480          "prompt_caching": false,
 481          "response_schema": false
 482        },
 483        "last_updated_at": "2026-04-24"
 484      },
 485      "deepseek-ai/DeepSeek-R1": {
 486        "mode": "chat",
 487        "context_window": {
 488          "max_input": 163840,
 489          "max_output": 163840,
 490          "max_tokens": 163840
 491        },
 492        "pricing": {
 493          "input_per_million_tokens": 0.7,
 494          "output_per_million_tokens": 2.4
 495        },
 496        "capabilities": {
 497          "function_calling": true,
 498          "vision": false,
 499          "reasoning": false,
 500          "prompt_caching": false,
 501          "response_schema": false
 502        },
 503        "last_updated_at": "2026-04-24"
 504      },
 505      "deepseek-ai/DeepSeek-R1-0528": {
 506        "mode": "chat",
 507        "context_window": {
 508          "max_input": 163840,
 509          "max_output": 163840,
 510          "max_tokens": 163840
 511        },
 512        "pricing": {
 513          "input_per_million_tokens": 0.5,
 514          "output_per_million_tokens": 2.15,
 515          "cache_read_per_million_tokens": 0.4
 516        },
 517        "capabilities": {
 518          "function_calling": true,
 519          "vision": false,
 520          "reasoning": false,
 521          "prompt_caching": false,
 522          "response_schema": false
 523        },
 524        "last_updated_at": "2026-04-24"
 525      },
 526      "deepseek-ai/DeepSeek-R1-0528-Turbo": {
 527        "mode": "chat",
 528        "context_window": {
 529          "max_input": 32768,
 530          "max_output": 32768,
 531          "max_tokens": 32768
 532        },
 533        "pricing": {
 534          "input_per_million_tokens": 1.0,
 535          "output_per_million_tokens": 3.0
 536        },
 537        "capabilities": {
 538          "function_calling": true,
 539          "vision": false,
 540          "reasoning": false,
 541          "prompt_caching": false,
 542          "response_schema": false
 543        },
 544        "last_updated_at": "2026-04-24"
 545      },
 546      "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
 547        "mode": "chat",
 548        "context_window": {
 549          "max_input": 131072,
 550          "max_output": 131072,
 551          "max_tokens": 131072
 552        },
 553        "pricing": {
 554          "input_per_million_tokens": 0.2,
 555          "output_per_million_tokens": 0.6
 556        },
 557        "capabilities": {
 558          "function_calling": false,
 559          "vision": false,
 560          "reasoning": false,
 561          "prompt_caching": false,
 562          "response_schema": false
 563        },
 564        "last_updated_at": "2026-04-24"
 565      },
 566      "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
 567        "mode": "chat",
 568        "context_window": {
 569          "max_input": 131072,
 570          "max_output": 131072,
 571          "max_tokens": 131072
 572        },
 573        "pricing": {
 574          "input_per_million_tokens": 0.27,
 575          "output_per_million_tokens": 0.27
 576        },
 577        "capabilities": {
 578          "function_calling": true,
 579          "vision": false,
 580          "reasoning": false,
 581          "prompt_caching": false,
 582          "response_schema": false
 583        },
 584        "last_updated_at": "2026-04-24"
 585      },
 586      "deepseek-ai/DeepSeek-R1-Turbo": {
 587        "mode": "chat",
 588        "context_window": {
 589          "max_input": 40960,
 590          "max_output": 40960,
 591          "max_tokens": 40960
 592        },
 593        "pricing": {
 594          "input_per_million_tokens": 1.0,
 595          "output_per_million_tokens": 3.0
 596        },
 597        "capabilities": {
 598          "function_calling": true,
 599          "vision": false,
 600          "reasoning": false,
 601          "prompt_caching": false,
 602          "response_schema": false
 603        },
 604        "last_updated_at": "2026-04-24"
 605      },
 606      "deepseek-ai/DeepSeek-V3": {
 607        "mode": "chat",
 608        "context_window": {
 609          "max_input": 163840,
 610          "max_output": 163840,
 611          "max_tokens": 163840
 612        },
 613        "pricing": {
 614          "input_per_million_tokens": 0.38,
 615          "output_per_million_tokens": 0.89
 616        },
 617        "capabilities": {
 618          "function_calling": true,
 619          "vision": false,
 620          "reasoning": false,
 621          "prompt_caching": false,
 622          "response_schema": false
 623        },
 624        "last_updated_at": "2026-04-24"
