Kimi K2
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in Kimi K2, it activates 32 billion parameters per forward pass and supports 256 k-token context windows. The model is optimized for persistent step-by-step thought, dynamic tool invocation, and complex reasoning workflows that span hundreds of turns. It interleaves step-by-step reasoning with tool use, enabling autonomous research, coding, and writing that can persist for hundreds of sequential actions without drift. It sets new open-source benchmarks on HLE, BrowseComp, SWE-Multilingual, and LiveCodeBench, while maintaining stable multi-agent behavior through 200–300 tool calls. Built on a large-scale MoE architecture with MuonClip optimization, it combines strong reasoning depth with high inference efficiency for demanding agentic and analytical tasks.
- Input / output price
- $0.57 / $2.30 per 1M
- Context
- 131K tokens
- Released
- Jul 11, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
3 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Novita novita/kimi-k2 | $0.57/M | $2.30/M |
Featherless featherless/kimi-k2 | $0.60/M | $2.50/M |
OpenRouter openrouter/kimi-k2 | $0.57/M | $2.30/M |
Is a provider down? OpenRouter status
Pricing
Averaged across 3 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $0.58 per 1M
- Average output
- $2.37 per 1M
- Average cache read
- $1.00 per 1M
Cost by volume
Total cost from 0 to 1T tokens on the cheapest and most expensive provider.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better4.8tokens/sacross providers
Response latency
Lower is better1.7sacross providers
Benchmarks
The Respan Index plus 19 published scores from 5 sources, each linked to where it was published.
17.6/ 100
Respan Index#146 of 176
- 146Kimi K217.6
- 145o3-mini17.7
- 147Qwen3.5 4B17.5
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Aider-Polyglothuggingface.co | 60% | huggingface.co | Jul 11, 2025 |
| LiveCodeBench v6 (Aug 24 - May 25)huggingface.co | 53.7% | huggingface.co | Jul 11, 2025 |
| WeirdMLHåvard Tveit Ihle | 39.4% | Håvard Tveit Ihle | Oct 5, 2026 |
| TerminalBench (Inhouse Framework)huggingface.co | 30% | huggingface.co | Jul 11, 2025 |
| GSO Opt@1GSO | 2% | GSO | Aug 26, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Tau2 retailhuggingface.co | 70.6% | huggingface.co | Jul 11, 2025 |
| SWE-bench Verified (Agentic Coding, single attempt)huggingface.co | 65.8% | huggingface.co | Jul 11, 2025 |
| Tau2 telecomhuggingface.co | 65.8% | huggingface.co | Jul 11, 2025 |
| Tau2 airlinehuggingface.co | 56.5% | huggingface.co | Jul 11, 2025 |
| SWE-bench Multilingual (Agentic Coding, single attempt)huggingface.co | 47.3% | huggingface.co | Jul 11, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA-Diamondhuggingface.co | 75.1% | huggingface.co | Jul 11, 2025 |
| SimpleBenchSimpleBench | 26.3% | SimpleBench | Oct 5, 2026 |
| Humanity's Last Exam (Text Only)huggingface.co | 4.7% | huggingface.co | Jul 11, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| AIME 2025huggingface.co | 49.5% | huggingface.co | Jul 11, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MMLU-Reduxhuggingface.co | 92.7% | huggingface.co | Jul 11, 2025 |
| IFEval (Prompt Strict)huggingface.co | 89.8% | huggingface.co | Jul 11, 2025 |
| MMLU-Prohuggingface.co | 81.1% | huggingface.co | Jul 11, 2025 |
| SimpleQAhuggingface.co | 31% | huggingface.co | Jul 11, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena EloLMArena | 1418 Elo · #104 of 191 | LMArena | Oct 8, 2026 |
How Kimi compares: Claude vs Kimi, DeepSeek vs Kimi, Gemini vs Kimi
Compare Kimi K2: Kimi K2 vs Kimi K2.5, Kimi K2 vs Kimi K3.1 Pro, Kimi K2 vs Kimi K3, Kimi K2 vs Kimi K2.6, Kimi K2 vs Kimi K2.7 Code
Apps
Use Kimi K2 in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Kimi K2 FAQ
Short answers, built from the data on this page.
Kimi K2 is a model from Moonshot, released on Jul 11, 2025. Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in Kimi K2, it activates 32 billion parameters per forward pass and supports 256 k-token context windows. The model is optimized for persistent step-by-step thought, dynamic tool invocation, and complex reasoning workflows that span hundreds of turns. It interleaves step-by-step reasoning with tool use, enabling autonomous research, coding, and writing that can persist for hundreds of sequential actions without drift. It sets new open-source benchmarks on HLE, BrowseComp, SWE-Multilingual, and LiveCodeBench, while maintaining stable multi-agent behavior through 200–300 tool calls. Built on a large-scale MoE architecture with MuonClip optimization, it combines strong reasoning depth with high inference efficiency for demanding agentic and analytical tasks.
On the Respan gateway, Kimi K2 costs from $0.57 per 1M input tokens and $2.30 per 1M output tokens on Novita and OpenRouter, after gateway discounts. Averaged across its 3 providers, it costs $0.58 per 1M input tokens and $2.37 per 1M output tokens.
Kimi K2 is available through 3 providers: Novita, Featherless, and OpenRouter.
Kimi K2 accepts up to 131K tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "kimi-k2". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Kimi K2 scores 17.6 out of 100 on the Respan Index v1.1, ranking #146 of 176 models. By category: Coding 5.0, Agents 12.5 (estimated), Reasoning 19.0, Knowledge & language 13.2, and Human preference 47.7. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
Kimi K2 has 19 published benchmark scores, including Aider-Polyglot 60%, Tau2 retail 70.6%, and GPQA-Diamond 75.1%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.