|
5 | 5 | "name": "Cohere", |
6 | 6 | "category": "provider_api", |
7 | 7 | "country": "CA", |
8 | | - "flag": "🇨🇦", |
| 8 | + "flag": "\ud83c\udde8\ud83c\udde6", |
9 | 9 | "url": "https://dashboard.cohere.com/api-keys", |
10 | 10 | "baseUrl": "https://api.cohere.com/v2", |
11 | 11 | "description": "Free \"Trial\" API key, no credit card. 1,000 API calls/month. Non-commercial use only.", |
|
36 | 36 | "rateLimit": "20 RPM" |
37 | 37 | }, |
38 | 38 | { |
39 | | - "id": "command-r7b", |
| 39 | + "id": "command-r7b-12-2024", |
40 | 40 | "name": "Command R7B", |
41 | 41 | "context": "128K", |
42 | 42 | "maxOutput": "4K", |
|
46 | 46 | { |
47 | 47 | "id": "embed-v4.0", |
48 | 48 | "name": "Embed 4", |
49 | | - "context": "—", |
50 | | - "maxOutput": "—", |
| 49 | + "context": "\u2014", |
| 50 | + "maxOutput": "\u2014", |
51 | 51 | "modality": "Embeddings (Text + Image)", |
52 | 52 | "rateLimit": "2,000 inputs/min" |
53 | 53 | }, |
54 | 54 | { |
55 | 55 | "id": "rerank-v3.5", |
56 | 56 | "name": "Rerank 3.5", |
57 | | - "context": "—", |
58 | | - "maxOutput": "—", |
| 57 | + "context": "\u2014", |
| 58 | + "maxOutput": "\u2014", |
59 | 59 | "modality": "Reranking", |
60 | 60 | "rateLimit": "10 RPM" |
61 | 61 | } |
|
65 | 65 | "name": "Google Gemini", |
66 | 66 | "category": "provider_api", |
67 | 67 | "country": "US", |
68 | | - "flag": "🇺🇸", |
| 68 | + "flag": "\ud83c\uddfa\ud83c\uddf8", |
69 | 69 | "url": "https://aistudio.google.com/app/apikey", |
70 | 70 | "baseUrl": "https://generativelanguage.googleapis.com/v1beta", |
71 | 71 | "description": "Free tier unavailable in EU/UK/Switzerland. Free-tier prompts may be used by Google to improve products.", |
|
93 | 93 | "name": "Mistral AI", |
94 | 94 | "category": "provider_api", |
95 | 95 | "country": "FR", |
96 | | - "flag": "🇫🇷", |
| 96 | + "flag": "\ud83c\uddeb\ud83c\uddf7", |
97 | 97 | "url": "https://console.mistral.ai/api-keys", |
98 | 98 | "baseUrl": "https://api.mistral.ai/v1", |
99 | 99 | "description": "Free \"Experiment\" plan, no credit card. ~1B tokens/month.", |
|
116 | 116 | "rateLimit": "~1 RPS, 500K TPM" |
117 | 117 | }, |
118 | 118 | { |
119 | | - "id": "mistral-large-latest", |
| 119 | + "id": "mistral-large-2411", |
120 | 120 | "name": "Mistral Large 3", |
121 | 121 | "context": "256K", |
122 | 122 | "maxOutput": "256K", |
|
132 | 132 | "rateLimit": "~1 RPS, 500K TPM" |
133 | 133 | }, |
134 | 134 | { |
135 | | - "id": "codestral-latest", |
| 135 | + "id": "codestral-2501", |
136 | 136 | "name": "Codestral", |
137 | 137 | "context": "256K", |
138 | 138 | "maxOutput": "256K", |
139 | 139 | "modality": "Code", |
140 | 140 | "rateLimit": "~1 RPS, 500K TPM" |
141 | 141 | }, |
142 | 142 | { |
143 | | - "id": "pixtral-large-latest", |
| 143 | + "id": "pixtral-large-2411", |
144 | 144 | "name": "Pixtral Large", |
