MoonshotAIReasoningReleased 6 November 2025
Kimi K2 Thinking pricing, context and benchmark
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning.
262K
Input context
98K
Output context
$0.6
Official input
$2.5
Official output
n/a
AA index
01 · Model Overview
Everything that matters, in one table
Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.
| Model | Kimi K2 Thinking |
| Model ID | moonshotai/kimi-k2-thinking |
| Provider | MoonshotAI |
| Release date | 6 November 2025 |
| Status | Generally available |
| Input context | 262,144 tokens |
| Output context | 98,304 tokens |
| Official input pricing | $0.6 per 1M tokens |
| Official output pricing | $2.5 per 1M tokens |
| Cache read pricing | $0.15 per 1M tokens |
| Market input pricing | $0.6 per 1M (cheapest route) |
| Market output pricing | $2.5 per 1M (cheapest route) |
| Reasoning tokens | Billed as output at $2.5 per 1M |
| Input modalities | text |
| Output modalities | text |
| Reasoning control | Yes, effort levels exposed |
| Tool support | Functions, tool choice, structured outputs |
| Tokenizer | Other |
| Provider routes | 1 endpoint |
| Artificial Analysis index | Not published |
| Speed | Not published |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | ✓ yes | $0.6 in |
| Image | no | no | not supported |
| Audio | no | no | not supported |
| Video | no | no | not supported |
| File (PDF) | no | no | not supported |
02 · Overview
What is Kimi K2 Thinking?
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 Thinking carries a 262K token window, uses the Other tokenizer and is served by MoonshotAI. On Hoodgen it sits in the Reasoning tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.
03 · Release
Release and what changed from the previous version
Released6 November 2025
| Property | Kimi K2 0905 | Kimi K2 Thinking | Change |
|---|---|---|---|
| Released | 2025 | 2025 | Same release window |
| Context | 262K | 262K | Unchanged |
| Max output | 98K | 98K | Unchanged |
| Input price | $0.6 | $0.6 | Unchanged |
| Output price | $2.5 | $2.5 | Unchanged |
| Input modalities | text | text | Unchanged |
| AA index | n/a | n/a | Newer benchmark run |
04 · Capabilities
Features and capabilities
◈
Thinking control
Reasoning effort can be dialled per request, so one model covers deep analysis and fast chat.
⚙
Function calling
Tools, tool choice and parallel calls, which is what agent loops need to act on results.
{ }
Structured outputs
Schema constrained JSON with response_format, so no parse and retry loop in your code.
⚡
Prompt caching
Cached input costs $0.15 per million instead of $0.6, so stable prefixes get cheaper.
⌁
Seeds
A seed can be pinned so the same prompt is reproducible across test runs.
05 · Reasoning
Thinking and reasoning capabilities
Kimi K2 Thinking can think before answering and exposes the effort level per request. Reasoning tokens bill as output at $2.5 per million, and the trace can be returned with include_reasoning.
| Level | First token | Cost per task | Best for |
|---|---|---|---|
| Measured | n/a | n/a | Artificial Analysis measures the default reasoning configuration |
| Low effort | Faster | Lower | Chat, autocomplete, classification |
| High effort | Slower | Higher | Debugging, planning, multi step agents |
07 · Use cases
What can you do with Kimi K2 Thinking?
Debugging and root cause
Multi file failures where the model has to hold a causal chain before answering.
Architecture and planning
Design docs, migration plans and trade off analysis over long context.
Data analysis
Spreadsheets and logs read in one pass, then summarised with the numbers quoted back.
Agentic coding
Repo wide changes that need plan, edit and verify loops.
08 · Cost levers
Prompt caching and how to cut the bill
Cached input bills at $0.15 per million instead of $0.6. Keep the system prompt and documents first and the changing question last, so every call hits the cache.
09 · Pricing
Kimi K2 Thinking pricing
Official pricing
List price
$0.6 / 1M in
$2.5 / 1M out
- $0.15 cached input
- 262K context
- text input
Cheapest route
$0.6 / 1M in
$2.5 / 1M out
- 1 route on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| Novita | standard | $0.6 | $2.5 | $0.15 | 100.0% |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0103 | $5.17 | 4917 |
| List price | $0.0103 | $5.17 | 4917 |
10 · Developers
API and developer information
| Model ID | moonshotai/kimi-k2-thinking |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | frequency_penalty · include_reasoning · max_tokens · presence_penalty · reasoning · repetition_penalty · response_format · seed · stop · structured_outputs · temperature · tool_choice · tools · top_k · top_p |
| Streaming | Yes, server sent events |
| Modality string | text->text |
| Max prompt tokens | 262,144 |
| Max completion tokens | 98,304 |
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "moonshotai/kimi-k2-thinking",
"messages": [{ "role": "user", "content": "Summarise this document." }],
"max_tokens": 1024
}'11 · Limitations
Model limitations
| Text only output | It cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals. |
| Output cap | 98,304 tokens per request. Long deliverables have to be chunked. |
| Benchmarks not published | Artificial Analysis does not publish an Intelligence Index for this release, so no benchmark score is claimed here. |
| Knowledge cutoff | The provider does not state a fixed cutoff for every release. Verify very recent events against search. |
12 · Comparison
Kimi K2 Thinking vs other MoonshotAI models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| Kimi K2 Thinking | 262K | $0.6 | $2.5 | n/a | 2025 |
| Kimi K2 0905 | 262K | $0.6 | $2.5 | n/a | 2025 |
| Kimi K2.6 | 262K | $0.39 | $1.8 | n/a | 2026 |
| Kimi K3.1 Pro | 1.05M | $0.237 | $8.411 | 46 | Oct 2026 |
13 · Privacy
Privacy and data policy
- On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
- Requests route through OpenRouter to MoonshotAI and are covered by that provider's API terms.
- Do not paste secrets or personal data you would not send to any hosted model.
14 · FAQ
Kimi K2 Thinking questions, answered
Kimi K2 Thinking is a reasoning model from MoonshotAI, released 6 November 2025. Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning.
✦
Start chatting with Kimi K2 Thinking
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.