 625      },
 626      "deepseek-ai/DeepSeek-V3-0324": {
 627        "mode": "chat",
 628        "context_window": {
 629          "max_input": 163840,
 630          "max_output": 163840,
 631          "max_tokens": 163840
 632        },
 633        "pricing": {
 634          "input_per_million_tokens": 0.25,
 635          "output_per_million_tokens": 0.88
 636        },
 637        "capabilities": {
 638          "function_calling": true,
 639          "vision": false,
 640          "reasoning": false,
 641          "prompt_caching": false,
 642          "response_schema": false
 643        },
 644        "last_updated_at": "2026-04-24"
 645      },
 646      "deepseek-ai/DeepSeek-V3.1": {
 647        "mode": "chat",
 648        "context_window": {
 649          "max_input": 163840,
 650          "max_output": 163840,
 651          "max_tokens": 163840
 652        },
 653        "pricing": {
 654          "input_per_million_tokens": 0.27,
 655          "output_per_million_tokens": 1.0,
 656          "cache_read_per_million_tokens": 0.216
 657        },
 658        "capabilities": {
 659          "function_calling": true,
 660          "vision": false,
 661          "reasoning": true,
 662          "prompt_caching": false,
 663          "response_schema": false
 664        },
 665        "last_updated_at": "2026-04-24"
 666      },
 667      "deepseek-ai/DeepSeek-V3.1-Terminus": {
 668        "mode": "chat",
 669        "context_window": {
 670          "max_input": 163840,
 671          "max_output": 163840,
 672          "max_tokens": 163840
 673        },
 674        "pricing": {
 675          "input_per_million_tokens": 0.27,
 676          "output_per_million_tokens": 1.0,
 677          "cache_read_per_million_tokens": 0.216
 678        },
 679        "capabilities": {
 680          "function_calling": true,
 681          "vision": false,
 682          "reasoning": false,
 683          "prompt_caching": false,
 684          "response_schema": false
 685        },
 686        "last_updated_at": "2026-04-24"
 687      },
 688      "google/gemini-2.0-flash-001": {
 689        "mode": "chat",
 690        "context_window": {
 691          "max_input": 1000000,
 692          "max_output": 1000000,
 693          "max_tokens": 1000000
 694        },
 695        "pricing": {
 696          "input_per_million_tokens": 0.1,
 697          "output_per_million_tokens": 0.4
 698        },
 699        "capabilities": {
 700          "function_calling": true,
 701          "vision": false,
 702          "reasoning": false,
 703          "prompt_caching": false,
 704          "response_schema": false
 705        },
 706        "deprecation_date": "2026-06-01",
 707        "last_updated_at": "2026-04-24"
 708      },
 709      "google/gemini-2.5-flash": {
 710        "mode": "chat",
 711        "context_window": {
 712          "max_input": 1000000,
 713          "max_output": 1000000,
 714          "max_tokens": 1000000
 715        },
 716        "pricing": {
 717          "input_per_million_tokens": 0.3,
 718          "output_per_million_tokens": 2.5
 719        },
 720        "capabilities": {
 721          "function_calling": true,
 722          "vision": false,
 723          "reasoning": false,
 724          "prompt_caching": false,
 725          "response_schema": false
 726        },
 727        "last_updated_at": "2026-04-24"
 728      },
 729      "google/gemini-2.5-pro": {
 730        "mode": "chat",
 731        "context_window": {
 732          "max_input": 1000000,
 733          "max_output": 1000000,
 734          "max_tokens": 1000000
 735        },
 736        "pricing": {
 737          "input_per_million_tokens": 1.25,
 738          "output_per_million_tokens": 10.0
 739        },
 740        "capabilities": {
 741          "function_calling": true,
 742          "vision": false,
 743          "reasoning": false,
 744          "prompt_caching": false,
 745          "response_schema": false
 746        },
 747        "last_updated_at": "2026-04-24"
 748      },
 749      "google/gemma-3-12b-it": {
 750        "mode": "chat",
 751        "context_window": {
 752          "max_input": 131072,
 753          "max_output": 131072,
 754          "max_tokens": 131072
 755        },
 756        "pricing": {
 757          "input_per_million_tokens": 0.05,
 758          "output_per_million_tokens": 0.1
 759        },
 760        "capabilities": {
 761          "function_calling": true,
 762          "vision": false,
 763          "reasoning": false,
 764          "prompt_caching": false,
 765          "response_schema": false
 766        },
 767        "last_updated_at": "2026-04-24"
 768      },
 769      "google/gemma-3-27b-it": {