145 | 145 | "context": "128K", |
146 | 146 | "maxOutput": "128K", |
|
153 | 153 | "name": "Z AI (Zhipu AI)", |
154 | 154 | "category": "provider_api", |
155 | 155 | "country": "CN", |
156 | | - "flag": "🇨🇳", |
| 156 | + "flag": "\ud83c\udde8\ud83c\uddf3", |
157 | 157 | "url": "https://open.bigmodel.cn/usercenter/apikeys", |
158 | 158 | "baseUrl": "https://open.bigmodel.cn/api/paas/v4", |
159 | 159 | "description": "Permanent free models, no credit card required.", |
|
189 | 189 | "name": "Cerebras", |
190 | 190 | "category": "inference_provider", |
191 | 191 | "country": "US", |
192 | | - "flag": "🇺🇸", |
| 192 | + "flag": "\ud83c\uddfa\ud83c\uddf8", |
193 | 193 | "url": "https://cloud.cerebras.ai/", |
194 | 194 | "baseUrl": "https://api.cerebras.ai/v1", |
195 | 195 | "description": "Free tier, no credit card. Ultra-fast inference (~2,600 tok/s). 1M tokens/day cap.", |
|
233 | 233 | "name": "Cloudflare Workers AI", |
234 | 234 | "category": "inference_provider", |
235 | 235 | "country": "US", |
236 | | - "flag": "🇺🇸", |
| 236 | + "flag": "\ud83c\uddfa\ud83c\uddf8", |
237 | 237 | "url": "https://dash.cloudflare.com/profile/api-tokens", |
238 | 238 | "baseUrl": "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run", |
239 | 239 | "description": "10,000 Neurons/day free. 50+ models available on free tier.", |
|
317 | 317 | "name": "GitHub Models", |
318 | 318 | "category": "inference_provider", |
319 | 319 | "country": "US", |
320 | | - "flag": "🇺🇸", |
| 320 | + "flag": "\ud83c\uddfa\ud83c\uddf8", |
321 | 321 | "url": "https://github.com/marketplace/models", |
322 | 322 | "baseUrl": "https://models.inference.ai.azure.com", |
323 | 323 | "description": "Free prototyping for all GitHub users. 45+ models. Per-request limits (8K in / 4K out).", |
|
364 | 364 | "rateLimit": "10 RPM, 50 RPD" |
365 | 365 | }, |
366 | 366 | { |
367 | | - "id": "Llama-4-Scout-17B-16E-Instruct", |
| 367 | + "id": "Llama-4-Scout-17B-16E", |
368 | 368 | "name": "Llama-4-Scout-17B-16E", |
369 | 369 | "context": "512K", |
370 | 370 | "maxOutput": "~4K", |
371 | 371 | "modality": "Text + Vision", |
372 | 372 | "rateLimit": "15 RPM, 150 RPD" |
373 | 373 | }, |
374 | 374 | { |
375 | | - "id": "Llama-4-Maverick-17B-128E-Instruct", |
| 375 | + "id": "Llama-4-Maverick-17B-128E", |
376 | 376 | "name": "Llama-4-Maverick-17B-128E", |
377 | 377 | "context": "256K", |
378 | 378 | "maxOutput": "~4K", |
379 | 379 | "modality": "Text + Vision", |
380 | 380 | "rateLimit": "10 RPM, 50 RPD" |
381 | 381 | }, |
382 | 382 | { |
383 | | - "id": "Meta-Llama-3.3-70B-Instruct", |
| 383 | + "id": "Meta-Llama-3.3-70B", |
384 | 384 | "name": "Meta-Llama-3.3-70B", |
385 | 385 | "context": "131K", |
386 | 386 | "maxOutput": "~4K", |
|
396 | 396 | "rateLimit": "15 RPM, 150 RPD" |
397 | 397 | }, |
398 | 398 | { |
399 | | - "id": "Mistral-Small-3.1-24B-Instruct", |
