AI Models · Open-Source Alternatives

Open-Source Alternatives to Claude Sonnet 4.6

The best open-weight, self-hostable alternatives to Claude Sonnet 4.6 in 2026 — compared on price, context window and capabilities. Run them locally and cut API costs.

Refreshed from live data · OpenSourceAI.tech

The best open-weight alternatives to Claude Sonnet 4.6

Claude Sonnet 4.6 is a proprietary, API-only model. These open-weight models can be self-hosted, run offline and used at a fraction of the cost — here's how the top ones stack up.

DeepSeek V4 Flash Open

DeepSeek · 1M ctx · $0.19/M out

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

DeepSeek V4 Flash vs Claude Sonnet 4.6 →

GLM 5.2 Open

Z.AI · 1M ctx · $2.44/M out

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

GLM 5.2 vs Claude Sonnet 4.6 →

MiniMax M3 Open

MiniMax · 1M ctx · $1.2/M out

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

MiniMax M3 vs Claude Sonnet 4.6 →

Nemotron 3 Ultra (free) Open

NVIDIA · 1M ctx · Free/M out

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

Nemotron 3 Ultra (free) vs Claude Sonnet 4.6 →

Kimi K3 Open

Moonshot AI · 1M ctx · $15/M out

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

Kimi K3 vs Claude Sonnet 4.6 →

gpt-oss-120b Open

OpenAI · 131K ctx · $0.17/M out

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 optimize

gpt-oss-120b vs Claude Sonnet 4.6 →

See the full open-source leaderboard

Live ranking of open-weight models with pricing, context windows and capabilities.

Open the leaderboard →