| Modello | Tipo | Prezzo ($/1M) | Contesto | Uscito il |
|---|---|---|---|---|
| Muse Spark 1.1 | text | $2 | 1.049K | apr 2026 |
| Llama Nemotron Rerank VL 1B V2 | rerank | — | 128K | mar 2026 |
| Llama Nemotron Embed VL 1B V2 | embedding | — | 33K | feb 2026 |
| Llama 3.1 Nemotron Safety Guard 8B V3 | moderation | — | 128K | ott 2025 |
| Llama 4 Maverick | text | $0,24 | 1.049K | set 2025 |
| Llama 4 Scout | text | $0,14 | 131K | set 2025 |
| Llama 3.3 70B Instruct abliterated | text | $0,7 | 16K | ago 2025 |
| Llama 3 70B abliterated | text | $0,7 | 8K | lug 2025 |
| Llama 3.3 Nemotron Super 49B v1.5 | text | $0,1 | 131K | lug 2025 |
| Llama 3.2 Nemoretriever 300M Embed V1 | embedding | — | 33K | lug 2025 |
| Llama 3.1 8B CS | text | $0,1 | 128K | mag 2025 |
| Llama 3.3 70B Cs obsoleto | text | — | — | mag 2025 |
| Llama 3.1 Nemotron 70B Instruct | text | $0,6 | 128K | apr 2025 |
| Nvidia Nemotron 70b | text | $0,37 | 16K | apr 2025 |
| AlfredPros: CodeLLaMa 7B Instruct Solidity | text | $0,9 | 4K | apr 2025 |
| Llama-xLAM-2 70B fc-r | text | $2,5 | 128K | apr 2025 |
| Llama 3.1 Nemotron Nano VL 8B v1 | text | — | 33K | apr 2025 |
| BART Large CNN | text | — | 128K | apr 2025 |
| Llama 3.1 Nemotron Ultra 253B llama-3-1-nemotron-ultra-253b | text | $0,9 | 128K | apr 2025 |
| Llama 3.1 Nemotron Ultra 253B ревизия v1 | text | $0,9 | 128K | apr 2025 |
| Llama 3.3 Nemotron Super 49B v1 | text | $0,15 | 131K | apr 2025 |
| Llama 3.3 70B llama-3-3-70b | text | $0,72 | 128K | apr 2025 |
| Llama 4 Scout 17B 16E Instruct | text | $0,06 | 10.000K | apr 2025 |
| Llama Guard 4 12B | moderation | $0,18 | 164K | apr 2025 |
| Llama 2 7B Chat | text | $0,1 | 128K | apr 2025 |
| M2M100 1.2B | text | $0,34 | 128K | apr 2025 |
| Llama 4 Maverick 17b 128e Instruct | text | $0,06 | 1.049K | apr 2025 |
| Llama 3.1 Nemotron Nano 8B v1 | text | — | 131K | mar 2025 |
| Llama Guard 3 8B | moderation | $0,03 | 131K | gen 2025 |
| Meta Llama Guard 4 12B | moderation | $0,21 | 131K | gen 2025 |
| Llama 3.3 70B Instruct | text | $0,1 | 131K | dic 2024 |
| Llama 3.3 70B Instruct fp8 Fast | text | $0,78 | 24K | dic 2024 |
| Llama 3.3 70B дообучена выполнять инструкции | text | $0,16 | 131K | dic 2024 |
| Meta Llama 3.3 70B Versatile | text | $0,64 | 131K | dic 2024 |
| Llama 3.3 8B Instruct | text | — | 128K | dic 2024 |
| Llama 3.3 70B дообучена выполнять инструкции | text | $0,59 | 128K | dic 2024 |
| Nemotron Tenyxchat Storybreaker 70b | text | $0,49 | 16K | dic 2024 |
| Llama 3.05 Storybreaker Ministral 70b | text | $0,49 | 16K | dic 2024 |
| Llama 3.2 3B | text | $0,05 | 128K | ott 2024 |
| Meta Llama Prompt Guard 2 22M | moderation | $0,01 | 1K | ott 2024 |
| Meta Llama Prompt Guard 2 86M | moderation | $0,01 | 1K | ott 2024 |
