Supernova Labs

About Supernova Labs

Supernova rebuilds inference around the real bottleneck — memory, not math — with kernels and predictive execution that never let a GPU wait. Maximum intelligence per chip, per watt, per dollar.

A better inference system. The inference cloud for open models — fast, affordable, and built to scale with you.

A serving stack tuned to the metal — per model, per accelerator — so deployments run at the speed the silicon actually allows.

A drop-in inference service for open models. Point your workload at our API and serve the same models far below standard cost — we keep the KV cache resident on cheap NAND and optimise the whole memory hierarchy for you. Strongest exactly where it hurts most: long context, high batch, and agent workloads.

Website ↗Documentation ↗

Source ↗ · 2026-11-12T04:15:26.633163180Z

Service status

unknown

Current inference service status unverified

2 indexed models

2 matching models

Z.ai: GLM 5.3

z-ai/glm-5.3-20260816

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency

Context window
1,048,576
Input modalities
text
Output modalities
text
Capabilities
promptCaching, reasoning, structuredOutputs, toolCalling

Benchmarks

  • Artificial Analysis: 31.7
  • OpenRouter Benchmarks: 78.829%
  • Vercel AI Gateway: 15.486%

Inference prices

  • Cached input tokens (per 1M) : $0.12 / cache_read_tokens_per_million · supernova ↗
  • Input tokens (per 1M) : $0.63 / input_tokens_per_million · supernova ↗
  • Output tokens (per 1M) : $1.98 / output_tokens_per_million · supernova ↗

Z.ai: GLM 5.2

z-ai/glm-5.2-20260616

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, and complex multi-step automation. Reasoning efforts `high` and `xhigh` are s

Context window
1,048,576
Input modalities
text
Output modalities
text
Capabilities
promptCaching, reasoning, structuredOutputs, toolCalling

Benchmarks

  • Artificial Analysis: 33.7
  • OpenRouter Benchmarks: 76.933%

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace