# Open Weights apps

> 32 open weights models and apps on inference shell.

**URL:** https://inference.sh/apps/tag/open-weights

---

- [Pika H3 Flex (self-hosted)](https://inference.sh/apps/pika/pika-h3-flex-oss.md) `pika/pika-h3-flex-oss`: GPU time, billed per millisecond
- [JEV-9B](https://inference.sh/apps/autotrust/jev-9b.md) `autotrust/jev-9b`: from $0.00055833/sec
- [AutoTrust-JEV-27B v1.1](https://inference.sh/apps/autotrust/jev-27b-v1-1.md) `autotrust/jev-27b-v1-1`: from $0.00055833/sec
- [Decision 3.0 d3 27B](https://inference.sh/apps/vllm-sr/d3.md) `vllm-sr/d3`: GPU time, billed per second
- [Decision 3.0 d3-flash 9B](https://inference.sh/apps/vllm-sr/d3-flash.md) `vllm-sr/d3-flash`: GPU time, billed per second
- [Decision 3.0 d3-mini 4B](https://inference.sh/apps/vllm-sr/d3-mini.md) `vllm-sr/d3-mini`: GPU time, billed per second
- [Decision 3.0 d3-nano 2B](https://inference.sh/apps/vllm-sr/d3-nano.md) `vllm-sr/d3-nano`: GPU time, billed per second
- [Decision 3.0 d3-lite 0.8B](https://inference.sh/apps/vllm-sr/d3-lite.md) `vllm-sr/d3-lite`: GPU time, billed per second
- [Decision 3.0 d3-edge 0.6B](https://inference.sh/apps/vllm-sr/d3-edge.md) `vllm-sr/d3-edge`: GPU time, billed per second
- [d1-omni-600M](https://inference.sh/apps/liquid/d1-omni-600m.md) `liquid/d1-omni-600m`: GPU time, billed per second
- [d1-3B](https://inference.sh/apps/liquid/d1-3b.md) `liquid/d1-3b`: GPU time, billed per second
- [Perplexity Decider v1.1 27B](https://inference.sh/apps/perplexity/decider-v1-1-27b.md) `perplexity/decider-v1-1-27b`: GPU time, billed per second
- [Decision 2.0 Vega 27B](https://inference.sh/apps/vllm-sr/decision-2-0-vega-27b.md) `vllm-sr/decision-2-0-vega-27b`: GPU time, billed per second
- [JEV-27B-VL](https://inference.sh/apps/autotrust/jev-27b-vl.md) `autotrust/jev-27b-vl`: free for a limited time
- [Decision 2.0 Lux 9B](https://inference.sh/apps/vllm-sr/decision-2-0-lux-9b.md) `vllm-sr/decision-2-0-lux-9b`: GPU time, billed per second
- [Decision 2.0 Nox 4B](https://inference.sh/apps/vllm-sr/decision-2-0-nox-4b.md) `vllm-sr/decision-2-0-nox-4b`: GPU time, billed per second
- [Decision 2.0 Sol 2B](https://inference.sh/apps/vllm-sr/decision-2-0-sol-2b.md) `vllm-sr/decision-2-0-sol-2b`: GPU time, billed per second
- [Decision 2.0 Eos 0.8B](https://inference.sh/apps/vllm-sr/decision-2-0-eos-0-8b.md) `vllm-sr/decision-2-0-eos-0-8b`: GPU time, billed per second
- [Decision 2.0 Kai 0.6B](https://inference.sh/apps/vllm-sr/decision-2-0-kai-0-6b.md) `vllm-sr/decision-2-0-kai-0-6b`: GPU time, billed per second
- [Kimi K3](https://inference.sh/apps/melious/kimi-k3.md) `melious/kimi-k3`: $3.1828/M input, $0.7957/M cached input, $15.9138/M output
- [GLM 5.2](https://inference.sh/apps/melious/glm-5-2.md) `melious/glm-5-2`: $1.1367/M input, $0.2842/M cached input, $4.5468/M output
- [GLM 5.2](https://inference.sh/apps/openrouter/glm-5-2.md) `openrouter/glm-5-2`: $1.00/M input, $4.00/M output
- [Kimi K2](https://inference.sh/apps/openrouter/kimi-k2.md) `openrouter/kimi-k2`: $0.60/M input ($0.60/M cached), $2.50/M output
- [FLUX.2 [klein]](https://inference.sh/apps/infsh/flux-2-klein.md) `infsh/flux-2-klein`: GPU time, billed per millisecond
- [Kimi K2 Thinking](https://inference.sh/apps/openrouter/kimi-k2-thinking.md) `openrouter/kimi-k2-thinking`: $0.60/M input ($0.15/M cached), $2.50/M output
- [Qwen3 30B A3B](https://inference.sh/apps/infsh/qwen3-30b-a3b.md) `infsh/qwen3-30b-a3b`: GPU time, billed per millisecond
- [RIFE Video Interpolation](https://inference.sh/apps/infsh/rife-video-interpolation.md) `infsh/rife-video-interpolation`: GPU time, billed per millisecond
- [Audio-X Generator](https://inference.sh/apps/infsh/audio-x.md) `infsh/audio-x`: GPU time, billed per millisecond
- [Mistral Small 3.2 24B Instruct](https://inference.sh/apps/infsh/mistral-small-3-2-24b-it-2506.md) `infsh/mistral-small-3-2-24b-it-2506`: GPU time, billed per millisecond
- [Gemma 3n E4B Instruct](https://inference.sh/apps/infsh/gemma-3n-e4b-it.md) `infsh/gemma-3n-e4b-it`: GPU time, billed per millisecond
- [Magistral Small 2506](https://inference.sh/apps/infsh/magistral-small-2506.md) `infsh/magistral-small-2506`: GPU time, billed per millisecond
- [GLM-4.6](https://inference.sh/apps/openrouter/glm-46.md) `openrouter/glm-46`: $0.43/M input tokens, $1.74/M output tokens