 770        "mode": "chat",
 771        "context_window": {
 772          "max_input": 131072,
 773          "max_output": 131072,
 774          "max_tokens": 131072
 775        },
 776        "pricing": {
 777          "input_per_million_tokens": 0.09,
 778          "output_per_million_tokens": 0.16
 779        },
 780        "capabilities": {
 781          "function_calling": true,
 782          "vision": false,
 783          "reasoning": false,
 784          "prompt_caching": false,
 785          "response_schema": false
 786        },
 787        "last_updated_at": "2026-04-24"
 788      },
 789      "google/gemma-3-4b-it": {
 790        "mode": "chat",
 791        "context_window": {
 792          "max_input": 131072,
 793          "max_output": 131072,
 794          "max_tokens": 131072
 795        },
 796        "pricing": {
 797          "input_per_million_tokens": 0.04,
 798          "output_per_million_tokens": 0.08
 799        },
 800        "capabilities": {
 801          "function_calling": true,
 802          "vision": false,
 803          "reasoning": false,
 804          "prompt_caching": false,
 805          "response_schema": false
 806        },
 807        "last_updated_at": "2026-04-24"
 808      },
 809      "meta-llama/Llama-3.2-11B-Vision-Instruct": {
 810        "mode": "chat",
 811        "context_window": {
 812          "max_input": 131072,
 813          "max_output": 131072,
 814          "max_tokens": 131072
 815        },
 816        "pricing": {
 817          "input_per_million_tokens": 0.049,
 818          "output_per_million_tokens": 0.049
 819        },
 820        "capabilities": {
 821          "function_calling": false,
 822          "vision": false,
 823          "reasoning": false,
 824          "prompt_caching": false,
 825          "response_schema": false
 826        },
 827        "last_updated_at": "2026-04-24"
 828      },
 829      "meta-llama/Llama-3.2-3B-Instruct": {
 830        "mode": "chat",
 831        "context_window": {
 832          "max_input": 131072,
 833          "max_output": 131072,
 834          "max_tokens": 131072
 835        },
 836        "pricing": {
 837          "input_per_million_tokens": 0.02,
 838          "output_per_million_tokens": 0.02
 839        },
 840        "capabilities": {
 841          "function_calling": true,
 842          "vision": false,
 843          "reasoning": false,
 844          "prompt_caching": false,
 845          "response_schema": false
 846        },
 847        "last_updated_at": "2026-04-24"
 848      },
 849      "meta-llama/Llama-3.3-70B-Instruct": {
 850        "mode": "chat",
 851        "context_window": {
 852          "max_input": 131072,
 853          "max_output": 131072,
 854          "max_tokens": 131072
 855        },
 856        "pricing": {
 857          "input_per_million_tokens": 0.23,
 858          "output_per_million_tokens": 0.4
 859        },
 860        "capabilities": {
 861          "function_calling": true,
 862          "vision": false,
 863          "reasoning": false,
 864          "prompt_caching": false,
 865          "response_schema": false
 866        },
 867        "last_updated_at": "2026-04-24"
 868      },
 869      "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
 870        "mode": "chat",
 871        "context_window": {
 872          "max_input": 131072,
 873          "max_output": 131072,
 874          "max_tokens": 131072
 875        },
 876        "pricing": {
 877          "input_per_million_tokens": 0.13,
 878          "output_per_million_tokens": 0.39
 879        },
 880        "capabilities": {
 881          "function_calling": true,
 882          "vision": false,
 883          "reasoning": false,
 884          "prompt_caching": false,
 885          "response_schema": false
 886        },
 887        "last_updated_at": "2026-04-24"
 888      },
 889      "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": {
 890        "mode": "chat",
 891        "context_window": {
 892          "max_input": 1048576,
 893          "max_output": 1048576,
 894          "max_tokens": 1048576
 895        },
 896        "pricing": {
 897          "input_per_million_tokens": 0.15,
 898          "output_per_million_tokens": 0.6
 899        },
 900        "capabilities": {
 901          "function_calling": true,
 902          "vision": false,
 903          "reasoning": false,
 904          "prompt_caching": false,
 905          "response_schema": false
 906        },
 907        "last_updated_at": "2026-04-24"
 908      },
 909      "meta-llama/Llama-4-Scout-17B-16E-Instruct": {
 910        "mode": "chat",
 911        "context_window": {
 912          "max_input": 327680,
 913          "max_output": 327680,
