LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen/Qwen2.5-72B-Instruct

alibaba·alibaba/qwen2.5-72b-instruct·GA·Open weights·qwen series
Qwen instruction model for multilingual chat, reasoning, and tool use

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·SiliconFlowCloud
$0.59 / $0.59
Blended $0.59 · 1× spread
Context
33,000
Output limit
4,000
Knowledge cutoff
—
Released / updated
2024-09-18 / 2025-11-25
Capabilities
Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
Modalities
Text

Available at 2 providers2 with public prices

  • ProviderInput / Output
  • SiliconFlowCloud
    Qwen/Qwen2.5-72B-Instruct
    $0.59 / $0.59
    Context 33,000Output limit 4,000
  • SiliconFlow (China)Cloud
    Qwen/Qwen2.5-72B-Instruct
    $0.62 / $0.62
    Context 33,000Output limit 4,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
SiliconFlow
Qwen/Qwen2.5-72B-Instruct
Cloud$0.59$0.59——33,0004,000
SiliconFlow (China)
Qwen/Qwen2.5-72B-Instruct
Cloud$0.62$0.62——33,0004,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

Common scenarios
1SiliconFlow$147.50
2SiliconFlow (China)$154.30
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list —Output list —Min blended $0.59

Price history accumulates from each data sync; currently only 1 sample(s) (2026-08-05). Each future sync adds a point, and once accumulated a line is drawn here.

Related models

Qwen4 Maxsame series—Qwen 3.6 Plus Uncensoredsame series—Qwen 3.8 27B Uncensoredsame series—
Data partly from models.dev (MIT)