Moonshot AI language model
Kimi K3.1 Pro
The first model of Moonshot AI's K3.1 series and its most capable Kimi to date: a 3T-class reasoning model with native vision and a 1M-token context. It costs a third less per token than Kimi K3; Moonshot says full weights ship by November 4, 2026.
01
Price
Input tokens
Output tokens
Cached input
Per 1M tokens. Octomind bills the listed provider price, with no markup, on every plan, including the free one (pay as you go from credits).
- Not included in any plan: every request bills from credits.
- Context caching is automatic: cache hits bill at $0.20 per 1M input tokens, a tenth of the input rate.
- Thinking is always on, at max effort by default, and reasoning tokens bill at the output rate.
02
What real work costs
| Workload | Cost |
|---|---|
| One chat reply 3,000 tokens in, 500 out | $0.01 |
| Summarise a 100-page report 50,000 tokens in, 1,500 out, one request | $0.12 |
| 1,000 classification calls 500 tokens in, 20 out, per call | $1.20 |
| Coding-agent session 2M tokens in across ~60 turns, 60,000 out, no cache | $4.60 |
| Same session, cached 85% of input read from the prompt cache, the rest written to it | $1.54 |
At the listed rate. Token counts are typical sizes, not measurements.
03
Specs
- Provider
- Moonshot AI
- Context window
- 1M tokens — ≈ 1,500 pages of prose or 100,000 lines of code
- Input
- Text, Images
- Output
- Text
- Structured output
- Yes — JSON schema
- Reasoning mode
- Yes
- Prompt caching
- Yes — cache hits at $0.2/M
- Weights
- Closed
- Released
- October 2026
- Status
- Live
- Model ID
kimi-k3.1-pro
Integration notes
- temperature, top_p, n, presence_penalty and frequency_penalty are fixed; omit them from requests.
- Thinking cannot be disabled; reasoning_effort accepts low, high or max and defaults to max.
- Images must be base64 or an uploaded file id: public image URLs are not supported.
04
Benchmarks
As published by the maker; not measured by Octomind.
| Benchmark | Score |
|---|---|
| Terminal-Bench 4.0source | 65.7% |
05
When to pick it
Pick it if
- you want Moonshot's current flagship at a lower rate than Kimi K3
- your prompts outgrow the 256K context of Kimi 2.6 and 2.7 Code
- you resend long prompts, so cache hits bill at a tenth of input
Skip it if
- you need temperature or top_p control: they are fixed
- Kimi 2.6 or 2.7 Code covers your workload at a lower rate
06
Where it sits on price
Blended price $4/M at 3 input tokens per output token: 32 live language models cost less, 7 cost more.
- Gemini 4 Argon $4/M
- GPT-6.1 Sol $4/M
- Kimi K3.1 Pro $4/M
- Gemini 3.1 Pro $4.5/M
- GPT 5.6 Terra $4.5/M
07
Use Kimi K3.1 Pro in Octomind
One OctoHub login reaches every model in the catalog. Pick this one per run, per session, or as your default.
octomind login
octomind run -m octohub:kimi-k3.1-pro/model octohub:kimi-k3.1-pro[model]
name = "octohub:kimi-k3.1-pro"08
Compare Kimi K3.1 Pro
09
Similar models
Nearest live models by listed input price.
- Claude Sonnet 5.5 $2/M input
- Gemini 3.1 Pro $2/M input
- Gemini 4 Argon $2/M input
- GPT 5.6 Terra $2/M input
10
Kimi K3.1 Pro FAQ
How much does Kimi K3.1 Pro cost?
Kimi K3.1 Pro lists at $2/M input, $10/M output, $0.2/M cached input per 1M tokens. A typical coding-agent session (2M tokens in, 60,000 out) comes to $4.60, or $1.54 when 85% of the input is read from the prompt cache. Octomind bills the listed provider price, with no markup, on every plan, including the free one (pay as you go from credits).
What is the context window of Kimi K3.1 Pro?
1M tokens, ≈ 1,500 pages of prose or 100,000 lines of code.
Does Kimi K3.1 Pro accept images?
Yes. It takes text and images as input and returns text.
Is Kimi K3.1 Pro open source?
No. Kimi K3.1 Pro is a closed-weights model, available only through Moonshot AI's API and hosted gateways such as OctoHub.
When was Kimi K3.1 Pro released?
October 2026, by Moonshot AI.
Is Kimi K3.1 Pro free?
No. Kimi K3.1 Pro bills per token at $2/M input, $10/M output, $0.2/M cached input per 1M. Octomind's free plan reaches it pay as you go from credits, so you pay only for the tokens you use, at the provider price. Credits carry a 3% top-up fee.
How do I use Kimi K3.1 Pro in Octomind?
Run octomind login once, then octomind run -m octohub:kimi-k3.1-pro. Inside a running session, /model octohub:kimi-k3.1-pro switches to it without losing context.
Use Kimi K3.1 Pro in Octomind
Choose a model when you start, then switch mid-session when the work changes.