apixlyapixly.ai

Available models157

AI models and API prices

Compare model prices, discounts and 24-hour success rates by group. Sign in to see your account prices.

Group statusAvailable models
Loading model prices…

Explore models by task

  1. Choose a task and open a model to compare its public groups, billing units and conditions.
  2. Create an Apixly API key and bind a group that lists the exact model ID.
  3. Use the model guide for one small request; verify completed output and actual usage before increasing traffic.
Create and bind an API key
Check model access first
curl --fail-with-body --max-time 30 'https://apixly.ai/v1/models' -H "Authorization: Bearer $APIXLY_API_KEY" | python3 -c 'import json, sys
models = json.load(sys.stdin).get("data", [])
if not models: raise SystemExit("No visible models; check the key and its bound groups")
print(json.dumps([item["id"] for item in models], ensure_ascii=False, indent=2))'

Embeddings

Endpoint guide

Reranking

Endpoint guide

Audio

Endpoint guide

Text generation

Endpoint guide

Image generation

Endpoint guide

Video generation

Endpoint guide
Available models · 157

Pricing questions

How is caching charged?

Cache reads and writes are listed separately. Cache writes use the 5-minute rate, and your effective group rate applies to the listed price.

Do audio and embedding use the same units?

No. Each model lists its own unit: characters, audio seconds, requests, input entries or tokens. Retrieval prices can change at 26 inputs per request.

How are discounts calculated?

Each comparable discount uses the matching official price for the same model, billing unit and conditions. Prices come from the live model catalog.

Open complete model plaza ↗