ModelPriceWatch.com
Last scan 2026-10-20 Models tracked 301 Providers 40 Cheapest paid pplx-decider-flash-v1.2 $0.010/Mtok in Every price links to its source

GLM-5.3

by Together

Current mid tier open weights mid tier
Email me when GLM-5.3 gets cheaper

Today's price · per 1M tokens

Input

$1.40

per 1M tokens

Output

$4.40

per 1M tokens

Blended

$2.15

blended $/1M — 3:1 weighted input:output

Cached input

$0.260

19% of input — prompt caching

How this price is scoped: Read 2026-09-05 from Together's own serverless-models card (docs.together.ai/docs/serverless-models, the markdown surface the context gate also reads): zai-org/GLM-5.3 at input $1.40 / cached input $0.26 / output $4.40, context 1048575, quantization FP4. The triple is identical to Z.AI's first-party rate and to Fireworks' Standard rate for the same SKU. The 1,048,575-token window is what Together's card lists for THIS endpoint (docs/CONTEXT_WINDOW_CONVENTION.md) — it is Together's served window, not a claim read off the maker.

Source: official Together pricing · read MODELPRICEWATCH.COM · 2026-10-20

Price receipt

We read Together's own pricing page on and found GLM-5.3 listed with a price on the same row — that read is where the number above comes from. We keep the page text we read; its content hash is ebb76cf030.

GLM-5.3 is available on 3 hosts. See the full cheapest-first comparison on the consolidated GLM-5.3 page →

Overview

Z.AI's GLM-5.3 on Together. $1.40/$4.40 per 1M; cached input $0.26. Together serves it at 1,048,575 tokens in FP4.

Run it yourself

Deploy this open model on rented GPUs

Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.

RunPod →
Rent GPUs by the second and serve any open-weight model yourself.
Novita AI →
Serverless open-model inference billed per token — no GPU ops.
Vast.ai →
GPU marketplace — rent spot/on-demand GPUs cheaply and serve any open-weight model.

Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.

Capabilities

struck through = not supported
Input 1/4
Text ✓ Image Audio Video
Output
Text ✓
Features 3/9
Prompt caching ✓ Reasoning Coding Fast inference Long context ✓ Open weights ✓ Multimodal Web search Realtime

Benchmark performance

accuracy % · higher is better
Avg benchmark score76.5%
Perf per $/Mtok35.6
GPQA Diamond
88.1%
SWE-Bench Verified
95.4%
Terminal-Bench 2.1 vendor
88.2%
LiveCodeBench
80.5%
Humanity's Last Exam
42%
Independent composite scores
  • AA Intelligence Index: 44.8 (Artificial Analysis composite across reasoning, knowledge and coding evals)
  • AA-Omniscience Index: 14.3 (−100–100)
  • GDPval-AA v2: 1650.3 ELO (Real-world work tasks, human baseline = 1000)
How it stacks up
  • Ranks #24 of 101 benchmarked models by average score
  • Ranks #35 of 196 comparably-measured models by percentile score, across 7 independent measurements
  • Ranks #88 of 196 comparably-tested models by normalized performance per dollar
  • Strongest at SWE-Bench Verified — 95.4%, #7 of 40

71.6 tokens/sec output

Source: Artificial Analysis, Artificial Analysis (text-only, no tools, max), Z.AI model card (HF), Claude Code 2.1.207 harness · updated · See full rankings →

Specifications

Provider
Together
Context window
1M tokens
Modality
text
Parameters
Proprietary
Open source
Yes — open weights available
Released
Status
Current
Last updated
Tags
cachingmid-tieropen-weights

Availability verified: — listed on Together's own page

Try on Together Official pricing page