 914          "max_tokens": 327680
 915        },
 916        "pricing": {
 917          "input_per_million_tokens": 0.08,
 918          "output_per_million_tokens": 0.3
 919        },
 920        "capabilities": {
 921          "function_calling": true,
 922          "vision": false,
 923          "reasoning": false,
 924          "prompt_caching": false,
 925          "response_schema": false
 926        },
 927        "last_updated_at": "2026-04-24"
 928      },
 929      "meta-llama/Llama-Guard-3-8B": {
 930        "mode": "chat",
 931        "context_window": {
 932          "max_input": 131072,
 933          "max_output": 131072,
 934          "max_tokens": 131072
 935        },
 936        "pricing": {
 937          "input_per_million_tokens": 0.055,
 938          "output_per_million_tokens": 0.055
 939        },
 940        "capabilities": {
 941          "function_calling": false,
 942          "vision": false,
 943          "reasoning": false,
 944          "prompt_caching": false,
 945          "response_schema": false
 946        },
 947        "last_updated_at": "2026-04-24"
 948      },
 949      "meta-llama/Llama-Guard-4-12B": {
 950        "mode": "chat",
 951        "context_window": {
 952          "max_input": 163840,
 953          "max_output": 163840,
 954          "max_tokens": 163840
 955        },
 956        "pricing": {
 957          "input_per_million_tokens": 0.18,
 958          "output_per_million_tokens": 0.18
 959        },
 960        "capabilities": {
 961          "function_calling": false,
 962          "vision": false,
 963          "reasoning": false,
 964          "prompt_caching": false,
 965          "response_schema": false
 966        },
 967        "last_updated_at": "2026-04-24"
 968      },
 969      "meta-llama/Meta-Llama-3-8B-Instruct": {
 970        "mode": "chat",
 971        "context_window": {
 972          "max_input": 8192,
 973          "max_output": 8192,
 974          "max_tokens": 8192
 975        },
 976        "pricing": {
 977          "input_per_million_tokens": 0.03,
 978          "output_per_million_tokens": 0.06
 979        },
 980        "capabilities": {
 981          "function_calling": true,
 982          "vision": false,
 983          "reasoning": false,
 984          "prompt_caching": false,
 985          "response_schema": false
 986        },
 987        "last_updated_at": "2026-04-24"
 988      },
 989      "meta-llama/Meta-Llama-3.1-70B-Instruct": {
 990        "mode": "chat",
 991        "context_window": {
 992          "max_input": 131072,
 993          "max_output": 131072,
 994          "max_tokens": 131072
 995        },
 996        "pricing": {
 997          "input_per_million_tokens": 0.4,
 998          "output_per_million_tokens": 0.4
 999        },
1000        "capabilities": {
1001          "function_calling": true,
1002          "vision": false,
1003          "reasoning": false,
1004          "prompt_caching": false,
1005          "response_schema": false
1006        },
1007        "last_updated_at": "2026-04-24"
1008      },
1009      "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": {
1010        "mode": "chat",
1011        "context_window": {
1012          "max_input": 131072,
1013          "max_output": 131072,
1014          "max_tokens": 131072
1015        },
1016        "pricing": {
1017          "input_per_million_tokens": 0.1,
1018          "output_per_million_tokens": 0.28
1019        },
1020        "capabilities": {
1021          "function_calling": true,
1022          "vision": false,
1023          "reasoning": false,
1024          "prompt_caching": false,
1025          "response_schema": false
1026        },
1027        "last_updated_at": "2026-04-24"
1028      },
1029      "meta-llama/Meta-Llama-3.1-8B-Instruct": {
1030        "mode": "chat",
1031        "context_window": {
1032          "max_input": 131072,
1033          "max_output": 131072,
1034          "max_tokens": 131072
1035        },
1036        "pricing": {
1037          "input_per_million_tokens": 0.03,
1038          "output_per_million_tokens": 0.05
1039        },
1040        "capabilities": {
1041          "function_calling": true,
1042          "vision": false,
1043          "reasoning": false,
1044          "prompt_caching": false,
1045          "response_schema": false
1046        },
1047        "last_updated_at": "2026-04-24"
1048      },
1049      "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": {
1050        "mode": "chat",
1051        "context_window": {
1052          "max_input": 131072,
1053          "max_output": 131072,
1054          "max_tokens": 131072
1055        },
1056        "pricing": {
1057          "input_per_million_tokens": 0.02,
