🌐 All Models
408 models · Page 4 of 12
ministral-8b-2512
Ministral 3 (a.k.a. Tinystral) 8B Instruct.
magistral-medium-2509
Our frontier-class reasoning model release candidate September 2025.
pixtral-large-2411
Official pixtral-large-2411 Mistral AI model
command-r7b-arabic-02-2025
command-a-reasoning-08-2025
llama-3.3-70b-versatile
Meta's Llama 3.3 70B — latest iteration with improved instruction following, served on Groq LPU.
groq/compound-mini
magistral-small-2509
Our efficient reasoning model released September 2025.
openai/gpt-oss-safeguard-20b
gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...
ministral-14b-2512
Ministral 3 (a.k.a. Tinystral) 14B Instruct.
magistral-medium-2509
Our frontier-class reasoning model release candidate September 2025.
open-mistral-nemo
Our best multilingual open source model released July 2024.
command-a-vision-07-2025
groq/compound
ministral-8b-2512
Ministral 3 (a.k.a. Tinystral) 8B Instruct.
llama-3.1-8b-instant
Meta's Llama 3.1 8B served on Groq's LPU for ultra-low latency — ideal for fast, lightweight text tasks.
pixtral-large-2411
Official pixtral-large-2411 Mistral AI model
mistral-vibe-cli-latest
Devstral 2512 release model
mistral-small-2506
Our latest enterprise-grade small model with the latest version released June 2025.
mistral-medium-2508
Update on Mistral Medium 3 with improved capabilities.
devstral-2512
Official devstral-2512 Mistral AI model
devstral-medium-2507
Our medium code-agentic model.
openai/gpt-oss-120b
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
gpt-oss-120b
120b open-weight language model from OpenAI
gpt-oss-20b
20b open-weight language model from OpenAI
kimi-k2-thinking
Kimi K2 Thinking is the latest, most capable version of an open-source thinking model.
kimi-k2-thinking
kimi-k2-thinking — available to run locally via Ollama on CPU and GPU hardware.
gpt-oss:20b
gpt-oss:20b — available to run locally via Ollama on CPU and GPU hardware.
qwen3-coder-next
qwen3-coder-next — available to run locally via Ollama on CPU and GPU hardware.
gemini-3-flash-preview
gemini-3-flash-preview — available to run locally via Ollama on CPU and GPU hardware.
gpt-oss:120b
gpt-oss:120b — available to run locally via Ollama on CPU and GPU hardware.
Llama-3.1-70B-Instruct
Open-source Llama-3.1-70B-Instruct model from meta-llama — available for download and self-hosting on Hugging Face.
minimax-m2
minimax-m2 — available to run locally via Ollama on CPU and GPU hardware.
Llama-3.2-3B-Instruct
Open-source Llama-3.2-3B-Instruct model from meta-llama — available for download and self-hosting on Hugging Face.
Elephant
Elephant Alpha is a 100B-parameter text model focused on intelligence efficiency, delivering strong performance while minimizing token usage. It supports a 256K context window with up to 32K output tokens,...
Qwen3-30B-A3B-Instruct-2507
Open-source Qwen3-30B-A3B-Instruct-2507 model from qwen — available for download and self-hosting on Hugging Face.