Modèles d’IA pour Déploiement local

An open-weight vision-language model listed for coding, research, multimodal interaction and agent tasks.

Contexte

262K

Entrée

0,45 $US

Sortie

3,2 $US

An open-weight coding model listed for coding agents and local development workflows.

Contexte

262K

Entrée

0,12 $US

Sortie

0,80 $US

Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is…

Contexte

512K

Entrée

0,00 $US

Sortie

0,00 $US

We are launching GLM-5, targeting complex systems engineering and long-horizon agentic tasks. Scaling is still one of the most important ways to improve the intelligence efficiency of Artificial General Intelligence (AGI). Compared to GLM-4.5, GLM-5 scales from 355B parameters (32B active) to 744B parameters (40B active), and increases pre-training data from 23T to 28.5T tokens. GLM-5 also integrates DeepSeek Sparse Attention (DSA), largely reducing deployment cost while preserving long-context capacity.

Contexte

198K

Entrée

0,60 $US

Sortie

1,92 $US

gpt-oss-safeguard-120b and gpt-oss-safeguard-20b are safety reasoning models built-upon gpt-oss. With these models, you can classify text content based on safety policies that you provide and perform a suite of foundational safety tasks. These models are intended for safety use cases. For other applications, we recommend using gpt-oss models.

Contexte

131K

Entrée

0,075 $US

Sortie

0,30 $US

MiniMax H3 is a lightweight, open-weights video generation model from MiniMax. It is designed for precise multimodal editing and controlled content generation, including instruction-guided edits, text and brand rendering, and…

Contexte

0

Entrée

0,00 $US

Sortie

0,00 $US

Inkling is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages. The model is designed to be used by developers building AI-powered applications, including agentic and tool-use systems, coding assistants, chatbots, and retrieval-augmented generation systems, and is suitable for general-purpose conversational use, instruction-following, and other natural language and multimodal tasks. It is released with open weights to support research, fine-tuning and integration into third-party products by downstream developers.

Contexte

524K

Entrée

0,95 $US

Sortie

4,05 $US

Inkling-Small is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages. The model is designed to be used by developers building AI-powered applications, including agentic and tool-use systems, coding assistants, chatbots, and retrieval-augmented generation systems, and is suitable for general-purpose conversational use, instruction-following, and other natural language and multimodal tasks. It is released with open weights to support research, fine-tuning and integration into third-party products by downstream developers.

Contexte

524K

Entrée

0,45 $US

Sortie

1,2 $US

Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date. It is a 2.8T-parameter model built on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), with native vision capabilities and a 1-million-token context window. It is the world's first open 3T-class model, designed for frontier intelligence across long-horizon coding, knowledge work, and reasoning.

Contexte

1,05M

Entrée

3 $US

Sortie

15 $US

Kokoro 82M is a lightweight, open-weight text-to-speech model from hexgrad. It converts text to speech across 8 languages (American and British English, Spanish, French, Hindi, Italian, Japanese, Portuguese, and Chinese)…

Contexte

4K

Entrée

0,62 $US

Sortie

0,00 $US

Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon…

Contexte

131K

Entrée

0,35 $US

Sortie

1,5 $US

🤗 Model &nbsp&nbsp | &nbsp&nbsp 🔀 the provider catalog (Enjoy two weeks free starting June 9!) &nbsp&nbsp | &nbsp&nbsp 💻 Github &nbsp&nbsp | &nbsp&nbsp 🧭 ModelScope &nbsp&nbsp | &nbsp&nbsp 🚀 Nex-AGI

Contexte

262K

Entrée

0,025 $US

Sortie

0,10 $US

Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and…

Contexte

1M

Entrée

0,65 $US

Sortie

3,25 $US

Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.

Contexte

131K

Entrée

0,21 $US

Sortie

1,9 $US

> [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc.

Contexte

262K

Entrée

0,14 $US

Sortie

1 $US

> [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with vLLM, SGLang, TokenSpeed, etc.

Contexte

1M

Entrée

2 $US

Sortie

6 $US

Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token.…

Contexte

262K

Entrée

0,10 $US

Sortie

0,30 $US

Trinity-Large-Thinking is a reasoning-optimized variant of Arcee AI's Trinity-Large family — a 398B-parameter sparse Mixture-of-Experts (MoE) model with approximately 13B active parameters per token. Built on Trinity-Large-Base and post-trained with extended chain-of-thought reasoning and agentic RL, Trinity-Large-Thinking delivers state-of-the-art performance on agentic benchmarks while maintaining strong general capabilities.

Contexte

262K

Entrée

0,22 $US

Sortie

0,85 $US

Whisper is OpenAI's open-source automatic speech recognition model, available via API as whisper-1. It supports transcription and translation across 50+ languages from audio files up to 25 MB. Accepts formats…

Contexte

0

Entrée

6 000 $US

Sortie

0,00 $US

Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation, proposed in the paper Robust Speech Recognition via Large-Scale Weak Supervision by Alec Radford et al. from OpenAI. Trained on >5M hours of labeled data, Whisper demonstrates a strong ability to generalise to many datasets and domains in a zero-shot setting.

Contexte

0

Entrée

7,5 $US

Sortie

0,00 $US