Kimi K2 0711
Open weightToolsMoonshotAI · Released July 2025 · Knowledge cutoff December 2024
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass.
It belongs to Moonshot AI's Kimi family, open-weight models known for agentic tool use, where K3 leads and the K2.x Code and Thinking variants target their namesake strengths.
Facts and pricing
- Provider
- MoonshotAI
- Context window
- 131K tokens
- Input price
- 6.8 credits / 1M tokens ($0.57 raw)
- Output price
- 27.6 credits / 1M tokens ($2.30 raw)
- Vision (image input)
- No
- Tool calling
- Yes
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin. Raw prices shown per 1M tokens.
Try Kimi K2 0711 now
What Kimi K2 0711 is best for
- Everyday chat and drafting on an open-weight model with transparent lineage
- Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows
Example prompts
Prompts that suit a open weight model like Kimi K2 0711:
- Draft a project update from these rough notes
- Explain how HTTPS works to a curious teenager
- Turn this list of features into a changelog entry
- Brainstorm objections to this proposal and how to answer them
MoonshotAI family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| Kimi K3.1 Pro | 1.0M | 24.0 | 120 | October 2026 |
| Kimi K3 | 1.0M | 2.3 | 192 | July 2026 |
| Kimi K3 (batch) | 1.0M | 27.4 | 137 | July 2026 |
| Kimi K2.7 Code | 262K | 7.2 | 42.0 | June 2026 |
| Kimi K2.6 | 262K | 7.8 | 40.9 | April 2026 |
| Kimi K2.5 | 262K | 6.0 | 30.0 | January 2026 |
| Kimi K2 Thinking | 262K | 7.2 | 30.0 | November 2025 |
| Kimi K2 0905 | 262K | 7.2 | 30.0 | September 2025 |
| Kimi K2 0711 | 131K | 6.8 | 27.6 | July 2025 |
Model comparisons
- Kimi K2 Thinking vs DeepSeek V4 Pro 0423
- Grok Build 0.1 vs Kimi K2.7 Code
- Kimi K2.7 Code vs Codestral 2508
- Kimi K2.7 Code vs Kimi K2 Thinking
Frequently asked questions
- What is Kimi K2 0711?
- Kimi K2 0711 is an AI model by MoonshotAI. Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass.
- How much does Kimi K2 0711 cost on Zeplik?
- Input tokens cost 6.8 credits per million and output tokens 27.6 credits per million (1 credit = $0.10; the raw provider rates are $0.57 and $2.30 per million). New accounts start with free credits.
- How long can a conversation with Kimi K2 0711 be?
- Kimi K2 0711 has a 131K-token context window (131,072 tokens), which covers the conversation plus any documents you attach.
- Does Kimi K2 0711 support images and tools?
- Kimi K2 0711 is text-only and supports tool calling.
Related models
Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window.
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts.
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.
Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm.
More you can do with Kimi K2 0711
- 468 AI skillsReady-to-run expert methods for writing, data, code and more, each running on Kimi K2 0711 or any model you pick.
- 997 integrationsConnect Gmail, Slack, GitHub, Notion and hundreds more so the assistant can work in your apps.
- Simple pricingPlus, Pro and Max plans with a monthly credit allowance that works across every model.