Modèles d’IA pour Programmation

A flagship GPT-5.6 model listed for complex reasoning, coding and multi-step agent workflows.

Contexte

1,05M

Entrée

2,5 $US

Sortie

15 $US

A Sonnet-class model listed for coding, agents and professional knowledge work with adaptive reasoning.

Contexte

1M

Entrée

2 $US

Sortie

10 $US

A fast multimodal Gemini model listed for responsive agent workflows, coding and multi-step reasoning.

Contexte

1,05M

Entrée

0,375 $US

Sortie

1,88 $US

A Grok model listed for coding, knowledge work and STEM tasks with text, image and file input.

Contexte

500K

Entrée

2 $US

Sortie

6 $US

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

A text model listed as a large mixture-of-experts release with a 1,048,576-token provider context window.

Contexte

1,05M

Entrée

1,32 $US

Sortie

3,96 $US

A dense instruction model listed for agent workflows, coding and complex professional tasks.

Contexte

262K

Entrée

1,5 $US

Sortie

7,5 $US

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

Contexte

262K

Entrée

0,12 $US

Sortie

0,80 $US

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and…

Contexte

1M

Entrée

10 $US

Sortie

50 $US

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and…

Contexte

200K

Entrée

5 $US

Sortie

25 $US

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective…

Contexte

1M

Entrée

5 $US

Sortie

25 $US

Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on…

Contexte

1M

Entrée

5 $US

Sortie

25 $US

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis…

Contexte

1M

Entrée

5 $US

Sortie

25 $US

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with…

Contexte

1M

Entrée

3 $US

Sortie

15 $US

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with…

Contexte

1M

Entrée

3 $US

Sortie

15 $US

Mistral Codestral Embed is specially designed for code, perfect for embedding code databases, repositories, and powering coding assistants with state-of-the-art retrieval.

Contexte

8K

Entrée

0,15 $US

Sortie

0,00 $US

**DeepSeek-V4-Flash-0731** is the official release of **DeepSeek-V4-Flash**, superseding the preview version, with substantially enhanced agentic capabilities. It has the same model structure as DeepSeek-V4-Flash-DSpark, i.e. it comes with a speculative decoding module attached.

Contexte

1,05M

Entrée

0,14 $US

Sortie

0,28 $US

We present a preview version of **DeepSeek-V4** series, including two strong Mixture-of-Experts (MoE) language models — **DeepSeek-V4-Pro** with 1.6T parameters (49B activated) and **DeepSeek-V4-Flash** with 284B parameters (13B activated) — both supporting a context length of **one million tokens**.

Contexte

1,05M

Entrée

1,32 $US

Sortie

3,96 $US

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool…

Contexte

1,05M

Entrée

0,50 $US

Sortie

3 $US

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation…

Contexte

1,05M

Entrée

2 $US

Sortie

12 $US

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution…

Contexte

1,05M

Entrée

1,5 $US

Sortie

9 $US

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and…

Contexte

1,05M

Entrée

0,75 $US

Sortie

3,75 $US

gemini-embedding-001 provides a unified cutting edge experience across domains, including science, legal, finance, and coding. This embedding model has consistently held a top spot on the Massive Text Embedding Benchmark…

Contexte

20K

Entrée

0,15 $US

Sortie

0,00 $US

You can also see significant improvements in many other scenarios such as chat, creative writing, and role-play scenario.

Contexte

203K

Entrée

0,40 $US

Sortie

1,75 $US

GLM-4.7-Flash is a 30B-A3B MoE model. As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.

Contexte

203K

Entrée

0,06 $US

Sortie

0,40 $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

GLM-5.1 is our next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin on NL2Repo (repo generation) and Terminal-Bench 2.0 (real-world terminal tasks).

Contexte

200K

Entrée

0,966 $US

Sortie

3,04 $US

We're introducing GLM-5.2, our latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on a **solid 1M-token context**. GLM-5.2's new capabilities include:

Contexte

1,05M

Entrée

0,50 $US

Sortie

3,15 $US

GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,…

Contexte

203K

Entrée

1,2 $US

Sortie

4 $US

GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks.…

Contexte

400K

Entrée

0,625 $US

Sortie

5 $US

GPT-5 Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,…

Contexte

400K

Entrée

10 $US

Sortie

10 $US

GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and…

Contexte

400K

Entrée

15 $US

Sortie

120 $US

GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks.…

Contexte

400K

Entrée

1,25 $US

Sortie

10 $US

GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic…

Contexte

400K

Entrée

1,25 $US

Sortie

10 $US

GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,…

Contexte

400K

Entrée

21 $US

Sortie

168 $US

GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks.…

Contexte

400K

Entrée

1,75 $US

Sortie

14 $US

GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results…

Contexte

400K

Entrée

1,75 $US

Sortie

14 $US

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,…

Contexte

400K

Entrée

0,75 $US

Sortie

4,5 $US

GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic…

Contexte

1,05M

Entrée

2 $US

Sortie

12 $US

Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.

