Descobrir modelos

Pontos de partida práticos com base no uso real do OpenRouter, no desempenho em produção e em avaliações comparativas independentes.

Explorar todos os 624 modelos
A fronteira de hoje

Claude Fable 5.2 assume a liderança na fronteira

Anthropic supera Google por 5 pontos no índice de inteligência da Artificial Analysis.

ModeloInteligência (0–100)

Auto is OpenRouter’s flagship model router, built for general-purpose usage. It adapts to each request, choosing cost-optimal models and adjusting reasoning effort. It balances task difficulty, benchmark results, live prices, and prompt caching. Use it for apps, chat, and general agents. For agent sessions, it follows progress across turns, keeps the same model while work is going well, and adjusts reasoning effort or switches models when the task gets stuck. It respects all your governance settings, including guardrails, ZDR, and budgets.

Auto Code is OpenRouter’s router built specifically for coding agents and harnesses. It uses the same routing engine as the [Auto Router](https://dynamicsinfo.com/openrouter/auto), with every request treated as part of an agent session and model choices guided by coding-task pass rate, completion time, and cost per solved task. It follows edits, test results, and recurring errors across turns, keeping the model while work is going well and trying more reasoning effort before switching when trouble persists. Its default coding tier starts from stronger models and weighs failed code changes more heavily. Your model and provider restrictions still apply.

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).

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 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://dynamicsinfo.com/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://dynamicsinfo.com/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).

Líderes em custo-benefício

A maior capacidade por dólar do preço de tabela.

PosiçãoModeloPercentil de inteligênciaPercentil de programaçãoPercentil agênticoTokens
1
Favicon de z-ai
GLM 5.3 Flash
40799111,9T
2
Favicon de deepseek
DeepSeek V4 Flash 0731 (batch)
–757382,5M
3
Favicon de inclusionai
Ling 3.0 Flash VL
–60576B
4
Favicon de anthropic
Claude Haiku 5.5 (batch)
65––30,4B
5
Favicon de deepseek
DeepSeek V4 Flash 0423
–59542,2T

Modelos mais rápidos

Maior mediana de velocidade de saída entre vários provedores.

PosiçãoModeloTaxa de processamentoTTFT p50Provedores
1
Favicon de qwen
Qwen3.8 27B
883 tok/s253ms23
2
Favicon de openai
gpt-oss-120b
832 tok/s138ms26
3
Favicon de deepseek
DeepSeek V4.1 Flash 1017
492 tok/s209ms48
4
Favicon de meta-llama
Llama 3.1 8B Instruct
470 tok/s143ms4
5
Favicon de openai
gpt-oss-20b
423 tok/s117ms12

Aliases sempre atualizados

Fixe um ID de modelo e receba sempre a versão mais recente dessa família.

PosiçãoModeloTokens da famíliaContexto
1
Favicon de perplexity
Decider Flash Latest
32,5B262K
2
Favicon de anthropic
Claude Fable Latest
1T1M
3
Favicon de google
Gemini Flash Latest
4,1T1M
4
Favicon de z-ai
GLM Latest
5,1T1M
5
Favicon de liquid
d1-ultra Latest
44,1B33K

Modelos gratuitos

Os modelos mais usados com um endpoint gratuito.

PosiçãoModeloTokens/sem.Contexto
1
Favicon de nvidia
Nemotron 3 Ultra (free)
3,2T1M
2
Favicon de nvidia
Nemotron 3.5 Super VL (free)
3T1M
3
Favicon de baidu
ERNIE-5.5-Flash-Preview (free)
1,9T1M
4
Favicon de nvidia
Nemotron 3.5 Lightning (free)
1,2T1M
5
Favicon de thinkingmachines
Inkling 2 Small (free)
1,1T1M

Modelos de imagem

Gere e edite imagens com os principais provedores de modelos.

Ver todos

Modelos de vídeo

Gere vídeos a partir de prompts de texto e imagem com os principais provedores de modelos.

Ver todos

Explore todas as modalidades

Comece com um conjunto direcionado de modelos para a tarefa que você precisa realizar.

Explorar todos os modelosPesquise, filtre, ordene e compare o catálogo completo na página de modelos.
Ver todos os 624 modelos