GPT-6 Luna
MiMo-V2.6-Flash
GLM 5.3 Prime- input
- $0.37
- cached
- $0.075
- output
- $1.25
- Context
- 1Mtokens
- Listed
- 1w ago
Cost/1M tokens
Language model from Z.ai, listed on OpenRouter on November 2, 2026.
- Multimodal model
- Accepts images, video
- 1M context
- Reasoning
- Tools
- Structured output
How it compares
Level
LightweightThe lab's smallest, cheapest and lowest-latency hosted line, built for high volume and simple tasks.
Lightweight models from other labs
Vs. your stack
Add the models you use to see how this one compares.
Sign inFrequently asked questions
API and pricing
The GLM 5.3 FlashX Legal API costs $0.37 per 1M tokens for input and $1.25 per 1M tokens for output. There is 1 paid provider tracked.
Yes, prompt caching is supported. Cached input costs $0.075 per 1M tokens versus $0.37 per 1M tokens uncached, an 80% discount.
$0.00495 at the cheapest provider, Z.AI, for a typical request of 10,000 input tokens and 1,000 output tokens.
1 endpoint had uptime data in the last day and 1 was at 99% uptime or better. The best uptime was 100.0%, by Z.AI.
Privacy and data
Z.AI. It is the provider with zero data retention (ZDR eligible or 0-day retention) for GLM 5.3 FlashX Legal.
Capabilities and specs
The context window is 1M tokens (1,048,576) and the maximum output is 131K tokens (131,072).
Yes for images and video. The listed input modalities are text, image and video, with no audio or PDF support listed.
Yes, tool calling (function calling) is supported.
Yes, structured output (JSON schema or JSON mode) is supported.
Yes, reasoning mode is supported and reasoning is always on. Effort levels are max, high and low with max as the default. The reasoning_effort setting is offered by 1 of 1 tracked providers.
Quality and benchmarks
Matched on model kind, blended price and release date, the alternatives are Hy4 by Tencent at $0.6254 per 1M tokens, MiMo-V2.6-Pro by Xiaomi at $0.5438 per 1M tokens, and Beam 1.0 501B A23B by Reflection AI at $0.475 per 1M tokens.
Hy4GLM 5.3 FlashX Legal vs Hy4MiMo-V2.6-ProGLM 5.3 FlashX Legal vs MiMo-V2.6-ProBeam 1.0 501B A23BGLM 5.3 FlashX Legal vs Beam 1.0 501B A23B
Versions and lineage
Both have a 1M token (1,048,576) context. GLM 5.3 FlashX Legal costs $0.37 input and $1.25 output per 1M tokens and was released November 2, 2026, while GLM 5.3 costs $0.0699 input and $1.40 output per 1M tokens and was released August 14, 2026.
Basics
Z.ai. It was first listed on OpenRouter on November 2, 2026.
No, it is not listed as free. The listed API price is $0.37 input and $1.25 output per 1M tokens, and its openness is unknown.
Generated from Vertical Tabs data, updated November 11, 2026.
Discussion
No comments yet
Be the first to share your thoughts.