openai
Kimi K3 vs GPT-6 Sol
79.2 overall · $4.00 / 1M
// moonshotai
Kimi K3
moonshotai/kimi-k3
reasoningtool callingimage inputvideo inputprompt caching
Kimi K3 costs $3.00 per 1M input tokens and $15.00 per 1M output tokens with a 1.0M-token context window.
A reasoning, tool-calling model from moonshotai, released Jul 16, 2026. On LiveBench it scores 79.2 overall — #11 of 55 benchmarked models — and ranks highest in reasoning (#6).
- Input / 1M
- $3.00
- Output / 1M
- $15.00
- Context
- 1.0M
- LiveBench overall
- 79.2 · #11
Specs and pricing
| Input price USD per 1M prompt tokens | $3.00 |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | $15.00 |
| Blended price 3:1 input:output — #28 most expensive of 343 listed models | $6.00 |
| Cached input read Blank means not priced separately — not free | $0.300 |
| Cache write | — |
| Context window | 1,048,576 tokens |
| Max output | 943,718 tokens |
| Input modalities | text, image, video |
| Tool calling | Yes |
| Extended reasoning | Yes |
| Knowledge cutoff | — |
| Listed | Jul 16, 2026 |
Also listed as moonshotai/kimi-k3:batch ($4.56 blended)— the same model at a different price or rate limit.
Benchmarks by category
LiveBench scores out of 100, with Kimi K3's rank among the 55 benchmarked models listed here. Run: kimi-k3.
Language#9 of 55
85.5
$0.0857 measured per point
What Kimi K3 costs to run
Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.
| Workload | Per month |
|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $1,726/mo |
| RAG assistant 8K in / 600 out × 100K requests | $2,220/mo |
| Coding agent 40K in / 4K out × 20K requests | $2,088/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $3,990/mo |
| Bulk classification 500 in / 20 out × 5M requests | $7,650/mo |
Compare Kimi K3 with
The benchmarked models closest to it on overall score.
Kimi K3 FAQ
How much does Kimi K3 cost?
Kimi K3 lists at $3.00 per 1M input tokens and $15.00 per 1M output tokens, with cached input reads at $0.300 per 1M. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $2,220 at list price.
What is the context window of Kimi K3?
Kimi K3 accepts up to 1,048,576 tokens of context and can return up to 943,718 output tokens per response.
Does Kimi K3 support tool calling?
Yes — Kimi K3 supports tool (function) calling and exposes extended reasoning. It accepts text, image, video input.
How does Kimi K3 score on benchmarks?
On LiveBench release 2026-06-25 (run: kimi-k3), Kimi K3 scores 79.2 overall, ranking #11 of 55 benchmarked models.
What is the API model ID for Kimi K3?
On OpenRouter the model ID is "moonshotai/kimi-k3". It was listed on Jul 16, 2026.
More from moonshotai
How these numbers are produced
- Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores and ranks — LiveBench release 2026-06-25. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.