AI Rate CardKimi K2 0711 vs Kimi K2.5: API price and specs
Kimi K2 0711 is 11% cheaper than Kimi K2.5 on input price.
Kimi K2.5 is 44% cheaper than Kimi K2 0711 on output price.
Kimi K2.5 is 17% cheaper than Kimi K2 0711 on a 1M-in / 200k-out workload.
| Field | Kimi K2 0711 | Kimi K2.5 |
|---|---|---|
| Lowest input, per 1M | $0.40 | $0.45 +12.5% |
| Median input, per 1M | $0.57 | $0.60 +5.3% |
| Lowest output, per 1M | $2.16 +80% | $1.20 |
| Median output, per 1M | $2.30 | $3.00 +30.4% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.83 +20.6% | $0.69 |
| Context | 262K | 262K |
| Max output | 262K | 262K |
| Providers | 10 +73.7% | 38 |
| Regions | — | EU, GLOBAL, US |
| Accepts | text | image, image/bmp, image/gif, image/heic, image/heif, image/jpeg, image/png, image/webp, text, video, video/3gpp, video/avi, video/mov, video/mp4, video/mpeg, video/mpg, video/webm, video/wmv, video/x-flv |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | opencode | deepinfra |
Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.
Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.
Providers selling both
aihubmix, aiml, fastrouter, helicone, kilo, opencode, openrouter, qiniu-ai, requesty, vercel
Frequently asked questions
Which is cheaper, Kimi K2 0711 or Kimi K2.5?
Kimi K2 0711 is 11% cheaper than Kimi K2.5 on input price. Kimi K2.5 is 44% cheaper than Kimi K2 0711 on output price. Kimi K2.5 is 17% cheaper than Kimi K2 0711 on a 1M-in / 200k-out workload.
Which has the larger context, Kimi K2 0711 or Kimi K2.5?
Kimi K2 0711: 262K tokens; Kimi K2.5: 262K tokens.
Where can I use both Kimi K2 0711 and Kimi K2.5?
aihubmix, aiml, fastrouter, helicone, kilo, opencode, openrouter, qiniu-ai, requesty, vercel