Cost, capability, and real-world signals translated into decisions your business team can act on.
Low-latency transcription and reliable context for regulated workflows.
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 ro
tencent/hy3:free // Cost-aware generation const result = await ai.generateContent(prompt); // Track usage and quality
Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://pools
poolside/laguna-xs-2.1:free // Cost-aware generation const result = await ai.generateContent(prompt); // Track usage and quality
North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse m
cohere/north-mini-code:free // Cost-aware generation const result = await ai.generateContent(prompt); // Track usage and quality
NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA,
nvidia/nemotron-3.5-content-safety:free // Cost-aware generation const result = await ai.generateContent(prompt); // Track usage and quality
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B
nvidia/nemotron-3-ultra-550b-a55b:free // Cost-aware generation const result = await ai.generateContent(prompt); // Track usage and quality
NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free // Cost-aware generation const result = await ai.generateContent(prompt); // Track usage and quality
Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai/), optimized for c
poolside/laguna-m.1:free // Cost-aware generation const result = await ai.generateContent(prompt); // Track usage and quality
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Desp
google/gemma-4-26b-a4b-it:free // Cost-aware generation const result = await ai.generateContent(prompt); // Track usage and quality
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image inp
google/gemma-4-31b-it:free // Cost-aware generation const result = await ai.generateContent(prompt); // Track usage and quality
Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation model
google/lyria-3-pro-preview // Cost-aware generation const result = await ai.generateContent(prompt); // Track usage and quality
Input and output prices from OpenRouter are normalized to a blended cost per million tokens.
LMSYS Arena Elo adds a reality check from blind, human-voted model comparisons.
Context limits and provider availability help teams choose an engine that fits the actual workflow.