Kimi K2 Thinking
moonshotai/kimi-k2-thinkingKimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning.
Standard pricing
Run this model at its standard rate. Cheap mode currently has no separate discount.
API routing ceilings, including your 5% Free-plan fee. Included usage applies first, then prepaid credits. Cached tokens and tools can have separate charges.
Other models with discounted rates
See all discounts →These are different models. Cheap mode may be slower; discounts compare each model’s own standard rate.
Choose how to use Kimi K2 Thinking
Playground
Try prompts in your browser, create an agent, and see the cost of each reply. Your selected model carries into setup.
Model capabilities below describe the underlying model. Available playground features depend on its provider.
API
Connect your app with a Gizmo API key. Choose fastest or cheapest, stream text responses, and inspect timing, tokens, and charges in request logs.
A current API route is listed for this exact model. Gateway configuration is required for live calls.
Provider price + a transparent platform fee
| Rate | Provider baseline | Free plan · 5% fee | Paid plan · 4% fee |
|---|---|---|---|
| Input / 1M tokens | $0.6 | $0.63 | $0.624 |
| Output / 1M tokens | $2.5 | $2.625 | $2.6 |
| API input / 1M tokens | $0.6 | $0.63 | $0.624 |
| API output / 1M tokens | $2.5 | $2.625 | $2.6 |
Legacy chat image rates use the catalog baseline. The dedicated image playground shows separate estimates and settles the provider’s metered usage. API rates are current routing ceilings; final API charges use provider-reported cost plus your fee. Cheapest routing compares eligible OpenRouter and Cheaper Inference rates for the same model; savings are not guaranteed. Cached input or other provider charges may differ. Compare all model rates and verified discounts →
How your plan pays for usage
API and playground share one included allowance. Usage including the fee draws from that allowance first, then your prepaid credits. Plans bill monthly; included usage resets weekly: Free $1, Starter $5, Growth $25, Scale $50.
A $1 provider charge becomes $1.05 on Free or $1.04 on a paid plan before included usage is applied. Plan eligibility still applies in the playground.
Free models and limits
Zero-cost models stay $0, including the fee, and do not consume your dollar allowance. Free accounts can make 1,000 free-model API requests per calendar month, resetting in UTC. Admitted requests count even if the provider fails.
Free includes 20 API requests/minute and 6 playground messages/minute. Paid plans raise these limits. See plan limits.
Before a text API request, Gizmo temporarily reserves included usage and, if necessary, prepaid credit for the model’s full context plus your maximum output. Image jobs reserve twice their displayed estimate. Unused funds return after metering. This hold can exceed the final charge; unconfirmed usage remains marked pending.
Overview
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.
Benchmarks
Artificial Analysis indices independent, 0–100
Design Arena head-to-head, human-voted
| Category | Elo | Win rate | Rank |
|---|---|---|---|
| Websites | 1126 | 48.8% | #89 |
3. Evaluation Results from the model card
| Benchmark | Setting | K2 Thinking | GPT-5 (High) | Claude Sonnet 4.5 (Thinking) | K2 0905 | DeepSeek-V3.2 | Grok-4 |
|---|---|---|---|---|---|---|---|
| HLE (Text-only) | no tools | 23.9 | 26.3 | 19.8* | 7.9 | 19.8 | 25.4 |
| w/ tools | 44.9 | 41.7* | 32.0* | 21.7 | 20.3* | 41.0 | |
| heavy | 51.0 | 42.0 | - | - | - | 50.7 | |
| AIME25 | no tools | 94.5 | 94.6 | 87.0 | 51.0 | 89.3 | 91.7 |
| w/ python | 99.1 | 99.6 | 100.0 | 75.2 | 58.1* | 98.8 | |
| heavy | 100.0 | 100.0 | - | - | - | 100.0 | |
| HMMT25 | no tools | 89.4 | 93.3 | 74.6* | 38.8 | 83.6 | 90.0 |
| w/ python | 95.1 | 96.7 | 88.8* | 70.4 | 49.5* | 93.9 | |
