MAI-Thinking-1
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 + $10.80 + $1.68 = $24.48
How much to trust these numbers
Microsoft Foundry public preview, Global Standard only. PTU deployment is not currently supported. The commercial majority excludes the two higher-priced US Government regions.
Azure Retail Prices API, serviceName 'Foundry Models', productName 'MAI Models', captured 2026-09-16: effective 2026-08-01 meters 'MAI-Thinking-1 Inp glbl 1M Tokens' at $2.00/M, 'MAI-Thinking-1 Cd Inp glbl 1M Tokens' at $0.20/M, and 'MAI-Thinking-1 Opt glbl 1M Tokens' at $8.00/M across 32 commercial regions. The same meters carry separate usgovarizona/usgovvirginia rows at $2.50/$0.25/$10.00, excluded from the commercial-majority lane. Microsoft Learn confirms model version 2026-06-01, GlobalStandard deployment, 256K context and 64K output cap; Microsoft AI announced the model as a public-preview Foundry model on 2026-08-12.
Same-model deployment markup
How much this Foundry lane costs over the same model's Direct API rate.
Not available — no Direct API 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.
- Claude Sonnet 5ClaudeDirect API$24.90CHF 20.04+$0.42 (+2%) vs this lane
- Claude Sonnet 5ClaudeFoundry ·Global$24.90CHF 20.04+$0.42 (+2%) vs this lane
- Kimi K3.1 ProKimi · Kimi direct APIDirect API$24.90CHF 20.04+$0.42 (+2%) vs this lane
- GPT-6 SolOpenAI / Azure OpenAI · OpenAI direct APIDirect API$24.90CHF 20.04+$0.42 (+2%) vs this lane
- GPT-6 SolOpenAI / Azure OpenAIFoundry ·Global$24.90CHF 20.04+$0.42 (+2%) vs this lane
- GPT-5.2 / CodexOpenAI / Azure OpenAIFoundry ·Data Zone$25.18CHF 20.27+$0.699 (+3%) vs this lane