MoonshotAIMultimodalReleased 20 April 2026
Kimi K2.6 pricing, context and benchmark
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.
262K
Input context
236K
Output context
$0.39
Official input
$1.8
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 K2.6 |
| Model ID | moonshotai/kimi-k2.6 |
| Provider | MoonshotAI |
| Release date | 20 April 2026 |
| Status | Generally available |
| Input context | 262,144 tokens |
| Output context | 235,929 tokens |
| Official input pricing | $0.39 per 1M tokens |
| Official output pricing | $1.8 per 1M tokens |
| Cache read pricing | $0.162 per 1M tokens (83% off input) |
| Market input pricing | $0.39 per 1M (cheapest route) |
| Market output pricing | $1.8 per 1M (cheapest route) |
| Highest route pricing | $0.7 in, $3.5 out per 1M |
| Input modalities | text · image |
| Output modalities | text |
| Reasoning control | Not exposed |
| Tool support | Text generation only |
| Tokenizer | Other |
| Provider routes | 8 endpoints |
| Artificial Analysis index | Not published |
| Speed | 36 tokens/s, 76.93s to first token |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | ✓ yes | $0.39 in |
| Image | ✓ yes | no | $0.39 in |
| Audio | no | no | not supported |
| Video | no | no | not supported |
| File (PDF) | no | no | not supported |
02 · Overview
What is Kimi K2.6?
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...
Kimi K2.6 carries a 262K token window, uses the Other tokenizer and is served by MoonshotAI. On Hoodgen it sits in the Multimodal 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
Released20 April 2026
| Property | Kimi K2 Thinking | Kimi K2.6 | Change |
|---|---|---|---|
| Released | 2025 | 2026 | Newer release |
| Context | 262K | 262K | Unchanged |
| Max output | 98K | 236K | Changed |
| Input price | $0.6 | $0.39 | Cheaper |
| Output price | $2.5 | $1.8 | Cheaper |
| Input modalities | text | text, image | Unchanged |
| AA index | n/a | n/a | Newer benchmark run |
04 · Capabilities
Features and capabilities
◉
Vision
Screenshots, charts and photographed documents are read at the text token rate.
⚡
Prompt caching
Cached input costs $0.162 per million instead of $0.39, so stable prefixes get cheaper.
07 · Use cases
What can you do with Kimi K2.6?
Document understanding
Screenshots, charts, scanned pages and PDFs read in the prompt.
Mixed media briefs
One thread holding text, images and files together.
Extraction
Schema constrained JSON out of messy inputs.
Research synthesis
Several sources condensed with the figures preserved.
08 · Cost levers
Prompt caching and how to cut the bill
Cached input bills at $0.162 per million instead of $0.39, a 83% discount. Keep the system prompt and documents first and the changing question last, so every call hits the cache.
09 · Pricing
Kimi K2.6 pricing
Official pricing
List price
$0.39 / 1M in
$1.8 / 1M out
- $0.162 cached input
- 262K context
- text, image input
Cheapest route
$0.39 / 1M in
$1.8 / 1M out
- 8 routes on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Highest route
$0.7 / 1M in
$3.5 / 1M out
- Priority or premium tier
- Best under load
- Use for latency critical calls
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| Chutes | standard | $0.39 | $1.8 | $0.039 | 100.0% |
| DigitalOcean | standard | $0.57 | $2.4 | $0.114 | 100.0% |
| StreamLake | standard | $0.598 | $2.52 | $0.101 | 100.0% |
| CoreWeave | standard | $0.65 | $3.41 | $0.15 | 100.0% |
| Crusoe | standard | $0.7 | $3.5 | $0.35 | 99.4% |
| DeepInfra | standard | $0.75 | $3.5 | $0.15 | 94.1% |
| Venice | standard | $0.75 | $3.5 | $0.16 | 96.8% |
| Parasail | standard | $0.75 | $3.5 | $0.16 | 99.7% |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0063 | $3.14 | 2987 |
| List price | $0.0078 | $3.88 | 3686 |
| Highest route | $0.0192 | $9.63 | 9144 |
10 · Developers
API and developer information
| Model ID | moonshotai/kimi-k2.6 |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | prompt and max_tokens |
| Streaming | Yes, server sent events |
| Modality string | text+image->text |
| Max prompt tokens | 262,144 |
| Max completion tokens | 235,929 |
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "moonshotai/kimi-k2.6",
"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 | 235,929 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 K2.6 vs other MoonshotAI models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| Kimi K2.6 | 262K | $0.39 | $1.8 | n/a | 2026 |
| Kimi K2 0905 | 262K | $0.6 | $2.5 | n/a | 2025 |
| Kimi K2 Thinking | 262K | $0.6 | $2.5 | n/a | 2025 |
| 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 K2.6 questions, answered
Kimi K2.6 is a multimodal model from MoonshotAI, released 20 April 2026. 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.
✦
Start chatting with Kimi K2.6
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.