Contexte

500K

Entrée

2 $US

Sortie

6 $US

Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding…

Contexte

256K

Entrée

1 $US

Sortie

2 $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

KAT-Coder-Air V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make…

Contexte

256K

Entrée

0,15 $US

Sortie

0,60 $US

KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,…

Contexte

256K

Entrée

0,30 $US

Sortie

1,2 $US

KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make…

Contexte

256K

Entrée

0,74 $US

Sortie

2,96 $US

📰   Tech Blog     |     📄   Paper

Contexte

262K

Entrée

0,57 $US

Sortie

2,85 $US

Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.

Contexte

262K

Entrée

0,95 $US

Sortie

4 $US

Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinking-token usage by approximately 30% compared with Kimi K2.6.

Contexte

262K

Entrée

0,71 $US

Sortie

3,5 $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

Laguna S 2.1 is a 118B total parameter Mixture-of-Experts model with 8B activated parameters per token, designed for agentic coding and long-horizon work. It sits between Laguna XS 2.1 (33B-A3B) and Laguna M.1 (225B-A23B) in the Laguna series and shares the family recipe: a token-choice router with softplus gating over 256 routed experts plus one shared expert, grouped-query attention, and interleaved full/sliding-window attention.

Contexte

1,05M

Entrée

0,09 $US

Sortie

0,18 $US

Laguna XS 2.1 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine. This model is an upgraded version of our Laguna XS.2 model with a +5.4% jump on SWE-bench Multilingual as well as stronger performance on terminal-style tasks.

Contexte

262K

Entrée

0,06 $US

Sortie

0,12 $US

LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or…

Contexte

128K

Entrée

0,00 $US

Sortie

0,00 $US

LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic…

Contexte

1,05M

Entrée

0,30 $US

Sortie

1,2 $US

🤗 HuggingFace  | 📰 Blog  | 🎨 Xiaomi MiMo API Platform  | 🗨️ Xiaomi MiMo Studio  |

Contexte

1,05M

Entrée

0,435 $US

Sortie

0,87 $US

Today, we release and open source MiniMax-M2, a **Mini** model built for **Max** coding & agentic workflows.

Contexte

205K

Entrée

0,255 $US

Sortie

1,02 $US

Today, we are handing **MiniMax-M2.1** over to the open-source community. This release is more than just a parameter update; it is a significant step toward democratizing top-tier agentic capabilities.

Contexte

205K

Entrée

0,30 $US

Sortie

1,2 $US

Extensively trained with reinforcement learning in hundreds of thousands of complex real-world environments, M2.5 is **SOTA in coding, agentic tool use and search, office work, and a range of other economically valuable tasks**, boasting scores of **80.2% in SWE-Bench Verified, 51.3% in Multi-SWE-Bench, and 76.3% in BrowseComp** (with context management).

Contexte

197K

Entrée

0,22 $US

Sortie

0,90 $US

MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters.

Contexte

524K

Entrée

0,30 $US

Sortie

1,2 $US

NVIDIA Nemotron 3 Embed 1B is an open text embedding model from NVIDIA, optimized for high-throughput, low-latency retrieval. It is suited for enterprise search, RAG, code retrieval, and agentic retrieval…

Contexte

33K

Entrée

0,00 $US

Sortie

0,00 $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

North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized…

Contexte

256K

Entrée

0,00 $US

Sortie

0,00 $US

The Pareto Router maintains a tiered shortlist of strong coding models, ranked by Artificial Analysis coding percentiles. Set min_coding_score between 0 and 1 on the pareto-router plugin to control how…

Contexte

2M

Entrée

Inconnu

Sortie

Inconnu

Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling…

Contexte

1M

Entrée

0,195 $US

Sortie

0,975 $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

Over the past few months, we have observed increasingly clear trends toward scaling both total parameters and context lengths in the pursuit of more powerful and agentic artificial intelligence (AI). We are excited to share our latest advancements in addressing these demands, centered on improving scaling efficiency through innovative model architecture. We call this next-generation foundation models **Qwen3-Next**.

Contexte

262K

Entrée

0,10 $US

Sortie

1,1 $US

Over the past few months, we have observed increasingly clear trends toward scaling both total parameters and context lengths in the pursuit of more powerful and agentic artificial intelligence (AI). We are excited to share our latest advancements in addressing these demands, centered on improving scaling efficiency through innovative model architecture. We call this next-generation foundation models **Qwen3-Next**.

Contexte

131K

Entrée

0,15 $US

Sortie

1,2 $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

0,10 $US

Sortie

0,15 $US

Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and…

Contexte

262K

Entrée

1,03 $US

Sortie

6,16 $US

Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world…

Contexte

1M

Entrée

0,03 $US

Sortie

0,13 $US

Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,…

Contexte

1M

Entrée

1,48 $US

Sortie

4,43 $US

Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at…

Contexte

256K

Entrée

0,85 $US

Sortie

1,25 $US

Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters, built for real-world agent workflows that require both strong capability and operational efficiency. It is optimized for coding agents, tool…

Contexte

262K

Entrée

0,075 $US

Sortie

0,625 $US

Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and…

Contexte

262K

Entrée

0,50 $US

Sortie

2,5 $US

Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude…

Contexte

262K

Entrée

0,50 $US

Sortie

3 $US

voyage-code-4 is a code embedding model from Voyage AI, a MongoDB company. It is designed for coding agents and code retrieval, with Matryoshka embeddings at 2048, 1024, 512, and 256…

Contexte

32K

Entrée

0,12 $US

Sortie

0,00 $US