AI models
Compare AI models available through the Pawan.Krd OpenAI-compatible API. Browse capabilities, context windows, providers, and model details to choose a model for your application.
17 models
CosmosRP v4.0 PRO
pkrd/cosmosrp-4.0-proOur latest and highest-quality model designed for creativity, roleplay and general tasks with deep thinking ability
CosmosRP v4.0
pkrd/cosmosrp-4.0Our latest and highest-quality model designed for creativity, roleplay and general tasks
CosmosRP v3.5
pkrd/cosmosrp-3.5Best quality, optimized for roleplay
CosmosRP V2.1
pkrd/cosmosrp-2.1Excellent, optimized for roleplay
DeepSeek V4 Flash (0731)
deepseek-ai/DeepSeek-V4-Flash-0731DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.
PKRD-TTS (Kurdish TTS)
pkrd/tts-kuOur latest TTS model for generating high-quality Kurdish speech.
PKRD-ASR Large (Kurdish ASR)
pkrd/asr-ku-largeOur latest ASR model for accurate Kurdish speech recognition.
Whisper Large V3
openai/whisper-large-v3Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation
Chatterbox Turbo TTS
ResembleAI/chatterbox-turboChatterbox is a family of three state-of-the-art, open-source text-to-speech models by Resemble AI.
DeepSeek V4 Flash
deepseek-ai/DeepSeek-V4-FlashDeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters.
DeepSeek V3.2
deepseek-ai/DeepSeek-V3.2DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance.
DeepSeek V3.1
deepseek-ai/DeepSeek-V3.1DeepSeek V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes.
MiniMax M2.5
MiniMaxAI/MiniMax-M2.5MiniMax-M2.5 is a SOTA large language model designed for real-world productivity.
Gemma 4 26B-A4B IT
google/gemma-4-26B-A4B-itStep 3.5 Flash
stepfun-ai/Step-3.5-FlashEngineered to deliver frontier reasoning and agentic capabilities with exceptional efficiency.
GPT-OSS - 120B
openai/gpt-oss-120bDesigned for powerful reasoning, agentic tasks, and versatile developer use cases.
GPT-OSS - 20B
openai/gpt-oss-20bExcellent model, can be used for general tasks.
How do I choose an AI model?
Start with the input and output your application needs, then compare model capabilities, context windows, and credit costs. Open a model to check its supported parameters and plan access. Model availability and capabilities vary.
Compare API pricing and plans or follow the API quickstart to make your first request.