Requesty
Live catalog/29 labs/12 free to call/2M context

Compare 684+ AI models.

Flagship and open-weight models from OpenAI, Anthropic, Google, AWS Bedrock, Azure, DeepSeek, Meta, xAI, Mistral, Moonshot and more, through one OpenAI-compatible API. Prices shown are provider rates; pay as you go adds 5%, or 0% on your own keys.

207
unique models
684
unique endpoints
30
unique providers
18,180
data points in the catalog
Benchmark rankingsDocs →
Price spread 1,500x
207

Frequently asked questions

Everything you need to know about accessing hundreds of AI models through a single API.

How many AI models can I access through Requesty?
Requesty routes to 684+ models across 30 providers, including OpenAI, Anthropic, Google Gemini, AWS Bedrock, Azure OpenAI, Google Vertex AI, DeepSeek, Meta Llama, xAI Grok, Mistral, Moonshot Kimi, Alibaba Qwen, Zhipu GLM and MiniMax. Use any of them through a single OpenAI-compatible API.
What is the difference between a model and an endpoint?
A model is one trained model, like Claude Sonnet 4.5. An endpoint is one provider's deployment of it in one region, and popular models have a dozen of those at different prices, context limits and data policies. The catalog holds 207 models served by 684 endpoints. The explorer above switches between the two views: Models groups every deployment onto one row, Endpoints lists them all so you can compare price and region directly.
Does Requesty charge markup on top of provider pricing?
On pay as you go, Requesty adds 5% to the upstream provider rate: a model that costs $10 per 1M tokens costs $10.50 through Requesty. Bring your own provider keys and the markup is 0%. Either way, smart routing, automatic failover, prompt caching, analytics and a single unified API are included, with no per-seat or per-request fees.
Which model is best for coding?
On SWE-Bench Verified (the most realistic coding benchmark, based on real GitHub issues) GPT-5.2 Codex, Claude Opus 4.7 and Claude Sonnet 4.6 currently lead. MiniMax M2.5 is the strongest open-weights option. The coding leaderboard ranks thirty models on live scores, and each model page carries its full benchmark chart.See the coding leaderboard→
Which model is best for reasoning and math?
For graduate-level reasoning (GPQA Diamond), GPT-5.4, Grok 4 and Claude Opus 4.7 lead the pack. For math (AIME, MATH benchmarks), GPT-5.4 and Grok 4 currently top the charts, with DeepSeek R1 offering strong performance at a fraction of the price.
What is the longest context window available?
Several models now support 1M+ token context windows, great for whole-codebase analysis or long document reasoning. Gemini 2.5 Pro and some Claude variants lead on context length. Note that effective quality often degrades past 128K tokens; prompt caching (supported on many models) is usually a better approach for repeated long context.
Are there free AI models I can use?
Yes, 12 models on Requesty have a zero-cost tier, including several Llama variants and DeepSeek models via third-party hosts. They're ideal for prototyping and development. You can filter by "Free" in the model explorer above.Browse all free models→
How do I switch between models in my code?
Requesty is OpenAI-SDK compatible. Point base_url to "https://router.requesty.ai/v1", set your API key, and change the "model" parameter to any supported model ID (e.g. "anthropic/claude-opus-5", "openai/gpt-5.6-sol", "vertex/gemini-3.7-flash"). No library changes needed. The same code works across providers.
Is my data private? Is it used for training?
Most major providers (Anthropic, Vertex AI, Azure OpenAI, AWS Bedrock) do not use API data for training by default. OpenAI offers zero-retention deployments via enterprise tiers. Each model detail page shows the specific data retention and training policy for that provider. Requesty itself never uses your data for training.
Can I get regional deployments (EU, US, APAC)?
Yes. Models available through AWS Bedrock, Azure OpenAI, and Google Vertex AI can be pinned to specific regions (eu-west-1, us-east5, etc.) using the @region suffix. Useful for GDPR, HIPAA, and data residency requirements. Filter by Region in the explorer to see all options.
How are benchmark scores calculated?
Benchmark scores shown on Requesty are sourced from official model cards, Artificial Analysis, and public leaderboards (LiveBench, SWE-Bench, Vellum). Scores measure specific skills and do not capture every aspect of model quality. Always test on your own workload. Each model detail page links the canonical benchmark sources.

Start building with Requesty

One line of code. 600+ models. Full control.

Speak to founders