Recherche

43 résultats · “Agent”

Classement des modèles

Cartesia Sonic 3.6

NOUVEAUAudio

Cartesia's low-latency streaming TTS — sub-90ms first audio, 44 languages, built for real-time voice agents.

“Cloned my voice from a 15-second clip, then had it speak Japanese — impressed by how good it sounds.”

~$0.03/min (from $5/mo)AbonnementDernière mise à jour nov. 2026
57%Ça vaut le coup

Claude Code

MIS À JOURAgent

Highest quality — but hits rate limits mid-session

“Best code I've ever had an AI write. It genuinely understands the codebase.”

Included in Pro/Max/UltraGratuitDernière mise à jour nov. 2026
60%Ça vaut le coup

Claude Duet

MIS À JOURAgent

Anthropic's personal AI agent

“Anthropic's new personal agent, and it's actually good”

Included in Pro/Max/Ultra (US)GratuitDernière mise à jour nov. 2026
50%Ça vaut le coup

Claude Fable 5.1

MIS À JOURProgrammation

Top agentic coding, expensive

“Top-tier agentic coding, but you'll pay for it — one full benchmark run was $1,550”

$10/$50 per 1M tokensÀ l'usageDernière mise à jour nov. 2026
53%Ça vaut le coup

Claude Opus 5.5

MIS À JOURChat

Best core correctness on coding, 40% cheaper than Opus 5

“Still the most reliable model for actually shipping code. It just doesn't hallucinate the way others do.”

$4/$20 per 1M tokensÀ l'usageDernière mise à jour nov. 2026
67%Ça vaut le coup

Cline

MIS À JOURAgent

Open-source coding agent

“Open-source and free to run — bring your own API key and go”

Free / BYO keyGratuitDernière mise à jour nov. 2026
56%Ça vaut le coup

Codex

MIS À JOURAgent

Reliable executor — lower ceiling, generous limits

“Great for kicking off background tasks and walking away”

Free · Plus $20/mo · API $1.75/$14Abonnement1 reviewsDernière mise à jour nov. 2026
68%Ça vaut le coup

Cursor

MIS À JOURAgent

Anysphere's AI-first coding agent/IDE; acquired by xAI (SpaceX) in Aug 2026 and bundled with The X Subscription.

Free · $8 Plus · $30 Premium · $100 Super · $200 UltraÀ l'usageDernière mise à jour nov. 2026
58%Ça vaut le coup

DeepSeek Harness

MIS À JOURAgent

Open-source agent framework — everything is a plugin

“Open-source agent framework where everything is a plugin.”

Free (open-source)GratuitDernière mise à jour nov. 2026
91%Ça vaut le coup

DeepSeek Super Agent

MIS À JOURAgent

DeepSeek's multi-task super agent that splits and handles multiple tasks at once.

“Multi-task super agent that splits and handles several tasks at once”

Free (MIT)GratuitDernière mise à jour nov. 2026
54%Ça vaut le coup

Devin

MIS À JOURAgent

Autonomous software engineer

“Autonomous end-to-end coding actually works for delegated tickets.”

Free · Pro $20/mo · Max $200/moAbonnementDernière mise à jour nov. 2026
45%Pas la peine

Google's execution model for everyday coding and agent work — Argon-class quality at $1.50/$7.50, flat to 1M context.

“Argon-class agent capability at $1.50/$7.50 per 1M — 25% below Sonnet 5.5.”

$1.50/$7.50 per 1M (flat to 1M)À l'usageDernière mise à jour nov. 2026
57%Ça vaut le coup

Gemini Agent

MIS À JOURAgent

Google's personal AI agent

“Deep Gmail and Workspace integration is the killer feature.”

Private previewDernière mise à jour nov. 2026
37%Pas la peine

GitHub Copilot

MIS À JOURAgent

The default coding assistant

“Deep IDE and GitHub integration — it just works everywhere”

Pro $10/mo · Pro+ $39/moAbonnementDernière mise à jour nov. 2026
29%Pas la peine

GLM 5.3 Flash

NOUVEAUChat

Z.ai's fast, ultra-cheap multimodal model for coding and long-horizon agent tasks (1M context).

“30M tokens processed for 50 cents — flagship-level output at a fraction of the price.”

$0.03/$0.08 per 1M tokensÀ l'usageDernière mise à jour nov. 2026
51%Ça vaut le coup

GPT 6.1 Sol

MIS À JOURChat

Bills run high on agent tasks

“The actual value king from OpenAI. Does 90% of what Astra does for way less.”

$2/$10 per 1M tokensÀ l'usage1 reviewsDernière mise à jour nov. 2026
41%Pas la peine

GPT-6 Astra

MIS À JOURChat

OpenAI's strongest model — 1M context

“Most capable model I've used this year, period. The 1M context actually works for huge codebases”

$10/$50 per 1M tokensÀ l'usageDernière mise à jour nov. 2026
57%Ça vaut le coup

Hunyuan Hy4

NOUVEAUChat

Tencent's open-source MoE flagship — 770B total/49B active params, 1M context, top open-source tier for math and agentic work.

“Horizon Math score is the best among all open models, second only to GPT-5.6 Sol.”

