OpenRouter
For each model on OpenRouter, latency (time to first token) and token throughput information is displayed for all providers. You can use this to estimate how long requests will take. If you want to optimize for throughput, you can use the :nitro variant to route to the fastest provider.
Pricing
Free
$/mo
- N/A Platform Fees
- 25+ free models
- 4 free providers
- 50 requests/day rate limit
- Free models only for token pricing
- Community Support
Pay-as-you-go
$/mo
- 5.5% Platform Fees
- 300+ models
- 60+ providers
- Credit card, crypto & more payment options
- 1M free BYOK requests/month (5% fee after)
- High global rate limits
- No minimum spend, token pricing based on models
- Email Support
- Regional routing available
- No platform-level rate limits
- 1000 request limit on free models for users with $10+ credits
Enterprise
$/mo
- Bulk discounts available for Platform Fees
- 300+ models
- 60+ providers
- Invoicing payment options
- 5M free BYOK requests/month; custom pricing after
- Optional dedicated rate limits
- Volume commitments, token pricing based on models
- Support SLA with Shared Slack Channel
- Admin Controls
- Data Policy-Based Routing
- Managed Policy Enforcement
- Provider Data Explorer
- SSO/SAML
- Contractual SLAs
- Regional routing available
Details
Pricing Tier
FreeCategories
Developer ToolsData Analysis
Target Audience
General PublicStartups
Integrations
Hub+3 more
Sponsor
Ad space