200+ models supported

Every Model.
One Memory.

Switch between GPT-5, Claude Opus, Gemini 3, Llama, and 200+ more — your memory follows seamlessly.

swap models, keep memory
// Monday: Use GPT-5.2
model: "gpt-5.2"

// Tuesday: Try Claude
model: "anthropic/claude-opus-4.5"

// Wednesday: Test Gemini
model: "google/gemini-3-pro"

// Memory persists across all of them ✓

No lock-in. No migration. Just change the model parameter.

OpenAIFlagship
Context
128K

GPT-5.2

OpenAI's flagship model. Improved personality, creativity, and reasoning.

VisionCreativeAgentic
OpenAI
Context
128K

GPT-5.1

Strong general-purpose model. Excellent balance of capability and cost.

VisionFunction CallingJSON Mode
OpenAIPro
Context
128K

GPT-4.5

Large pre-trained model for Pro users. Deep knowledge and nuance.

VisionResearchAnalysis
OpenAIReasoning
Context
200K

o3

Most powerful reasoning model. SOTA on coding, math, and science benchmarks.

Chain-of-ThoughtSOTAScience
OpenAIPremium
Context
200K

o1-pro

Premium reasoning with extended compute. Best for the hardest problems.

ExpertResearch
OpenAIReasoning
Context
200K

o1

Advanced reasoning model. Thinks before responding for complex tasks.

Chain-of-ThoughtMathCode
AnthropicFlagship
Context
200K

Claude Opus 4.6

Most capable Claude. Best for coding, agents, and complex reasoning.

VisionCodingAgentic
AnthropicPopular
Context
200K

Claude Sonnet 4.5

Best balance of speed, intelligence, and cost. Great for everyday tasks.

VisionBalancedAnalysis
Anthropic
Context
200K

Claude Haiku 4.5

Fastest and cheapest Claude. Lightning-fast for simple tasks at scale.

VisionUltra FastLow Cost
GoogleFlagship
Context
1M

Gemini 3 Pro

Most advanced multimodal model. Perfect for analyzing entire codebases or documents.

VisionAudioVideo
Google1M Context
Context
1M

Gemini 3 Flash

Fast and scalable with massive context. Great for real-time apps.

VisionFastMultimodal
Google1M Context
Context
1M

Gemini 2.5 Pro

Strong predecessor with native tool use and agentic capabilities.

AgenticTool UseReasoning
Google
Context
1M

Gemini 2.5 Flash

Fast and cost-efficient. Excellent for high-volume multimodal workloads.

FastLow CostMultimodal
Meta via OpenRouterFlagship
Context
1M

Llama 4 Maverick

128-expert MoE flagship. Industry-leading multimodal with 17B active params. Beats GPT-4o.

VisionMoE 128EMultilingual
Meta via OpenRouter10M Context
Context
10M

Llama 4 Scout

16-expert MoE with industry-leading 10M context. Fits on single H100. Best in class.

VisionLong ContextOpen Weights
Meta via OpenRouter
Context
128K

Llama 3.3 70B

Best price-to-performance open model. Excellent general-purpose capabilities.

Open WeightsBalancedCoding
Mistral via OpenRouterFlagship
Context
256K

Mistral Large 3

41B/675B MoE flagship. World's best open-weight multimodal model. Apache 2.0 license.

VisionMoEAgentic
Mistral via OpenRouter
Context
128K

Ministral 3 14B

Best-in-class edge model. Vision + reasoning in 14B params. Perfect for local deployment.

VisionEdgeOpen Weights
Mistral via OpenRouter
Context
128K

Mistral Small 3.2

24B enterprise-ready compact model. Vision capabilities with Apache 2.0 license.

VisionFastOpen Weights
And More

200+ More Models

Cohere, Perplexity, Together, and dozens more. If it's on OpenRouter, it works with MemoryRouter.

CoherePerplexityTogether+ more

Ready to Add Memory?

One line change. Same code. Persistent memory across every model.