Models
Browse available models routable through Multi-Router. Compare capabilities, pricing, and specs.
Current Models
Claude Haiku 4.5
anthropic/claude-haiku-4-5The fastest model with near-frontier intelligence. Best for low-latency, high-volume workloads.
Claude Opus 4.6
anthropic/claude-opus-4-6The most intelligent model for building agents and coding. Exceptional performance in reasoning, complex analysis, and multi-step tasks.
Claude Sonnet 4.6
anthropic/claude-sonnet-4-6The best combination of speed and intelligence. Ideal for high-throughput tasks requiring strong reasoning.
Gemini 2.5 Flash
google/gemini-2.5-flashBest price-performance model for large scale processing, low-latency, high-volume tasks with thinking.
Gemini 2.5 Flash-Lite
google/gemini-2.5-flash-liteFastest and most budget-friendly multimodal model. Ideal for classification, extraction, and low-latency workloads.
Gemini 2.5 Pro
google/gemini-2.5-proState-of-the-art thinking model for complex problems in code, math, STEM, and long-context analysis.
Gemini 3 Flash
google/gemini-3-flash-previewFrontier-class reasoning and multimodal understanding at a fraction of the cost of larger models.
Gemini 3.1 Flash-Lite
google/gemini-3.1-flash-lite-previewMost cost-efficient multimodal model. Optimized for high-frequency lightweight tasks like translation and data extraction.
Gemini 3.1 Pro
google/gemini-3.1-pro-previewAdvanced intelligence with better thinking, improved token efficiency, and factual consistency. Optimized for software engineering and agentic workflows.
MiniMax M2.5
minimax/minimax-m2-5General-purpose model with tool use and 197K context. Free tier.
Nemotron 3 Nano 30B A3B
nvidia/nemotron-3-nano-30b-a3bCompact MoE model for efficient text generation with 256K context. Free tier.
Nemotron 3 Super
nvidia/nemotron-3-superMoE model (120B total, 12B active) optimized for text tasks with 262K context. Free tier.
Nemotron Nano 12B 2 VL
nvidia/nemotron-nano-12b-2-vlCompact vision-language model with 128K context. Free tier.
Nemotron Nano 9B V2
nvidia/nemotron-nano-9b-v2Compact reasoning model with 128K context. Free tier.
GPT-4.1
openai/gpt-4.1Excels at instruction following and tool calling with broad knowledge across domains. 1M token context.
GPT-5
openai/gpt-5Strong coding, reasoning, and agentic capabilities across domains with built-in reasoning tokens.
GPT-5 Mini
openai/gpt-5-miniNear-frontier intelligence for cost-sensitive, low-latency, high-volume workloads.
GPT-5 Nano
openai/gpt-5-nanoFastest and cheapest GPT-5 variant. Optimized for summarization and classification tasks.
GPT-5.4
openai/gpt-5.4Most capable frontier model. Exceptional at complex professional work with configurable reasoning depth.
GPT-5.4 Pro
openai/gpt-5.4-proPremium tier using extended compute for harder problems. Best for research-grade reasoning tasks.
o3
openai/o3Sets a new standard for math, science, coding, and visual reasoning tasks with highest reasoning capability.
o3-pro
openai/o3-proExtended compute version of o3 for harder problems. Best for research-grade reasoning tasks.
o4-mini
openai/o4-miniFast, cost-efficient reasoning model optimized for coding and visual tasks.
Qwen3 Coder 480B A35B
qwen/qwen3-coder-480b-a35bMoE coding model (480B total, 35B active) with tool use and 262K context. Free tier.
Qwen3 Next 80B A3B Instruct
qwen/qwen3-next-80b-a3b-instructMoE instruction-tuned model with tool use and 262K context. Free tier.
Step 3.5 Flash
stepfun/step-3-5-flashMoE model (196B total, 11B active) with strong reasoning and 256K context. Free tier.
GLM 4.5 Air
z-ai/glm-4-5-airReasoning model with 131K context from Zhipu AI. Free tier.
Legacy Models
Still available but consider migrating to current models for improved performance.