Skip to content

Models

PEKPIK LLM exposes 170+ models across chat, code, embeddings, image, video and audio. The live catalogue and pricing are always on the pricing section of the website.

The standard OpenAI models endpoint returns everything your key can call:

Terminal window
curl https://aiapiv2.pekpik.com/v1/models \
-H "Authorization: Bearer $PEKPIK_KEY"
Use caseExample model IDs
Flagship chatclaude-opus-4-7, gpt-5.4, gemini-2.5-pro
Cost-efficient chatdeepseek-v3.2, glm-4.6, kimi-k2.5, gemini-2.5-flash
Reasoningdeepseek-r1-0528, kimi-k2-thinking
Codecodestral-latest
Embeddingstext-embedding-3-small, text-embedding-3-large
Imagesgpt-image-2, gemini-2.5-flash image models
Audiowhisper-1 (transcription), TTS voices

The exact model and version you request is what runs. We never quantize, distill, or silently substitute a cheaper model, and we continuously spot-check live outputs against each provider’s reference behaviour.

Token models are billed per 1M input/output tokens; media models per call. Prices are quoted in USD on the pricing page and confirmed at provisioning. See Billing.