Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.
Listed rates
Price across providers
Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.
Lowest input$0.4/M
Across 35 priced providers
Median input$1/M
Midpoint of listed rates
Highest input$1.101/M
2.8× the lowest listed rate
Output range$1.75 – $3.362
Per million output tokens
Vultr$0.4/MLowest
CrofAI$0.48/M
Alibaba (China)$0.573/M
DevPass (LLM Gateway)$0.573/M
Zhipu AI$0.598/M
CrossModel$0.6/M
Deep Infra$0.6/M
GMI Cloud$0.6/M
FastRouter$0.6/M
DInference$0.75/M
Meganova$0.8/M
TokenGo$0.89/M
Charm Hyper$0.93/M
Cortecs$0.988/M
Vercel AI Gateway$1/M
Hugging Face$1/M
Novita AI$1/M
OpenCode Go$1/M
Merge Gateway$1/M
OrcaRouter$1/M
Z.AI$1/M
Abacus$1/M
OpenCode$1/M
Amazon Bedrock$1/M
Together AI$1/M
OpenRouter$1/M
Vertex$1/M
TensorX$1/M
Impossibl$1/M
Kilo Gateway$1/M
Ofox$1/M
Eden AI$1/M
Tempr Gateway$1/M
Poe$1/M
Melious$1.101/M
Cost calculator
Estimate a workload
$0.00
Excludes taxes, non-token charges, and tiered discounts.
Context limits also differ by provider, from 200K to 205K tokens. Compare the provider table above before choosing on price alone.
Specification
Capabilities
Recorded from the source catalog and provider listings.
Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.
Each axis is this model's percentile among the 4 benchmarks it has published results for, measured against every other model with a score on that same benchmark. Percentiles are used because benchmarks do not share a scale — a 60 on one is not a 60 on another. Hover any point for the raw score.
Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.
Cost against capability
Price and performance
Listed input price plotted against SWE-Bench Verified, the benchmark with the widest published coverage that this model appears in.
The stepped line is the efficient frontier: at each price, the best score available for that money or less. A model sitting on it is not being beaten by anything cheaper. Price is log-scaled because listed rates span four orders of magnitude. Only models with both a listed price and a score on this benchmark can appear.
Catalog activity
Change log
Field-level changes detected between successful source imports.
Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.
What is GLM-5?
General GLM flagship for coding, analysis, and tool-heavy engineering workflows. It is published by Zhipu AI and catalogued here from Models.dev.
How much does GLM-5 cost?
Listed input pricing starts at $0.4 per million tokens from Vultr, rising to $1.101 across 35 listed providers.
What is the context length of GLM-5?
GLM-5 accepts up to 204.8K tokens of context and returns up to 131.072K output tokens.
Does GLM-5 support tool calling and structured output?
Provider catalogs list support for tool calling, and reasoning.
Which providers serve GLM-5?
41 providers list this model: Alibaba Token Plan (China), Alibaba Coding Plan (China), Tencent Coding Plan (China), Alibaba Coding Plan, Alibaba Token Plan, SCNet Token Plan and 35 more.
Are the weights for GLM-5 open?
Yes. The weights are published and downloadable from Hugging Face.
When was GLM-5 released?
The catalog records a release date of 2026-02-12, last verified Oct 24, 2026.
Alibaba Coding Plan
Vultr
Zhipu AI
CrossModel
Deep Infra
GMI Cloud
FastRouter
DInference
Meganova
Cortecs
Hugging Face
Novita AI
OpenCode Go
Merge Gateway
OrcaRouter
Abacus
Amazon Bedrock
Together AI
OpenRouter
TensorX
Impossibl
Ofox
Poe