Skip to content
Sovyron

Pendra

6 modelsProvider docs

As of Oct 4, 2026, Pendra lists 6 supported models in the Sovyron catalog, including DeepSeek V4 Flash, Qwen3.6 27B, GLM-4.7-Flash, GPT OSS 120B and Qwen3-Coder 30B-A3B Instruct — deepseek-flash, qwen, glm-flash, gpt-oss and llama families. Every price in the table is Pendra's own, normalized to USD — open a model to compare it with the cheapest offer across all providers. Offer mix: 6 free-tier offers.

Supported models and pricing

6 of 6 models
Pendra model prices in USD per 1M tokens, updated Oct 4, 2026
Model1M input1M output1M cache readContextReleasedTags
DeepSeek V4 Flashfreefree—1.0MApr 24, 2026free
Qwen3.6 27Bfreefree—262kApr 22, 2026free
GLM-4.7-Flashfreefree—200kJan 19, 2026free
GPT OSS 120Bfreefree—131kAug 5, 2025free
Qwen3-Coder 30B-A3B Instructfreefree—262kApr 1, 2025free
Llama-3.3-70B-Instructfreefree—128kDec 6, 2024free