Qwen3.8 Max
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.
$12.00 + $9.18 + $1.26 = $22.44
How much to trust these numbers
New flagship, GA (not preview); text plus image/video understanding. Single price tier across the full 1M window; thinking and non-thinking modes priced the same. Plain rate — no promotional discount, unlike Qwen3.7 Max. The cached column uses the official $0.17/M explicit cache-read rate; implicit cache is $0.25/M. 1M-token free quota for 90 days.
Alibaba Cloud Model Studio's qwen3.8-max model page, Singapore/International endpoint, captured 2026-08-28: $2/M input, $6/M output, $0.25/M implicit cached input, $2.50/M explicit cache creation and $0.17/M explicit cache read. The cached column uses the published explicit cache-read rate, matching the meaning used by the other Qwen cached-input rows; the earlier 10% derivation was not valid for this Qwen3.8 exception. A separate Global deployment-scope table prices this model lower, at $1.65/M input and $4.951/M output; the tracked lane is International.
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.
- GPT-5.2 / CodexOpenAI / Azure OpenAIFoundry ·Global$22.89CHF 18.43+$0.45 (+2%) vs this lane
- GPT-5.3 Codex / ChatOpenAI / Azure OpenAIFoundry ·Global$22.89CHF 18.43+$0.45 (+2%) vs this lane
- GLM-5.1GLM · Z.ai direct APIDirect API$23.36CHF 18.81+$0.924 (+4%) vs this lane
- GLM-5.2GLM · Z.ai direct APIDirect API$23.36CHF 18.81+$0.924 (+4%) vs this lane
- GLM-5.3GLM · Z.ai direct APIDirect API$23.36CHF 18.81+$0.924 (+4%) vs this lane
- DeepSeek-V4 ProDeepSeek · Fireworks-hostedFoundry ·Data Zone$21.26CHF 17.12-$1.18 (-5%) vs this lane