77
Stack Score
Best for
Developers and analysts who need massive context windows or Chinese-language tasks at a fraction of OpenAI pricing.
At a glance
- Pricing
- freemium
- Setup time
- Instant
- Learning curve
- easy
- Last verified
- 5/19/2026
What we love
- ✓Long context handles entire codebases or books in one prompt
- ✓Best-in-class Chinese language performance
- ✓Free tier is unusually generous for capability level
- ✓API pricing is cheaper than GPT-4 or Claude for similar tasks
Where it falls short
- −English writing trails GPT-4 and Claude in nuance
- −No native voice mode or computer use
- −Data residency in China — non-starter for some enterprises
Pricing
✓ Pricing verified Jun 21, 20262 tiers
Free
$0
forever
- ✓Chat on web and mobile
- ✓File uploads
- ✓Web search
API
From $0.15
per million input tokens
- ✓2M context
- ✓OpenAI-compatible API
- ✓Function calling
Why we picked it
The context window is genuinely large — useful when you need to drop in a whole codebase or book.
Overview
Moonshot AI's chat model with 2M+ token context window. Strong on long document analysis and Chinese-language tasks.
Key features
- ●Context window up to 2 million tokens
- ●Strong Chinese-language reasoning and writing
- ●File upload — PDFs, slides, audio for analysis
- ●Image input with vision reasoning
- ●Web search built into chat responses
- ●Code interpreter for Python execution
- ●API with OpenAI-compatible endpoints
Best use cases
Long document analysis
Drop a 1500-page contract or research paper and ask targeted questions in one prompt.
Chinese content creation
Marketing teams targeting mainland China get more native-feeling output than Western models.
Codebase Q&A
Paste an entire monorepo and ask architecture questions without splitting context.
Integrations
Similar tools
See all LLMs →One AI Stack pick every week.
The tool we’d pay for this week, why we’d pay for it, and what we’d skip. No promo spam.