1058          "output_per_million_tokens": 0.03
1059        },
1060        "capabilities": {
1061          "function_calling": true,
1062          "vision": false,
1063          "reasoning": false,
1064          "prompt_caching": false,
1065          "response_schema": false
1066        },
1067        "last_updated_at": "2026-04-24"
1068      },
1069      "microsoft/WizardLM-2-8x22B": {
1070        "mode": "chat",
1071        "context_window": {
1072          "max_input": 65536,
1073          "max_output": 65536,
1074          "max_tokens": 65536
1075        },
1076        "pricing": {
1077          "input_per_million_tokens": 0.48,
1078          "output_per_million_tokens": 0.48
1079        },
1080        "capabilities": {
1081          "function_calling": false,
1082          "vision": false,
1083          "reasoning": false,
1084          "prompt_caching": false,
1085          "response_schema": false
1086        },
1087        "last_updated_at": "2026-04-24"
1088      },
1089      "microsoft/phi-4": {
1090        "mode": "chat",
1091        "context_window": {
1092          "max_input": 16384,
1093          "max_output": 16384,
1094          "max_tokens": 16384
1095        },
1096        "pricing": {
1097          "input_per_million_tokens": 0.07,
1098          "output_per_million_tokens": 0.14
1099        },
1100        "capabilities": {
1101          "function_calling": true,
1102          "vision": false,
1103          "reasoning": false,
1104          "prompt_caching": false,
1105          "response_schema": false
1106        },
1107        "last_updated_at": "2026-04-24"
1108      },
1109      "mistralai/Mistral-Nemo-Instruct-2407": {
1110        "mode": "chat",
1111        "context_window": {
1112          "max_input": 131072,
1113          "max_output": 131072,
1114          "max_tokens": 131072
1115        },
1116        "pricing": {
1117          "input_per_million_tokens": 0.02,
1118          "output_per_million_tokens": 0.04
1119        },
1120        "capabilities": {
1121          "function_calling": true,
1122          "vision": false,
1123          "reasoning": false,
1124          "prompt_caching": false,
1125          "response_schema": false
1126        },
1127        "last_updated_at": "2026-04-24"
1128      },
1129      "mistralai/Mistral-Small-24B-Instruct-2501": {
1130        "mode": "chat",
1131        "context_window": {
1132          "max_input": 32768,
1133          "max_output": 32768,
1134          "max_tokens": 32768
1135        },
1136        "pricing": {
1137          "input_per_million_tokens": 0.05,
1138          "output_per_million_tokens": 0.08
1139        },
1140        "capabilities": {
1141          "function_calling": true,
1142          "vision": false,
1143          "reasoning": false,
1144          "prompt_caching": false,
1145          "response_schema": false
1146        },
1147        "last_updated_at": "2026-04-24"
1148      },
1149      "mistralai/Mistral-Small-3.2-24B-Instruct-2506": {
1150        "mode": "chat",
1151        "context_window": {
1152          "max_input": 128000,
1153          "max_output": 128000,
1154          "max_tokens": 128000
1155        },
1156        "pricing": {
1157          "input_per_million_tokens": 0.075,
1158          "output_per_million_tokens": 0.2
1159        },
1160        "capabilities": {
1161          "function_calling": true,
1162          "vision": false,
1163          "reasoning": false,
1164          "prompt_caching": false,
1165          "response_schema": false
1166        },
1167        "last_updated_at": "2026-04-24"
1168      },
1169      "mistralai/Mixtral-8x7B-Instruct-v0.1": {
1170        "mode": "chat",
1171        "context_window": {
1172          "max_input": 32768,
1173          "max_output": 32768,
1174          "max_tokens": 32768
1175        },
1176        "pricing": {
1177          "input_per_million_tokens": 0.4,
1178          "output_per_million_tokens": 0.4
1179        },
1180        "capabilities": {
1181          "function_calling": true,
1182          "vision": false,
1183          "reasoning": false,
1184          "prompt_caching": false,
1185          "response_schema": false
1186        },
1187        "last_updated_at": "2026-04-24"
1188      },
1189      "moonshotai/Kimi-K2-Instruct": {
1190        "mode": "chat",
1191        "context_window": {
1192          "max_input": 131072,
1193          "max_output": 131072,
1194          "max_tokens": 131072
1195        },
1196        "pricing": {
1197          "input_per_million_tokens": 0.5,
1198          "output_per_million_tokens": 2.0
1199        },
1200        "capabilities": {
1201          "function_calling": true,
1202          "vision": false,
1203          "reasoning": false,
