Models

OpenAI's open-weight 120B reasoning model. Strong at coding, tool use and agentic tasks; the drop-in replacement Groq recommends for Llama 3.3 70B.

DeepSeek's fast, inexpensive V4 model with a 1M-token context. Strong general assistant and coding model at the lowest price per token here.

The newest DeepSeek Flash model: better reasoning and tool use than V4 Flash, still with a 1M-token context.

Z.ai's fast GLM 5.3 model with tool calling, JSON mode and a 1M-token context, at a low per-token price.

Meta's instruction-tuned 70B model. Still served here after its retirement on Groq — the same <code>llama-3.3-70b-versatile</code> id works unchanged.

The small GPT-OSS model: fast and inexpensive for lightweight assistants and classification.

Compact vision-language model for image understanding, OCR and screenshot reasoning.

Fast, natural open-weight text-to-speech with 54 voices across 8 languages, on the OpenAI <code>/v1/audio/speech</code> endpoint.

Expressive Llama-based text-to-speech with emotive tags and eight English voices.

OpenAI's multilingual speech recognition model on the standard <code>/v1/audio/transcriptions</code> endpoint — same request shape as OpenAI and Groq.

NVIDIA's very fast English-first transcription model with accurate timestamps; ideal for long recordings and batch jobs.

Parse screenshots into structured, labeled UI elements for computer-use agents.