| Llama 3.2 90B Vision Instruct | text | $0,36 | 128K | set 2024 |
| Llama 3.2 Nv Embedqa 1B | embedding | — | 8K | set 2024 |
| Llama 3.2 11b Vision Instruct | text | $0,05 | 131K | set 2024 |
| Llama 3.2 1b Instruct | text | $0,01 | 128K | set 2024 |
| Llama 3.2 3B Instruct | text | $0,02 | 131K | set 2024 |
| Esm2 650M | text | — | 128K | ago 2024 |
| Llama 3.1 405B Instruct | text | $0,17 | 128K | lug 2024 |
| Llama 3.1 405B Instruct Turbo | text | $3,5 | 128K | lug 2024 |
| Llama 3.1 70B Instruct | text | $0,72 | 128K | lug 2024 |
| Llama 3.1 70B | text | $0,17 | 131K | lug 2024 |
| Llama 3.1 8B Instruct | text | $0,04 | 128K | lug 2024 |
| Llama 3.1 8B | text | $0,02 | 131K | lug 2024 |
| Meta Llama 3.1 8B Instruct Turbo | text | $0,02 | 128K | lug 2024 |
| Llama 3.1 Instruct (8B) | text | $0,2 | 8K | lug 2024 |
| Meta Llama 3.1 8B Instant | text | $0,06 | 131K | lug 2024 |
| Meta: Llama 3 8B Instruct | text | $0,03 | 8K | apr 2024 |
| Llama 3 70B Instruct | text | $0,17 | 8K | apr 2024 |
| Meta Llama 3 8B Instruct Lite | text | $0,14 | 8K | apr 2024 |
| Esmfold | text | — | 128K | mar 2024 |
| Code Llama 13B | text | $0,2 | 16K | — |
| Code Llama 13B Instruct | text | $0,2 | 16K | — |
| Code Llama 13B Python | text | $0,2 | 16K | — |
| Code Llama 34B | text | $0,9 | 16K | — |
| Code Llama 34B Instruct | text | $0,9 | 16K | — |
| Code Llama 34B Python | text | $0,9 | 16K | — |
| Code Llama 70B | text | $0,9 | 4K | — |
| Code Llama 70B Instruct | text | $0,9 | 4K | — |
| Code Llama 70B Python | text | $0,9 | 4K | — |
| Code Llama 7B | text | $0,2 | 16K | — |
| Code Llama 7B Instruct | text | $0,2 | 16K | — |
| Code Llama 7B Python | text | $0,2 | 16K | — |
| CodeLlama | text | — | 4K | — |
| CodeLlama 34B Instruct | text | $0,61 | 16K | — |
| CodeLlama 34B Instruct HF | text | $1 | 4K | — |
| CodeLlama 70B Instruct | text | $1,23 | 16K | — |
| CodeLlama 70B Instruct HF | text | $1 | 4K | — |
| CodeLlama 7B | text | $0,08 | 16K | — |
| CodeLlama 7B Instruct | text | $1,92 | 4K | — |
| Dolphin3 8B | text | $0,1 | 128K | — |
| Llama 2 13B | text | $0,2 | 4K | — |
| Llama 2 13B Chat | text | $0,2 | 4K | — |
| Llama 2 13B Chat HF | text | $0,25 | 4K | — |
| Llama 2 70B | text | $1,18 | 4K | — |
| Llama 2 70B Chat | text | $0,75 | 4K | — |
| Llama 2 70B Chat HF | text | $1 | 4K | — |
| Llama 2 7B | text | $0,1 | 4K | — |
| Llama 2 7B Chat HF | text | $0,15 | 4K | — |
| Llama 2 7B Chat HF Lora | text | — | 8K | — |
| Llama 3.1 70B Instruct Turbo | text | $0,15 | 131K | — |
| Llama 3.2 11B | text | $0,16 | 128K | — |
| Llama 3.2 1B | text | $0,1 | 128K | — |
| Llama 3.2 3B Instruct Turbo | text | — | — | — |
| Llama 3.2 90B | text | $0,72 | 128K | — |
| Llama 3.2 Nv Rerankqa 1B V2 | rerank | — | — | — |
| Llama 3 70B | text | $0,64 | 8K | — |