| 399 | + "id": "Mistral-Small-3.1", |
400 | 400 | "name": "Mistral-Small-3.1", |
401 | 401 | "context": "128K", |
402 | 402 | "maxOutput": "~4K", |
|
417 | 417 | "name": "Groq", |
418 | 418 | "category": "inference_provider", |
419 | 419 | "country": "US", |
420 | | - "flag": "🇺🇸", |
| 420 | + "flag": "\ud83c\uddfa\ud83c\uddf8", |
421 | 421 | "url": "https://console.groq.com/keys", |
422 | 422 | "baseUrl": "https://api.groq.com/openai/v1", |
423 | 423 | "description": "Free tier, no credit card. Ultra-fast LPU inference.", |
|
490 | 490 | { |
491 | 491 | "id": "whisper-large-v3", |
492 | 492 | "name": "whisper-large-v3", |
493 | | - "context": "—", |
494 | | - "maxOutput": "—", |
495 | | - "modality": "Audio → Text", |
| 493 | + "context": "\u2014", |
| 494 | + "maxOutput": "\u2014", |
| 495 | + "modality": "Audio \u2192 Text", |
496 | 496 | "rateLimit": "20 RPM, 2,000 RPD" |
497 | 497 | }, |
498 | 498 | { |
499 | 499 | "id": "whisper-large-v3-turbo", |
500 | 500 | "name": "whisper-large-v3-turbo", |
501 | | - "context": "—", |
502 | | - "maxOutput": "—", |
503 | | - "modality": "Audio → Text", |
| 501 | + "context": "\u2014", |
| 502 | + "maxOutput": "\u2014", |
| 503 | + "modality": "Audio \u2192 Text", |
504 | 504 | "rateLimit": "20 RPM, 2,000 RPD" |
505 | 505 | } |
506 | 506 | ] |
|
509 | 509 | "name": "Hugging Face", |
510 | 510 | "category": "inference_provider", |
511 | 511 | "country": "US", |
512 | | - "flag": "🇺🇸", |
| 512 | + "flag": "\ud83c\uddfa\ud83c\uddf8", |
513 | 513 | "url": "https://huggingface.co/settings/tokens", |
514 | 514 | "baseUrl": "https://api-inference.huggingface.co/models", |
515 | 515 | "description": "Free Serverless Inference API + ~$0.10/month free credits. Thousands of models.", |
|
569 | 569 | "name": "Kilo Code", |
570 | 570 | "category": "inference_provider", |
571 | 571 | "country": "US", |
572 | | - "flag": "🇺🇸", |
| 572 | + "flag": "\ud83c\uddfa\ud83c\uddf8", |
573 | 573 | "url": "https://kilo.ai", |
574 | 574 | "baseUrl": "https://api.kilo.ai/api/gateway", |
575 | 575 | "description": "Free models with no credit card required. `kilo-auto/free` auto-router routes to minimax/minimax-m2.5:free (80%) and stepfun/step-3.5-flash:free (20%).", |
|
578 | 578 | { |
579 | 579 | "id": "bytedance-seed/dola-seed-2.0-pro:free", |
580 | 580 | "name": "bytedance-seed/dola-seed-2.0-pro:free", |
581 | | - "context": "—", |
582 | | - "maxOutput": "—", |
| 581 | + "context": "\u2014", |
| 582 | + "maxOutput": "\u2014", |
583 | 583 | "modality": "Text", |
584 | 584 | "rateLimit": "~200 req/hr" |
585 | 585 | }, |
586 | 586 | { |
587 | 587 | "id": "x-ai/grok-code-fast-1:optimized:free", |
588 | 588 | "name": "x-ai/grok-code-fast-1:optimized:free", |
589 | | - "context": "—", |
590 | | - "maxOutput": "—", |
| 589 | + "context": "\u2014", |
