Skip to content
Sovyron

Atomic Chat

5 modelsProvider docs

As of Oct 4, 2026, Atomic Chat lists 5 supported models in the Sovyron catalog, including Gemma 4 E4B Instruct (IQ4_XS), Gemma 4 E4B Instruct (MLX 4-bit), Qwen 3.5 9B (MLX 4-bit), Qwen 3.5 9B (Q4_K_M) and Meta Llama 3.1 8B Instruct (GGUF) — gemma, qwen and llama families. Every price in the table is Atomic Chat's own, normalized to USD — open a model to compare it with the cheapest offer across all providers. Offer mix: 5 free-tier offers.

Supported models and pricing

5 of 5 models
Atomic Chat model prices in USD per 1M tokens, updated Oct 4, 2026
Model1M input1M output1M cache readContextReleasedTags
Gemma 4 E4B Instruct (IQ4_XS)freefree—33kApr 2, 2026free
Gemma 4 E4B Instruct (MLX 4-bit)freefree—33kApr 2, 2026free
Qwen 3.5 9B (MLX 4-bit)freefree—33kMar 5, 2026free
Qwen 3.5 9B (Q4_K_M)freefree—33kMar 5, 2026free
Meta Llama 3.1 8B Instruct (GGUF)freefree—131kJul 23, 2024free