| Llama 3 8B | text | $0,06 | 8K | — |
| Llama 4 Maverick 17B | text | $0,61 | 128K | — |
| Llama 4 Maverick 17B 16e Instruct | text | $0,55 | 1.000K | — |
| Llama 4 Scout 17B 128e Instruct | text | $0,36 | 10.000K | — |
| Llama Guard 2 8B | moderation | $0,2 | 8K | — |
| Llama Guard 3 11B Vision | moderation | $0,35 | 128K | — |
| Llama Guard 3 1B | moderation | $0,1 | 131K | — |
| Llama V2 13B | text | $0,2 | 4K | — |
| Llama V2 13B Chat | text | $0,2 | 4K | — |
| Llama V2 70B | text | $0,1 | 4K | — |
| Llama V2 70B Chat | text | $0,9 | 2K | — |
| Llama V2 7B | text | $0,2 | 4K | — |
| Llama V2 7B Chat | text | $0,2 | 4K | — |
| Llama V3.1 405B Instruct | text | $3 | 128K | — |
| Llama V3.1 405B Instruct Long | text | $0,1 | 4K | — |
| Llama V3.1 70B Instruct | text | $0,9 | 131K | — |
| Llama V3.1 70B Instruct 1B | text | $0,1 | 4K | — |
| Llama V3.1 8B Instruct | text | $0,1 | 16K | — |
| Llama V3.1 Nemotron 70B Instruct | text | $0,9 | 131K | — |
| Llama V3.2 11B Vision Instruct | text | $0,2 | 16K | — |
| Llama V3.2 1B | text | $0,1 | 131K | — |
| Llama V3.2 1B Instruct | text | $0,1 | 16K | — |
| Llama V3.2 3B | text | $0,1 | 131K | — |
| Llama V3.2 3B Instruct | text | $0,1 | 16K | — |
| Llama V3.2 90B Vision Instruct | text | $0,9 | 16K | — |
| Llama V3.3 70B Instruct | text | $0,9 | 131K | — |
| Llama V3 70B Instruct | text | $0,9 | 8K | — |
| Llama V3 70B Instruct HF | text | $0,9 | 8K | — |
| Llama V3 8B | text | $0,2 | 8K | — |
| Llama V3 8B Instruct HF | text | $0,2 | 8K | — |
| Llama2 | text | — | 4K | — |
| Llama2 Uncensored | text | — | 4K | — |
| Llama3 | text | — | 8K | — |
| Llama3.1 | text | — | 8K | — |
| Llama3.2 11B Instruct | text | $0,14 | 128K | — |
| Llama3.2 90B Instruct | text | $2 | 128K | — |
| Llama3 405B Instruct | text | — | 32K | — |
| Llama4 Maverick Instruct Basic | text | $0,39 | 131K | — |
| Llama4 Scout Instruct Basic | text | $0,26 | 131K | — |
| Llamaguard 7B | moderation | $0,2 | 4K | — |
| Llava 7B | text | $0,13 | 4K | — |
| Meta Textgeneration Llama 2 13B | text | — | 4K | — |
| Meta Textgeneration Llama 2 13B F | text | — | 4K | — |
| Meta Textgeneration Llama 2 70B | text | — | 4K | — |
| Meta Textgeneration Llama 2 70B B F | text | — | 4K | — |
| Meta Textgeneration Llama 2 7B | text | — | 4K | — |
| Meta Textgeneration Llama 2 7B F | text | — | 4K | — |
| Openthinker 7B | text | $0,1 | 33K | — |
Prezzo misto, secondo uno schema di tre token in ingresso per uno in uscita. Si prende dallo sviluppatore stesso, se vende questo modello; altrimenti dall'offerta più economica tra i fornitori, come coppia da un unico listino. Solo tariffa base a token. Un trattino significa che il modello non ha un prezzo a token nelle fonti aperte, non che sia gratuito.