| 590 | + "maxOutput": "\u2014", |
591 | 591 | "modality": "Text (code)", |
592 | 592 | "rateLimit": "~200 req/hr" |
593 | 593 | }, |
|
602 | 602 | { |
603 | 603 | "id": "arcee-ai/trinity-large-thinking:free", |
604 | 604 | "name": "arcee-ai/trinity-large-thinking:free", |
605 | | - "context": "—", |
606 | | - "maxOutput": "—", |
| 605 | + "context": "\u2014", |
| 606 | + "maxOutput": "\u2014", |
607 | 607 | "modality": "Text (reasoning)", |
608 | 608 | "rateLimit": "~200 req/hr" |
609 | 609 | }, |
|
621 | 621 | "name": "LLM7.io", |
622 | 622 | "category": "inference_provider", |
623 | 623 | "country": "GB", |
624 | | - "flag": "🇬🇧", |
| 624 | + "flag": "\ud83c\uddec\ud83c\udde7", |
625 | 625 | "url": "https://token.llm7.io", |
626 | 626 | "baseUrl": "https://api.llm7.io/v1", |
627 | 627 | "description": "Zero-friction API gateway. No registration needed for basic access. 30+ models.", |
|
630 | 630 | { |
631 | 631 | "id": "deepseek-r1-0528", |
632 | 632 | "name": "deepseek-r1-0528", |
633 | | - "context": "—", |
634 | | - "maxOutput": "—", |
| 633 | + "context": "\u2014", |
| 634 | + "maxOutput": "\u2014", |
635 | 635 | "modality": "Text (reasoning)", |
636 | 636 | "rateLimit": "30 RPM (120 with token)" |
637 | 637 | }, |
638 | 638 | { |
639 | 639 | "id": "deepseek-v3-0324", |
640 | 640 | "name": "deepseek-v3-0324", |
641 | | - "context": "—", |
642 | | - "maxOutput": "—", |
| 641 | + "context": "\u2014", |
| 642 | + "maxOutput": "\u2014", |
643 | 643 | "modality": "Text", |
644 | 644 | "rateLimit": "30 RPM (120 with token)" |
645 | 645 | }, |
646 | 646 | { |
647 | 647 | "id": "gemini-2.5-flash-lite", |
648 | 648 | "name": "gemini-2.5-flash-lite", |
649 | | - "context": "—", |
650 | | - "maxOutput": "—", |
| 649 | + "context": "\u2014", |
| 650 | + "maxOutput": "\u2014", |
651 | 651 | "modality": "Text + Vision", |
652 | 652 | "rateLimit": "30 RPM (120 with token)" |
653 | 653 | }, |
654 | 654 | { |
655 | 655 | "id": "gpt-4o-mini", |
656 | 656 | "name": "gpt-4o-mini", |
657 | | - "context": "—", |
658 | | - "maxOutput": "—", |
| 657 | + "context": "\u2014", |
| 658 | + "maxOutput": "\u2014", |
659 | 659 | "modality": "Text + Vision", |
660 | 660 | "rateLimit": "30 RPM (120 with token)" |
661 | 661 | }, |
662 | 662 | { |
663 | 663 | "id": "mistral-small-3.1-24b", |
664 | 664 | "name": "mistral-small-3.1-24b", |
665 | 665 | "context": "32K", |
666 | | - "maxOutput": "—", |
| 666 | + "maxOutput": "\u2014", |
667 | 667 | "modality": "Text", |
668 | 668 | "rateLimit": "30 RPM (120 with token)" |
669 | 669 | }, |
670 | 670 | { |
671 | 671 | "id": "qwen2.5-coder-32b", |
672 | 672 | "name": "qwen2.5-coder-32b", |
673 | | - "context": "—", |
674 | | - "maxOutput": "—", |
| 673 | + "context": "\u2014", |
| 674 | + "maxOutput": "\u2014", |
675 | 675 | "modality": "Text (code)", |