| heavy | 97.5 | 100.0 | - | - | - | 96.7 | |
| IMO-AnswerBench | no tools | 78.6 | 76.0* | 65.9* | 45.8 | 76.0* | 73.1 |
| GPQA | no tools | 84.5 | 85.7 | 83.4 | 74.2 | 79.9 | 87.5 |
3. Evaluation Results from the model card
| Benchmark | Setting | K2 Thinking | GPT-5 (High) | Claude Sonnet 4.5 (Thinking) | K2 0905 | DeepSeek-V3.2 |
|---|---|---|---|---|---|---|
| MMLU-Pro | no tools | 84.6 | 87.1 | 87.5 | 81.9 | 85.0 |
| MMLU-Redux | no tools | 94.4 | 95.3 | 95.6 | 92.7 | 93.7 |
| Longform Writing | no tools | 73.8 | 71.4 | 79.8 | 62.8 | 72.5 |
| HealthBench | no tools | 58.0 | 67.2 | 44.2 | 43.8 | 46.9 |
3. Evaluation Results from the model card
| Benchmark | Setting | K2 Thinking | GPT-5 (High) | Claude Sonnet 4.5 (Thinking) | K2 0905 | DeepSeek-V3.2 |
|---|---|---|---|---|---|---|
| BrowseComp | w/ tools | 60.2 | 54.9 | 24.1 | 7.4 | 40.1 |
| BrowseComp-ZH | w/ tools | 62.3 | 63.0* | 42.4* | 22.2 | 47.9 |
| Seal-0 | w/ tools | 56.3 | 51.4* | 53.4* | 25.2 | 38.5* |
| FinSearchComp-T3 | w/ tools | 47.4 | 48.5* | 44.0* | 10.4 | 27.0* |
| Frames | w/ tools | 87.0 | 86.0* | 85.0* | 58.1 | 80.2* |
3. Evaluation Results from the model card
| Benchmark | Setting | K2 Thinking | GPT-5 (High) | Claude Sonnet 4.5 (Thinking) | K2 0905 | DeepSeek-V3.2 |
|---|---|---|---|---|---|---|
| SWE-bench Verified | w/ tools | 71.3 | 74.9 | 77.2 | 69.2 | 67.8 |
| SWE-bench Multilingual | w/ tools | 61.1 | 55.3* | 68.0 | 55.9 | 57.9 |
| Multi-SWE-bench | w/ tools | 41.9 | 39.3* | 44.3 | 33.5 | 30.6 |
| SciCode | no tools | 44.8 | 42.9 | 44.7 | 30.7 | 37.7 |
| LiveCodeBenchV6 | no tools | 83.1 | 87.0* | 64.0* | 56.1* | 74.1 |
| OJ-Bench (cpp) | no tools | 48.7 | 56.2* | 30.4* | 25.5* | 38.2* |
| Terminal-Bench | w/ simulated tools (JSON) | 47.1 | 43.8 | 51.0 | 44.5 | 37.7 |
Capabilities
Reasoning is always on.
Sampling controls: temperature, top_p, top_k, max_tokens, frequency_penalty, presence_penalty, repetition_penalty. Defaults: top_k null, top_p null, temperature null, presence_penalty null, frequency_penalty null, repetition_penalty null.
Pricing on Gizmo
These are provider baseline rates before Gizmo’s 5% Free-plan or 4% paid-plan fee. Your included usage covers charges first; overage uses prepaid credits. See the fee-inclusive comparison above.
Provider baseline rates
- Input
- $0.6 / 1M
- Output
- $2.50 / 1M
Examples before the platform fee
- Typical chat turn
- $0.0024 2k in · 500 out
- $1 of input
- ≈ 1.67M tokens
- $1 of output
- ≈ 400k tokens
- Full context, once
- $0.16
Providers and pricing
One way to run Kimi K2 Thinking on Gizmo.
| Provider | Route | Input / 1M | Output / 1M | Context | Uptime 24h |
|---|---|---|---|---|---|
| Novita · bf16Lowest price | OpenRouter | $0.60 | $2.50 | 262k | 100% |
Rates are each provider’s, per million tokens, before Gizmo’s 5% (Free) or 4% (paid) fee. “Cheapest” routing starts at the top of this list; “Fastest” starts with the model’s maker.
More from Moonshot AI
Kimi K3.1 ProMoonshot AI · 1.05M ctx$2 · $10Kimi K3Moonshot AI · 1.05M ctx$0.192 · $16Kimi K3 (batch)Moonshot AI · 1.05M ctx$0.917 · $6Kimi K2.7 CodeMoonshot AI · 262k ctx$0.6 · $3.50Kimi K2.6Moonshot AI · 262k ctx$0.65 · $3.41Kimi K2.5Moonshot AI · 262k ctx$0.532 · $3.32Kimi K2 0905Moonshot AI · 262k ctx$0.6 · $2.50Kimi K2 0711Moonshot AI · 131k ctx$0.57 · $2.30Similar price, other creators
Run Kimi K2 Thinking in under a minute
Create your account
Sign up with just an email. Start on the free tier with no card, or pick a paid plan for a bigger weekly allowance and $25 in bonus credits.
Your agent is ready
Kimi K2 Thinking is preselected as the brain of your first agent. Give it a name and a system prompt, or keep the defaults.
Chat, research, create
Live web research and image generation are built in. Every reply shows what it cost, and you can switch models anytime.