opendunes

Meta models

All 8 Meta models on OpenDunes, priced in Algerian Dinars.

Models8
Understands
TextImages
Replies with
Text
↑8,99 – 239,64 DA/ 1M tokens
↓26,63 – 332,84 DA/ 1M tokens
Context up to1.3M
5 with fills your json4 with uses your tools1 with thinks first

8 models

meta-llama/llama-3.1-8b-instructText

Llama 3.1 8B Instruct is the small model of Meta's Llama 3.1 family, tuned to follow instructions and described as fast and efficient. You send text and get text back; it reads about 131 pages at once and can use tools or fill in an exact form you give it. Use it for sorting, short rewrites, simple chat and high-volume jobs.

TextText
≈ 0,030 DAper message↑ 16,64 DA↓ 26,63 DAper 1M tokens
by MetaJul 23, 2024
Open in chat
meta-llama/llama-3.3-70b-instructText

Llama 3.3 70B Instruct is a text-only Meta model tuned for conversation in English, Spanish, French, German, Italian, Portuguese, Hindi and Thai. You send a chat, with tools or an exact form to fill in if you need them, and get a reply of up to about 16 pages from a conversation of up to 131 pages. Pick it for assistants and support in those languages.

TextText
≈ 0,33 DAper message↑ 196,37 DA↓ 262,94 DAper 1M tokens
by MetaDec 6, 2024
Open in chat
meta-llama/llama-4-scoutText

Llama 4 Scout takes text and pictures and answers in text or code across 12 languages. It reads about 1,300 pages at once, enough to caption or question many images, or take in a very large document in one request. Meta tuned it for chat in many languages, captions and image understanding.

TextImagesText
≈ 0,083 DAper message↑ 33,28 DA↓ 99,85 DAper 1M tokens
by MetaApr 5, 2025
Open in chat
meta-llama/llama-4-maverickText

Llama 4 Maverick takes text and pictures and answers in text or code across 12 languages, keeping about a thousand pages of conversation in mind. Meta tuned it for reasoning about images and for assistant-style chat. Use it to answer questions about photos, charts and screenshots, or for multilingual assistants with long conversations.

TextImagesText
≈ 0,28 DAper message↑ 116,49 DA↓ 332,84 DAper 1M tokens
by MetaApr 5, 2025
Open in chat
meta-llama/llama-guard-4-12bText

Llama Guard 4 checks whether a request or a model's reply is safe. You send text, or text with pictures, and it answers in text: safe, or unsafe with the violated categories from a published list of hazards. Use it as a filter before a chat model sees a user message, and again on the reply. It sorts and does not chat or answer questions, so pair it with a chat model such as Llama 4 Scout.

TextImagesText
≈ 0,090 DAper message↑ 59,91 DA↓ 59,91 DAper 1M tokens
by MetaApr 30, 2025
Open in chat
meta-llama/llama-3.1-70b-instructText

Llama 3.1 70B Instruct is a text model from Meta tuned for conversation, reading about 131 pages at once and able to use tools or fill in an exact form you give it. You send a chat and get a written reply of up to about 16 pages. Use it for assistants, support replies and writing that needs more depth than a small model gives.

TextText
≈ 0,36 DAper message↑ 239,64 DA↓ 239,64 DAper 1M tokens
by MetaJul 23, 2024
Open in chat

Meta: Llama 3.2 3B Instruct

Going away Nov 20, 2026
meta-llama/llama-3.2-3b-instructText

Llama 3.2 3B Instruct is a small multilingual text model from Meta, covering eight languages (English, Spanish and Hindi among them) and reading about 131 pages at once. It is tuned for following instructions, thinking things through and using tools. Use it for chat, summaries and light automated steps at small scale.

TextText
≈ 0,073 DAper message↑ 16,94 DA↓ 111,50 DAper 1M tokens
by MetaSep 25, 2024
Open in chat

Meta: Llama 3.2 1B Instruct

Going away Nov 20, 2026
meta-llama/llama-3.2-1b-instructText

Llama 3.2 1B Instruct is the smallest Llama text model, meant for summaries, short chats and analysing text in several languages on devices with little computing power. It supports eight core languages and reads about 60 pages at once. Use it for simple, repetitive jobs like tagging or short summaries.

TextText
≈ 0,042 DAper message↑ 8,99 DA↓ 66,90 DAper 1M tokens
by MetaSep 25, 2024
Open in chat