676 | 676 | "rateLimit": "30 RPM (120 with token)" |
677 | 677 | }, |
|
689 | 689 | "name": "NVIDIA NIM", |
690 | 690 | "category": "inference_provider", |
691 | 691 | "country": "US", |
692 | | - "flag": "🇺🇸", |
| 692 | + "flag": "\ud83c\uddfa\ud83c\uddf8", |
693 | 693 | "url": "https://build.nvidia.com/explore/discover", |
694 | 694 | "baseUrl": "https://integrate.api.nvidia.com/v1", |
695 | 695 | "description": "Free with NVIDIA Developer Program membership. 100+ models. No daily token cap.", |
|
789 | 789 | "name": "Ollama Cloud", |
790 | 790 | "category": "inference_provider", |
791 | 791 | "country": "US", |
792 | | - "flag": "🇺🇸", |
| 792 | + "flag": "\ud83c\uddfa\ud83c\uddf8", |
793 | 793 | "url": "https://ollama.com/settings/keys", |
794 | 794 | "baseUrl": "https://api.ollama.com", |
795 | 795 | "description": "Free tier with qualitative usage limits. 400+ models from Ollama library. Not OpenAI SDK-compatible; uses [Ollama API](https://docs.ollama.com/cloud).", |
|
849 | 849 | "name": "OpenRouter", |
850 | 850 | "category": "inference_provider", |
851 | 851 | "country": "US", |
852 | | - "flag": "🇺🇸", |
| 852 | + "flag": "\ud83c\uddfa\ud83c\uddf8", |
853 | 853 | "url": "https://openrouter.ai/keys", |
854 | 854 | "baseUrl": "https://openrouter.ai/api/v1", |
855 | 855 | "description": "35+ free models (marked with `:free` suffix). OpenAI SDK-compatible.", |
|
965 | 965 | "name": "SiliconFlow", |
966 | 966 | "category": "inference_provider", |
967 | 967 | "country": "CN", |
968 | | - "flag": "🇨🇳", |
| 968 | + "flag": "\ud83c\udde8\ud83c\uddf3", |
969 | 969 | "url": "https://cloud.siliconflow.cn/account/ak", |
970 | 970 | "baseUrl": "https://api.siliconflow.cn/v1", |
971 | 971 | "description": "Free tier with 14 CNY signup credits. Permanently free models available.", |
|
1014 | 1014 | { |
1015 | 1015 | "id": "deepseek-ai/DeepSeek-OCR", |
1016 | 1016 | "name": "deepseek-ai/DeepSeek-OCR", |
1017 | | - "context": "—", |
| 1017 | + "context": "\u2014", |
1018 | 1018 | "maxOutput": "8K", |
1019 | 1019 | "modality": "Vision (OCR)", |
1020 | 1020 | "rateLimit": "1,000 RPM, 50K TPM" |
|
1049 | 1049 | }, |
1050 | 1050 | { |
1051 | 1051 | "id": 5, |
1052 | | - "text": "Kilo Code free model list may change over time. nvidia/nemotron-3-super-120b-a12b:free is for trial use only — prompts are logged by NVIDIA. Auto-router `kilo-auto/free` routes to minimax/minimax-m2.5:free (80%) and stepfun/step-3.5-flash:free (20%)." |
| 1052 | + "text": "Kilo Code free model list may change over time. nvidia/nemotron-3-super-120b-a12b:free is for trial use only \u2014 prompts are logged by NVIDIA. Auto-router `kilo-auto/free` routes to minimax/minimax-m2.5:free (80%) and stepfun/step-3.5-flash:free (20%)." |
1053 | 1053 | } |
1054 | 1054 | ], |
1055 | 1055 | "glossary": [ |
|
0 commit comments