questions 12
+How many AI models can I access through Requesty?
Requesty routes to 212 models across 33 providers, 682 deployable endpoints in total, 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.
+Does Requesty charge markup on top of provider pricing?
No. Requesty passes through exactly what the upstream provider charges. You pay the same per-token rate as going direct to OpenAI, Anthropic or Google, and you get smart routing, automatic failover, prompt caching, analytics, and a single unified API included. Requesty makes money on a small platform fee for enterprise features, not on per-token markup.
+What is the difference between a model and an endpoint?
A model is the weights a lab trained, like Claude Sonnet or Qwen3 Coder. An endpoint is one provider serving that model in one region, written provider/model@region. The same model often has a dozen endpoints at different prices and speeds, which is why this catalog can group 682 endpoints into 212 models. Expand any row to see every deployment of that model.
+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. See the leaders table above for live rankings, and each model detail page for full benchmark charts.
+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?
The largest context window in this catalog is 2M tokens, enough for whole-codebase analysis or long document reasoning. 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 endpoints on Requesty have a zero-cost tier, including several Llama variants and DeepSeek models via third-party hosts. They are ideal for prototyping and development. Use the free filter in the explorer above.
+Can I use embedding, image, speech and transcription models too?
Yes. Alongside the chat catalog the router serves 46 models on the other OpenAI-compatible paths: 15 embedding, 10 image, 12 speech and 9 transcription. Embeddings go to POST /v1/embeddings, image generation to POST /v1/images/generations, text to speech to POST /v1/audio/speech and transcription to POST /v1/audio/transcriptions, all on the same base URL and the same key. Use the api switch above the table to see them, each priced the way its provider charges it: per token for embeddings, per character or per token for text to speech, and per minute of audio for Whisper.
+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-4-7", "openai/gpt-5.2", "google/gemini-2.5-pro"). 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.
