Switch between GPT-5.5, Claude Opus 4.8, Gemini 3.5, Llama 4, and 200+ more — your memory follows seamlessly.
// Monday: Use GPT-5.5
model: "gpt-5.5"
// Tuesday: Try Claude
model: "anthropic/claude-opus-4.8"
// Wednesday: Test Gemini
model: "google/gemini-3.5-flash"
// Memory persists across all of them ✓No lock-in. No migration. Just change the model parameter.
Smartest model yet — a new class of intelligence for real work. Agentic coding + knowledge work. $5/$30 per 1M.
Highest-accuracy option. Extended thinking for the most demanding tasks. $30/$180 per 1M.
Default ChatGPT model. Fast, natural, low hallucination in law/medicine/finance. Recalls past context.
Capable agentic workhorse with native computer use. Great balance of speed and intelligence.
Most capable agentic coding model. Combines reasoning with deep code intelligence.
Flagship model. Dynamic workflows orchestrating hundreds of subagents, 3x cheaper fast mode. $5/$25 per 1M.
Near-Opus performance. 1M context, strong computer use (72.5% OSWorld). $3/$15 per 1M.
Fastest and cheapest Claude. Lightning-fast for simple tasks at scale.
Next-gen frontier intelligence with action. Excels at agentic, long-horizon, and coding tasks. Default in the Gemini app.
Record-breaking ARC-AGI-2 (77.1%). Advanced reasoning, vibe coding, agentic workflows.
Most cost-effective. $0.25/$1.50 per 1M tokens, 2.5x faster than 2.5 Flash.
Best price-performance for low-latency, high-volume multimodal tasks.
Latest Mistral flagship-class model for enterprise reasoning and agents.
Latest Large-family Mistral model for broad enterprise workloads.
Fresh coding-focused Mistral model for software engineering agents.
Latest general Grok model for fast chat, reasoning, and tool-heavy agents.
High-capability Grok 4 line model available through OpenRouter.
xAI build-focused model for implementation-heavy agent workflows.
Latest DeepSeek Pro-class model for reasoning, coding, and cost-efficient production use.
Fast DeepSeek V4 variant for high-throughput applications.
Strong general DeepSeek model for chat, coding, and analysis.
Latest Perplexity search model for grounded answers and web-aware agents.
Perplexity reasoning model for research tasks that need grounded multi-step analysis.
Deep research model for long-form investigations and synthesis.
Cohere, Perplexity, Together, and dozens more. If it's on OpenRouter, it works with MemoryRouter.
One line change. Same code. Persistent memory across every model.
Start free with a 14-day trial. No credit card required.