TOOLS · 7
#TOOLDESCRIPTIONPRICE/CALL
01LLM inference (Llama, Mistral, Gemma, Qwen, GLM, Granite)docsText completion via 20+ open-source language models. Micro to standard tier, priced from $0.001 per request.$0.001
02Vision inference (Llama 3.2 Vision, Llama 4 Scout)docsMultimodal image-understanding models for visual question-answering.$0.005
03Reasoning (QwQ 32B, DeepSeek R1)docsChain-of-thought reasoning models for complex multi-step problems.$0.015
04Image generation (FLUX.1 Schnell)docsText-to-image generation via FLUX.1 Schnell.$0.01
05Audio: Whisper STT / MeloTTSdocsSpeech-to-text transcription (Whisper) and text-to-speech synthesis (MeloTTS).$0.005
06Embeddings (BGE, Qwen3)docsDense text embeddings for semantic search and retrieval.$0.001
07Batch processingdocsBatch inference across multiple inputs in a single call.$0.05
Prices set by the provider and charged per successful call.