1204          "prompt_caching": false,
1205          "response_schema": false
1206        },
1207        "last_updated_at": "2026-04-24"
1208      },
1209      "moonshotai/Kimi-K2-Instruct-0905": {
1210        "mode": "chat",
1211        "context_window": {
1212          "max_input": 262144,
1213          "max_output": 262144,
1214          "max_tokens": 262144
1215        },
1216        "pricing": {
1217          "input_per_million_tokens": 0.5,
1218          "output_per_million_tokens": 2.0,
1219          "cache_read_per_million_tokens": 0.4
1220        },
1221        "capabilities": {
1222          "function_calling": true,
1223          "vision": false,
1224          "reasoning": false,
1225          "prompt_caching": false,
1226          "response_schema": false
1227        },
1228        "last_updated_at": "2026-04-24"
1229      },
1230      "nvidia/Llama-3.1-Nemotron-70B-Instruct": {
1231        "mode": "chat",
1232        "context_window": {
1233          "max_input": 131072,
1234          "max_output": 131072,
1235          "max_tokens": 131072
1236        },
1237        "pricing": {
1238          "input_per_million_tokens": 0.6,
1239          "output_per_million_tokens": 0.6
1240        },
1241        "capabilities": {
1242          "function_calling": true,
1243          "vision": false,
1244          "reasoning": false,
1245          "prompt_caching": false,
1246          "response_schema": false
1247        },
1248        "last_updated_at": "2026-04-24"
1249      },
1250      "nvidia/Llama-3.3-Nemotron-Super-49B-v1.5": {
1251        "mode": "chat",
1252        "context_window": {
1253          "max_input": 131072,
1254          "max_output": 131072,
1255          "max_tokens": 131072
1256        },
1257        "pricing": {
1258          "input_per_million_tokens": 0.1,
1259          "output_per_million_tokens": 0.4
1260        },
1261        "capabilities": {
1262          "function_calling": true,
1263          "vision": false,
1264          "reasoning": false,
1265          "prompt_caching": false,
1266          "response_schema": false
1267        },
1268        "last_updated_at": "2026-04-24"
1269      },
1270      "nvidia/NVIDIA-Nemotron-Nano-9B-v2": {
1271        "mode": "chat",
1272        "context_window": {
1273          "max_input": 131072,
1274          "max_output": 131072,
1275          "max_tokens": 131072
1276        },
1277        "pricing": {
1278          "input_per_million_tokens": 0.04,
1279          "output_per_million_tokens": 0.16
1280        },
1281        "capabilities": {
1282          "function_calling": true,
1283          "vision": false,
1284          "reasoning": false,
1285          "prompt_caching": false,
1286          "response_schema": false
1287        },
1288        "last_updated_at": "2026-04-24"
1289      },
1290      "openai/gpt-oss-120b": {
1291        "mode": "chat",
1292        "context_window": {
1293          "max_input": 131072,
1294          "max_output": 131072,
1295          "max_tokens": 131072
1296        },
1297        "pricing": {
1298          "input_per_million_tokens": 0.05,
1299          "output_per_million_tokens": 0.45
1300        },
1301        "capabilities": {
1302          "function_calling": true,
1303          "vision": false,
1304          "reasoning": false,
1305          "prompt_caching": false,
1306          "response_schema": false
1307        },
1308        "last_updated_at": "2026-04-24"
1309      },
1310      "openai/gpt-oss-20b": {
1311        "mode": "chat",
1312        "context_window": {
1313          "max_input": 131072,
1314          "max_output": 131072,
1315          "max_tokens": 131072
1316        },
1317        "pricing": {
1318          "input_per_million_tokens": 0.04,
1319          "output_per_million_tokens": 0.15
1320        },
1321        "capabilities": {
1322          "function_calling": true,
1323          "vision": false,
1324          "reasoning": false,
1325          "prompt_caching": false,
1326          "response_schema": false
1327        },
1328        "last_updated_at": "2026-04-24"
1329      },
1330      "zai-org/GLM-4.5": {
1331        "mode": "chat",
1332        "context_window": {
1333          "max_input": 131072,
1334          "max_output": 131072,
1335          "max_tokens": 131072
1336        },
1337        "pricing": {
1338          "input_per_million_tokens": 0.4,
1339          "output_per_million_tokens": 1.6
1340        },
1341        "capabilities": {
1342          "function_calling": true,
1343          "vision": false,
1344          "reasoning": false,
1345          "prompt_caching": false,
1346          "response_schema": false
1347        },
1348        "last_updated_at": "2026-04-24"
1349      }
1350    }
1351  }