L’état de l’art aujourd’hui
Claude Opus 5.5 prend la tête des modèles de pointe
Anthropic devance OpenAI de 1 point sur l’indice d’intelligence Artificial Analysis.
ModèleIntelligence (0–100)
Découvrir les modèles
Des points de départ pratiques issus de l’utilisation réelle d’OpenRouter, des performances en production et de tests de référence indépendants.
Routeurs
Voir tous les routeursThe Auto Router automatically selects the best model for your prompt, powered by the wisdom of the market. It routes you based on what the OpenRouter community collectively spends on for exactly the kind of task your prompt represents. It looks at spend over a trailing 7-day window, so it stays up to date with new model releases automatically. Your response will be priced at the same rate as the routed model. The cost_tier setting (low, medium, high, xhigh, or max) selects how much you're willing to pay. The default is low, giving you a highly cost-efficient set of models. When selecting models, the auto router respects any guardrails, privacy/ZDR policies, and model restrictions you have in the request or account settings. Multi-turn conversations stick to one model until it is no longer a leading choice for your task. Learn more in our [docs](/docs/guides/routing/routers/auto-router). For another way to route, see [Pareto Code](/openrouter/pareto-code).
The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that support features needed for your request such as image understanding, tool calling, structured outputs and more.
The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openrouter.ai/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how strong a coder you need; higher scores select stronger (and typically more expensive) models. If you omit min_coding_score, the router defaults to the High tier. Selecting Nitro from the variant dropdown ranks the models in your tier by measured throughput and routes each request to the fastest one, so you trade some model variety for lower latency. Read the [Pareto Router docs](https://openrouter.ai/docs/guides/routing/routers/pareto-router) for the full selection logic, fallback behavior, and how to customize routing. For another way to route, see the [Auto Router](/openrouter/auto).
Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a judge model synthesizes their responses into a structured analysis — consensus, contradictions, partial coverage, unique insights, and blind spots — and writes the final answer from it. By default the panel is the `Quality` preset; switch to `Budget` for cheaper members, or override the panel and judge entirely with the fusion plugin's `analysis_models` and `model` fields. Reach for Fusion when a single model isn't enough — research, expert critique, or anywhere the cost of being wrong outweighs a few extra completions. Because Fusion runs every panel member plus a judge call, your request is priced as the sum of those underlying completions rather than a single model. To see which models ran, visit [Activity](/activity). Note: Context limits are dependent on which models you select. Learn more in our [docs](/docs/guides/features/plugins/fusion). For another way to route, see the [Auto Router](/openrouter/auto).
The experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, but expect beta quality. When new improvements are proven in auto-beta, we graduate them to the auto router. We've love to hear your feedback on whether auto-beta is working for you, or requests for routing improvements. To see which model was used, visit [Activity](/activity), or read the `model` attribute of the response. Your response will be priced at the same rate as the routed model. Learn more, including how to customize the models for routing, in our [docs](/docs/guides/routing/routers/auto-router).
Meilleurs rapports qualité-prix
Le maximum de capacités par dollar au tarif catalogue.
| Rang | Modèle | Percentile d’intelligence | Centile en programmation | Centile agentique | Jetons |
|---|---|---|---|---|---|
| 1 | 38 | 79 | 91 | 15,3T | |
| 2 |  | 25 | 72 | 81 | 629,1B |
| 3 |  | 63 | – | – | 28,7B |
| 4 |  | – | 75 | 73 | 3,9T |
| 5 | | – | 59 | 54 | 2,6T |
Modèles les plus rapides
Vitesse de sortie médiane la plus élevée parmi plusieurs fournisseurs.
| Rang | Modèle | Débit | TTFT p50 | Fournisseurs |
|---|---|---|---|---|
| 1 |  | 733 tok/s | 176ms | 27 |
| 2 | | 500 tok/s | 257ms | 23 |
| 3 | 448 tok/s | 216ms | 5 | |
| 4 | | 417 tok/s | 295ms | 11 |
| 5 |  | 368 tok/s | 237ms | 2 |
Alias toujours à jour
Épinglez un identifiant de modèle et obtenez toujours la version la plus récente de cette famille.
| Rang | Modèle | Jetons de la famille | Contexte |
|---|---|---|---|
| 1 | 5,1T | 1M | |
| 2 | | 52,9B | 33K |
| 3 | | 1T | 1,1M |
| 4 |  | 4,8T | 1M |
| 5 | | 65,5T | 1M |
Modèles gratuits
Les modèles les plus utilisés disposant d’un point de terminaison gratuit.
| Rang | Modèle | Jetons/sem. | Contexte |
|---|---|---|---|
| 1 | 2,9T | 1M | |
| 2 | 2,6T | 1M | |
| 3 | 1T | 1M | |
| 4 | 740,3B | 512K | |
| 5 | 374,5B | 1M |
Modèles d’image
Générez et modifiez des images avec les principaux fournisseurs de modèles.
Modèles vidéo
Générez des vidéos à partir de prompts textuels et d’images auprès des principaux fournisseurs de modèles.
Explorez chaque modalité
Commencez par une sélection ciblée de modèles adaptés à votre tâche.
Parcourir tous les modèlesRecherchez, filtrez, triez et comparez l’ensemble du catalogue sur la page des modèles.
Voir les 602 modèles