OpenRouter

OpenRouter pricing details

• Free plan available
• paid plans from $0.07/1M tokens

Pay-per-token, no monthly fees; 374+ models; free models: 20 req/min, 50 req/day (under $10 lifetime credits) or 1000/day ($10+); BYOK 1M free routing requests/mo; cheapest free models (DeepSeek R1, Llama 3.3 70B, Gemma 3, Gemini Flash) all rate-limited; paid models start at ~$0.07/1M input for small open models

In our index: Free plan available; paid from $0.07/1M tokens

How OpenRouter scores across our 6 index dimensions

• Functionality: 5/5 (research only)
• Usability: 4/5 (research only)
• Stability: 4/5 (research only)
• Collaboration: 3/5 (research only)
• Localization: 3/5 (research only)
• Value: 5/5 (research only)

Score rationale: Research-only: broadest model selection by far; free tier has daily caps that tighten before $10 spend; BYOK support is unique; English-only interface

What OpenRouter does well

• Best dimension: Core features at 5/5 — backed by verification against the official site & pricing.
• Second strong point: Value for money at 5/5.
• Pricing: Pay-per-token, no monthly fees
• Positioning: OpenRouter is the largest AI model gateway — 374+ models from Anthropic, OpenAI, Google, DeepSeek and more, with free tiers, BYOK support, and unified OpenAI-compatible API.
• Source check: Research-only: broadest model selection by far; free tier has daily caps that tighten before $10 spend; BYOK support is unique; English-only interface

Where OpenRouter falls short

• Weakest dimension: Localization at 3/5.
• Weigh localization before committing.

How OpenRouter compares to other AI API Gateways tools

Our index tracks 5 AI API Gateways tools. OpenRouter sits at 4.3/5, with paid plans from $0.07/1m tokens. Here are the 4 closest alternatives we hold pricing and scoring evidence for.

• Groq — 4.2/5 · Free plan · $0.05/1M tokens
  Groq runs open-source LLMs on custom LPU chips that deliver 500+ tokens per second — the fastest inference API available, with a generous free tier and no credit card required.
• Fireworks AI — 4.0/5 · $1 free credit for new accounts · $0.10/1M tokens
  Fireworks AI runs 200+ open-source LLMs with a self-serve post-training stack (SFT/LoRA/RL) and 99.9% uptime SLA — pay-per-token serverless, no GPU provisioning, Day-0 support for new open weights.
• Together AI — 3.9/5 · $5 free signup credit · $0.05/1M tokens
  Together AI is an open-model inference platform with 100+ open-source models, fine-tuning support, and dedicated GPU capacity — built for production AI teams.
• DashScope — 3.8/5 · Free plan · ¥0.20/1M tokens (~$0.03)
  DashScope is Alibaba Cloud's AI model service — Qwen, GLM, MiniMax and other Chinese models with OpenAI-compatible API, free credit promotions, and native Chinese support.