¥6/¥18 per 1M ($0.83/$2.50)À l'usage1 reviewsDernière mise à jour nov. 2026
49%Pas la peine

Kimi Code

MIS À JOURAgent

Kimi's coding agent

“Fast, cheap, and the CLI is clean”

$15–$159/moAbonnementDernière mise à jour nov. 2026
44%Pas la peine

Kimi K2.7 Code

NOUVEAUProgrammation

Moonshot's open-weight coding-focused agentic model (1T MoE, 32B active, 256K context) for long-horizon software engineering.

“Noticeably better at tool/skill calling and no longer over-thinks like the previous version.”

$0.95/$4.00 per 1M tokensÀ l'usageDernière mise à jour nov. 2026
41%Pas la peine

Manus AI

MIS À JOURAgent

General-purpose autonomous agent

“The demos are unreal — multi-step browser tasks done end-to-end.”

From $20/mo (credit)AbonnementDernière mise à jour nov. 2026
16%Pas la peine

Meta Muse

MIS À JOURAgent

Meta's personal AI agent

“Meta's personal agent, built on the Muse family.”

Free · Power $20/moAbonnement1 reviewsDernière mise à jour nov. 2026
25%Pas la peine

MiniMax M3.1 Flash

MIS À JOURChat

MiniMax's fast, cheap text/language model (M3.1 Flash) for coding, reasoning, and agentic tasks.

“Cuts agent task cost by 70%, which is the whole point.”

$0.15/$0.60 per 1MÀ l'usageDernière mise à jour nov. 2026
37%Pas la peine

Muse Wonder Full

MIS À JOURChat

#3 on the Intelligence Index (56)

“Where did this come from? It appeared out of nowhere and it's sitting at #3 on the index”

$50/moAbonnementDernière mise à jour nov. 2026
47%Pas la peine

Nemotron 3.5 Super VL

MIS À JOURChat

Open 120B vision-language model — 5x faster for always-on agents

$0.15/$0.50 per 1MÀ l'usageDernière mise à jour nov. 2026
52%Ça vaut le coup

OpenAI dots

MIS À JOURAgent

OpenAI's personal AI agent

“OpenAI's personal agent — handles the boring stuff.”

Included in Pro ($100–500/mo)AbonnementDernière mise à jour nov. 2026
38%Pas la peine

Perplexity

MIS À JOURAgent

AI answer engine that combines real-time web search with cited, conversational answers, deep research, and multi-model selection.

Free · Pro $20/mo · Max $200/moAbonnementDernière mise à jour nov. 2026
37%Pas la peine

Qoder CN

MIS À JOURAgent

Niche research tool

“Niche research and writing tool.”

¥59/¥169/moAbonnementDernière mise à jour nov. 2026
38%Pas la peine

Qwen 3.8 Flash

NOUVEAUChat

Alibaba's fast, cheap open-weight multimodal model (Qwen 3.8 family) with 1M context, deep thinking, and agentic coding — the budget Flash sibling to Qwen 3.8 Max.

“Sparse and fast — only 6B active parameters, decoding at 150 tps on a single consumer GPU.”

$0.11 / $0.38 per 1M tokensÀ l'usageDernière mise à jour nov. 2026
57%Ça vaut le coup

Qwen 3.8 Max

MIS À JOURChat

Alibaba's flagship 2.4T-parameter MoE model (95B active) with a 1M-token context, native image/video understanding, and strong agentic coding; first Max-class Qwen with open weights.

“Alibaba's best model yet, and the Chinese + English mix is finally balanced.”

$2/$6 per 1M tokensÀ l'usageDernière mise à jour nov. 2026
43%Pas la peine

Qwen4-Max

NOUVEAUChat

Alibaba's 2.4T-parameter MoE flagship (71B active), native vision, 1M-token context — 6th on Code Arena.

“2.4T total parameters with only 71B active per token — lower inference cost at the same scale.”

$0.075/M input (cache hit)À l'usageDernière mise à jour nov. 2026
47%Pas la peine

Windsurf

MIS À JOURAgent

Fast, fluid AI IDE

“Fast, fluid, and the UX is genuinely pleasant to use”

Free · Pro $20/moAbonnementDernière mise à jour nov. 2026
51%Ça vaut le coup

WorkBuddy

MIS À JOURAgent

#1 agent by monthly users (32M MAU)

“The #1 agent by monthly users now — 32 million MAU, up 647% month over month.”

Pro $10/moAbonnementDernière mise à jour nov. 2026
40%Pas la peine

Zcode

MIS À JOURAgent

Z.ai's coding agent on GLM-5.2

“Z.ai's coding agent, built on Z.ai's own 5.2 base model”

From $18/moAbonnementDernière mise à jour nov. 2026
32%Pas la peine

Derniers avis

GLM 5.3 FlashKimi K2.7 CodeMiniMax M3.1 FlashCodingCostOpen-source

The open source war - GLM is the budget champion

Model tested - Models : GLM-5.3-Flash vs Kimi-K2.7-Code vs MiniMax-M3.1-Flash all via opencode-go - Use case : coding - two real feature tasks on yolped, my Rus

quriousprof⭐⭐· Nov 8, 2026