Kimi K3.1 Pro is available on AIHubMix under the model ID kimi-k3.1-pro. The model page lists both a regular rate and a limited promotional rate: during the offer, input is $1.80 / 1M tokens and output is $9.00 / 1M tokens, which is 10% off the regular $2.00 / $10.00 rates. The promotional prices are marked valid through 2026-11-23.
The context window is 1,048,576 tokens (about 1M), aimed at coding and agent workflows that need a long working set. This post is a pricing and usage note, not an independent performance review. Final billing follows the AIHubMix model page.
AIHubMix also announced the offer on X.
At a glance
| Item | Value |
|---|---|
| Model | Kimi K3.1 Pro |
| Model ID | kimi-k3.1-pro |
| Platform | AIHubMix |
| Currency | USD |
| Regular (in / out) | $2.00 / $10.00 per 1M tokens |
| Promo (in / out) | $1.80 / $9.00 per 1M tokens |
| Discount | About 10% off regular |
| Promo valid through | 2026-11-23 |
| Cache read (regular / promo) | $0.20 / $0.18 per 1M tokens |
| Context window | 1,048,576 tokens |
| Positioning | Coding and agents |
The cost estimates below use only the input and output unit prices. They leave out cache hits, minimum billable units, and rounding.
Regular vs promotional prices
Both the regular and promotional rates come from the AIHubMix model page. The regular rates are not reverse-engineered from the 10% discount.
| Meter | Regular | Promo | Difference per 1M tokens |
|---|---|---|---|
| Input | $2.00 | $1.80 | $0.20 |
| Output | $10.00 | $9.00 | $1.00 |
| Cache read | $0.20 | $0.18 | $0.02 |
Estimate with:
Regular cost = input_tokens / 1,000,000 × $2.00
+ output_tokens / 1,000,000 × $10.00
Promo cost = input_tokens / 1,000,000 × $1.80
+ output_tokens / 1,000,000 × $9.00
Savings = regular cost − promo cost
Worked examples at round sizes:
| Assumed usage | Regular | Promo | Savings |
|---|---|---|---|
| 100K in + 100K out | $1.20 | $1.08 | $0.12 |
| 1M in + 100K out | $3.00 | $2.70 | $0.30 |
| 1M in + 1M out | $12.00 | $10.80 | $1.20 |
Example: a cross-file code change
Suppose one cross-file edit packs related source files, interface notes, failing test output, and key error logs into the context — 500K input tokens — and the model returns a patch plan, change notes, and follow-up tests — 50K output tokens. This is a worked billing example, not a measured run.
At the regular rate:
0.5 × $2.00 + 0.05 × $10.00 = $1.00 + $0.50 = $1.50
At the promotional rate:
0.5 × $1.80 + 0.05 × $9.00 = $0.90 + $0.45 = $1.35
So for that assumed load:
- Regular estimate: $1.50
- Promo estimate: $1.35
- Difference: $0.15
Real tasks vary with code span, log length, turn count, and how context is managed. Re-estimate on your own workload before you commit. Heavy cache hits need a separate pass at the cache-read rate.
Calling it and using the context
On AIHubMix you can call it through OpenAI-compatible Chat Completions:
curl -s https://aihubmix.com/v1/chat/completions \
-H "Authorization: Bearer $AIHUBMIX_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"kimi-k3.1-pro","messages":[{"role":"user","content":"Hello"}]}'
A roughly 1M-token window is useful when you evaluate large-repo understanding, cross-file refactors, long-log triage, or agent flows that keep multi-step tool results in context. It is a capacity figure, not a free allowance, a monthly quota, or a performance guarantee.
FAQ
Is Kimi K3.1 Pro available on AIHubMix now?
Yes. The model page and AIHubMix announcement both show it live under kimi-k3.1-pro. Account access and quotas follow the console.
Which price should you budget with?
During the offer, budget $1.80 / 1M tokens for input and $9.00 / 1M tokens for output. The regular rates are $2.00 and $10.00. The offer is marked through 2026-11-23; after that, use the model page.
Are $2.00 / $10.00 reverse-engineered from 10% off?
No. They are the regular rates on the AIHubMix model page. The promotional $1.80 / $9.00 rates are listed there as well, so the two can be compared directly.
Is the 1M-token context a free allowance?
No. It is a context-window size. It does not imply free quota, a monthly allotment, or a final bill.
When does the offer end, and where is it listed?
The promotional prices are marked valid through 2026-11-23. Cross-check the AIHubMix model page and the X announcement. If the page changes later, follow the page.
Do these estimates include cache reads?
No. The worked examples use only input and output unit prices. Cache reads are listed separately at $0.20 regular and $0.18 promotional per 1M tokens.
Wrap-up
Kimi K3.1 Pro is live on AIHubMix. During the offer, input is $1.80 and output is $9.00 per 1M tokens — about 10% off the regular $2.00 / $10.00 — through 2026-11-23. For coding tasks such as a cross-file edit, estimate from your own input and output usage, then confirm the current rates and terms on the model page.
