GLM-5.1
Z.ai's flagship model for long-horizon agents and complex engineering tasks.
- Input price
- $0.66–$0.9636list $0.82520% off
- Output price
- $2.6408–$3.8544list $3.30120% off
- Context
- 200K
- Max output
- 128K
- Capability
- 151 (#59 of 82)
- Human preference
- 1463
- 30-day uptime
- —
- Released
- 2026-04-08
- Knowledge cutoff
- 2025-04
InputTextOutputText
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.
Prompt ≤ 32K tokens
- Input
- $0.66list $0.82520% off
- per 1M tokens
- Output
- $2.6408list $3.30120% off
- per 1M tokens
- Cache read
- $0.132list $0.16520% off
- per 1M tokens
- Explicit cache read
- $0.0664list $0.08320% off
- per 1M tokens
- Cache write (5 min)
- $0.8248list $1.03120% off
- per 1M tokens
Prompt > 32K tokens
- Input
- $0.88list $1.1020% off
- per 1M tokens
- Output
- $3.0808list $3.85120% off
- per 1M tokens
- Cache read
- $0.176list $0.2220% off
- per 1M tokens
- Explicit cache read
- $0.088list $0.1120% off
- per 1M tokens
- Cache write (5 min)
- $1.10list $1.37520% off
- per 1M tokens
Estimated cost of common use (500 output tokens each)
- One chat message
- $0.0033
- 3K input tokens
- Agent first turn
- $0.112
- 100K tokens of context, none cached
- Each later agent turn
- $0.0213
- context read from cache, plus 2K new tokens
- 20-turn agent task
- $0.517
- 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