Question 1

How many AI models are on AIgateway?

Accepted Answer

1050+ across text, image, video, audio (STT + TTS), embeddings, rerank, moderation, and classification — from 85+ labs. The live catalog is at /v1/models.

Question 2

Which is the best LLM to use today?

Accepted Answer

For quality-first agentic work: Claude Opus 4.8. General production default: Claude Sonnet 4.6 or GPT-5.5. Very long context (>500K): Gemini 3.1 Pro (2M tokens). Best cost/quality open-weight: Kimi K2.7 Code or MiniMax M3.

Question 3

Which is the cheapest LLM API?

Accepted Answer

Cheapest way to start: add a card (no charge) for $1 in credit across a curated trial catalog of 16 models, led by GLM-5.3 Flash. The $1 expires 30 days after you add the card. Cheapest paid: GPT-5.4-nano and Gemini 3.1 Flash-Lite at ~$0.05 per 1M input tokens.

Question 4

Which model has the longest context window?

Accepted Answer

Gemini 3.1 Pro at 2 million tokens, followed by GPT-5.5 at 1 million tokens.

Question 5

Can I filter models by capability?

Accepted Answer

Yes — filter by modality (text/image/audio/video/embed), provider, vision, tool calling, reasoning, streaming, trial catalog, price, and context window. The URL supports deep-links, e.g. /models?modality=image&provider=google.

Add a card, get $1 free — starting with GLM-5.3 Flash.