OpenClaw logo

Best open-source models for OpenClaw

Open source

Open-weight models you can inspect, fine-tune, and self-host. A natural fit for OpenClaw, which is a self-hostable operator runtime, so you can keep the whole stack in-house with no per-token bill. We rank a deep bench here because most of OpenClaw's real volume goes to open weights.

We also have more in-depth OpenClaw rankings:Best free models for OpenClawBest models for OpenClaw
The ranking
Updated June 2026
  • 1MoonshotAI
    Kimi K2.6Moonshot AIThe strongest open-weight agentic model right now (47.6% on CursorBench).
    Context262K
    Input$0.68/M
  • 2DeepSeek
    DeepSeek V4DeepSeekFrontier-class reasoning with open weights, cheap to host yourself.
    Context1.049M
    Input$0.435/M
  • 3Zhipu
    GLM 5.1Z.AIZhipu's open-weight flagship, strong at long agentic sessions.
    Context203K
    Input$0.98/M
  • 4Qwen
    Qwen3 Coder 480B A35BQwenOpen-weight coding specialist sized for big repositories.
    Context1.049M
    Input$0.22/M
  • 5M
    MiMo-V2.5-ProXiaomiXiaomi's open-weight MoE, a capable all-rounder for long agent sessions.
    Context1.049M
    Input$0.435/M
  • 6Minimax
    MiniMax M2.7MiniMaxCompact open MoE that punches above its price on coding benchmarks.
    Context205K
    Input$0.25/M
  • 7Nvidia
    Nemotron 3 SuperNvidiaNvidia's open-weight model, very cheap to self-host for high-volume runs.
    Context1M
    Input$0.09/M
  • 8Nvidia
    Nemotron 3 UltraNvidiaNvidia's larger open-weight model, a step up from Super for harder reasoning.
    Context1M
    Input$0.5/M
  • 9DeepSeek
    DeepSeek V4 FlashDeepSeekThe cheapest DeepSeek tier, same open weights for high-volume, low-stakes steps.
    Context1.049M
    Input$0.098/M
  • 10OpenAI
    gpt-oss-120bOpenAIOpenAI's open-weight generalist, dependable for everyday work and the cheapest to host.
    Context131K
    Input$0.039/M
  • 11Qwen
    Qwen3 Next 80B A3B InstructQwenFast open-weight MoE for quick reasoning and routine sub-agent steps.
    Context262K
    Input$0.09/M
  • 12M
    MiMo-V2.5XiaomiThe cheaper MiMo tier, same open weights for routine high-volume work.
    Context1.049M
    Input$0.14/M
  • 13Stepfun
    Step 3.5 FlashStepFunStepFun's fast open MoE, cheap for routine actions and sub-agents.
    Context262K
    Input$0.09/M
Share:
Details:
  • Agent


    OpenClaw logoOpenClaw
  • Models


    13
  • Filter


    Open source
  • Updated


    June 2026
Ad
Website favicon