MoonshotAI: Kimi K2.6 (free)
Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...
Anyone in the Space can @-mention MoonshotAI: Kimi K2.6 (free) with the team's shared context — pooled credits, one chat, one memory.
Starter is free forever — 1 Space, 100 credits/month, 1 MCP. No card.
Verdict
Best for
- Zero-budget long-context document processing
- Multilingual Chinese-English translation tasks
- High-volume content moderation workflows
- Vision tasks with tight cost constraints
- Prototyping before committing to paid models
Strengths
The 262K context window at zero cost is the standout feature — most free-tier models cap out at 32K or less. Native Chinese language support is strong, reflecting MoonshotAI's domestic focus. Image understanding works reliably for straightforward visual tasks like OCR, chart reading, and basic scene description. The model handles long documents without the context-splitting gymnastics required by shorter-window alternatives, which simplifies workflows for legal contracts, research papers, and multi-page reports.
Trade-offs
Reasoning quality trails GPT-4o and Claude Sonnet on multi-step logic problems and nuanced instruction-following. Latency can spike during peak hours, typical of free-tier infrastructure. English fluency is competent but less polished than models trained primarily on Western corpora — expect occasional awkward phrasing in creative writing or marketing copy. Vision capabilities are functional but shallow compared to GPT-4o or Gemini Pro Vision; complex diagrams or fine-grained visual reasoning will hit limits quickly.
Specifications
- Provider
- moonshotai
- Category
- llm
- Context length
- 262,144 tokens
- Max output
- —
- Modalities
- text, image
- License
- proprietary
- Released
- 2026-04-20
Pricing
- Input
- $0.00/Mtok
- Output
- $0.00/Mtok
- Model ID
moonshotai/kimi-k2.6:free
Per-token prices show what the model costs upstream. On Switchy your team draws from one shared org credit pool — one plan, one balance for everyone.
Team cost calculator
5 seats · 80 msgs/day
Switchy meters this against your org's shared credit pool — one plan, one balance for everyone.
Providers
| Provider | Context | Input | Output | P50 latency | Throughput | 30d uptime |
|---|---|---|---|---|---|---|
| moonshotai | 262k | $0.00/Mtok | $0.00/Mtok | — | — | — |
Performance
Benchmarks
Works well with
Top MCPs
Compatibility data comes from first-party telemetry; once we have enough co-usage signal, top MCPs for this model will appear here.
How Switchy teams use it
Starter prompts
Summarize Long Contract
Read this contract and list all payment terms, delivery deadlines, and termination clauses in a numbered list. Flag any ambiguous language.Open in a Space →
Translate Technical Docs
Translate this Chinese technical specification to English. Keep all section headers, table structures, and technical terms consistent throughout.Open in a Space →
Extract Data from Invoice
Extract the vendor name, invoice number, line items with quantities and prices, subtotal, tax, and total from this invoice image. Return as JSON.Open in a Space →
Compare Policy Versions
Compare these two policy documents and list every substantive change between version 1 and version 2. Ignore formatting differences.Open in a Space →
Generate FAQ from Transcript
Read this transcript and create a FAQ with 10-15 questions that customers would likely ask. Provide concise answers based only on what's discussed.Open in a Space →