GLM-5.3-FlashX
Fresh input / cached input / output cost breakdown, active and scheduled rates, provenance, same-model deployment markup, and cost-comparable alternatives for this purchasable lane.
Illustrative workloads
Pick a useful starting shape, then fine-tune every input below.
Workload and pricing scenario
Adjust the token shape, cache behavior, time window, and service tier. Every number below updates immediately.
Workload cost calculator
Share of input tokens served from cache. Applied only to models with a cache meter.
Rows with a rate that changes by time of day, promo window or service tier are priced for this scenario instead of their flat listed rate; a brand-colored label under the model name names which one applies. Context size for band-priced rows uses the input-token count below.
Picking a specific hour also previews time-of-day rates that are scheduled but have not started billing yet; those rows are labelled · preview with their start instant. Now only ever shows rates that are billable at this moment.
What this lane charges right now
Priced under the workload and scenario above. The full published schedule below always shows every variant regardless of which scenario is selected.
Where this workload's cost goes
60M input tokens (90% cache hit) and 210K output tokens, at the resolved rate above.
$2.22 + $4.05 + $0.263 = $6.53
How much to trust these numbers
Faster-serving sibling of GLM-5.3-Flash with the same multimodal 1M-token context and 128K maximum output. Z.ai's model guide says FlashX is live through the API but not yet available on the GLM Coding Plan.
Z.ai official pricing page (docs.z.ai/guides/overview/pricing), captured 2026-09-18: GLM-5.3-FlashX is listed at $0.37/M input, $0.075/M cached input and $1.25/M output; the separate 'Limited-time Free' label applies to cached-input storage, which this schema does not model. Z.ai's official model guide (docs.z.ai/guides/vlm/glm-5.3-flash), captured 2026-09-18, identifies the API code as glm-5.3-flashx, supports video/image/text/file input, and lists a 1M-token context with 128K maximum output. A full paged Azure Retail Prices API sweep captured 2026-09-18 found no FlashX meter, so this is a direct-only lane.
Same-model deployment markup
How much more Microsoft Foundry charges for this exact model, over this Direct rate.
Not available — no Microsoft Foundry listing exists for this exact model in the catalog.
Other lanes within ±25% of this workload's cost
Same provider first, then ranked by cost proximity, for 60M in / 210K out. This is a cost ranking only — never a quality recommendation.
- Qwen3.6 PlusQwen · Model Studio (Intl)Direct API$6.33CHF 5.10-$0.202 (-3%) vs this lane
- Claude Haiku 5.5 Over 100K PromptClaudeDirect API$6.23CHF 5.01-$0.307 (-5%) vs this lane
- Claude Haiku 5.5 Over 100K PromptClaudeFoundry ·Global$6.23CHF 5.01-$0.307 (-5%) vs this lane
- Claude Haiku 5.5 Over 100K PromptClaudeFoundry ·Data Zone$6.85CHF 5.51+$0.315 (+5%) vs this lane
- MiniMax 3MiniMax · Fireworks-hostedFoundry ·Data Zone$5.82CHF 4.69-$0.711 (-11%) vs this lane
- DeepSeek-V4 ProDeepSeek · DeepSeek direct APIDirect API$5.56CHF 4.48-$0.969 (-15%) vs this lane