Qwen3.8 Max
Alibaba's Qwen3.8 flagship with hybrid thinking (default on) and vision support.
- Input price
- $1.485–$2.00list $1.6510% off
- Output price
- $4.4559–$6.00list $4.95110% off
- Context
- 1M
- Max output
- 131K
- Capability
- 158 (#29 of 82)
- Human preference
- 1486
- 30-day uptime
- —
InputTextImageOutputText
Providers
Providers that serve this model. With Auto, each request goes to the best available provider. Prices in USD per 1M tokens; stats cover the last 30 days.
Pricing
Prices vary by provider. Showing Alibaba Cloud (Model Studio Intl), the lowest. Pick a provider above to see its prices.
- Input
- $1.485list $1.6510% off
- per 1M tokens
- Output
- $4.4559list $4.95110% off
- per 1M tokens
- Cache read
- $0.1854list $0.20610% off
- per 1M tokens
- Explicit cache read
- $0.1233list $0.13710% off
- per 1M tokens
- Cache write (5 min)
- $1.8567list $2.06310% off
- per 1M tokens
Estimated cost of common use (500 output tokens each)
- One chat message
- $0.00668
- 3K input tokens
- Agent first turn
- $0.188
- 100K tokens of context, none cached
- Each later agent turn
- $0.0245
- context read from cache, plus 2K new tokens
- 20-turn agent task
- $0.653
- first turn plus 19 more
Try it
Runs on your balance and is billed like any API request.
Similar models
Other models with the same output types at a similar price.
Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-11-18): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text