Call a Specialist Today! (02) 9388 1741
Browse and Compare 1,600+ AI Models
The definitive model catalog explore every major LLM with side-by-side cost, latency, context window, and capability comparisons. Pick the right model for every use case.
Find the Right Model for Every Job
Portkey's Model Catalog gives you the data to make smart model selection decisions across cost, speed, quality, and capability dimensions all in one place.
Comprehensive Coverage
1,600+ models indexed across OpenAI, Anthropic, Google, Mistral, Meta, Cohere, and hundreds more all queryable from one place.
- 1,600+ models indexed
- 200+ providers covered
- Updated continuously
- Open and closed source
Side-by-Side Comparison
Compare models on cost per token, latency, context window, supported modalities, and benchmark scores in a single view.
- Cost per input/output token
- Context window size
- Latency benchmarks
- Benchmark score comparison
Real-Time Pricing Data
Up-to-date pricing data for every model and provider so you can optimise cost without guesswork or manual research.
- Real-time price updates
- Input and output token pricing
- Compare across providers
- Historical price tracking
Latency Benchmarks
Measured p50 and p99 latency from Portkey's global gateway infrastructure see real-world performance before you commit.
- p50 and p99 latency
- Measured from global infra
- Per-provider comparison
- Updated continuously
Capability Filters
Filter by modality, context length, fine-tuning support, function calling, and compliance certifications to narrow to the right model fast.
- Filter by modality
- Context window filter
- Fine-tuning support flag
- Compliance certification filter
One-Click Gateway Integration
Every model in the catalog is accessible via the Portkey AI Gateway switch models without changing your application code.
- Direct gateway integration
- No code changes to switch
- Config-driven model selection
- A/B test via catalog
Stop Guessing Choose Models With Data
The AI model landscape changes every week. Portkey's Model Catalog gives you current, accurate data on cost, latency, and capabilities so you can make confident model decisions and switch without engineering effort.
- 1,600+ models across 200+ providers in one place
- Real-time pricing and latency benchmarks
- Side-by-side capability comparison
- Integrated with AI Gateway for instant switching