← LLM Directory
OpenRouter

OpenRouter

Hosted Platform

Unified API gateway to 400+ models from OpenAI, Anthropic, Google, Meta, and more. Pay per token, no subscriptions.

20 modelsCompare models →Website →Pricing →

Flagship2 models

ModelInput / 1MOutput / 1MContext
Claude 4 Opus
Best Claude model. Full power for complex tasks.
$15.00$75.00200K
GPT-5.2
Latest GPT model via OpenRouter.
$2.50$15.00256K

Reasoning3 models

ModelInput / 1MOutput / 1MContext
o3
OpenAI's reasoning model for hard problems.
$10.00$40.00200K
o4-mini
Affordable reasoning model.
$1.10$4.40200K
DeepSeek R1
Open-weight reasoning model.
$0.550$2.1964K

Coding1 model

ModelInput / 1MOutput / 1MContext
GPT-4.1
Long-context coding model.
$2.00$8.001.0M

RAG1 model

ModelInput / 1MOutput / 1MContext
Command A
Cohere's latest model for RAG and enterprise.
$0.950$3.80256K

Popular9 models

ModelInput / 1MOutput / 1MContext
Claude 4 Sonnet
Best price-performance Claude.
$3.00$15.00200K
Gemini 2.5 Pro
Google's best model with 1M context.
$1.25$10.001.0M
Gemini 2.5 Flash
Fast, affordable Gemini.
$0.150$0.6001.0M
DeepSeek V4
Incredible price-performance. 1M context.
$0.300$0.6001.0M
Kimi K2
Moonshot's latest coding model. MoE architecture.
$0.600$2.40131K
Mistral Large
Mistral's most capable model.
$2.00$6.00128K
Grok 3
xAI's flagship with real-time data access.
$3.00$15.00131K
MiniMax-M2.7
MiniMax with 1M context.
$0.300$1.201.0M
GPT-4.1 Mini
Affordable long-context model.
$0.400$1.601.0M

Budget1 model

ModelInput / 1MOutput / 1MContext
GPT-5 Nano
Ultra-cheap for classification and routing.
$0.050$0.300128K

Open Source2 models

ModelInput / 1MOutput / 1MContext
Llama 4 Maverick
Meta's latest open-weight model.
$0.200$0.600256K
Qwen3 235B-A22B
Top open-source MoE model.
$0.800$1.60128K

New1 model

ModelInput / 1MOutput / 1MContext
Nemotron 3 Ultra 253B
NVIDIA's flagship MoE model.
$0.800$2.40131K

Other Providers

OpenAIAnthropicGoogleDeepSeekxAIMetaMistralCohereMoonshot AIMiniMaxAlibaba Cloud (Qwen)NVIDIAOllamaTogether AI