AI Rate CardKimi K2.7 Code vs Kimi K3: API price and specs
Kimi K3 is 20% cheaper than Kimi K2.7 Code on input price.
Kimi K3 is 38% cheaper than Kimi K2.7 Code on output price.
Kimi K3 is 29% cheaper than Kimi K2.7 Code on a 1M-in / 200k-out workload.
Kimi K3 has a 300% larger context than Kimi K2.7 Code.
| Field | Kimi K2.7 Code | Kimi K3 |
|---|---|---|
| Lowest input, per 1M | $0.55 +25.3% | $0.44 |
| Median input, per 1M | $0.95 | $3.00 +215.8% |
| Lowest output, per 1M | $2.60 +61.2% | $1.61 |
| Median output, per 1M | $4.00 | $15.00 +275% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $1.07 +40.5% | $0.76 |
| Context | 262K +75% | 1M |
| Max output | 262K +75% | 1M |
| Providers | 46 +23.3% | 60 |
| Regions | APAC, EU, GLOBAL, US | APAC, EU, GLOBAL, US |
| Accepts | application/pdf, file, image, image/bmp, image/gif, image/heic, image/heif, image/jpeg, image/png, image/webp, pdf, text, video, video/3gpp, video/avi, video/mov, video/mp4, video/mpeg, video/mpg, video/webm, video/wmv, video/x-flv | application/pdf, file, image, image/bmp, image/gif, image/heic, image/heif, image/jpeg, image/png, image/webp, pdf, 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 | yes |
| Cheapest provider | kenari | aihubmix |
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
302ai, abacus, aiand, aihubmix, aiml, baseten, cometapi, cortecs, deepinfra, edenai, empiriolabs, fastrouter, github-copilot, huggingface, hyper, impossibl, io-net, iteracompute, jiekou, kenari, kilo, meganova, melious, moark, nebius, novita, ofox, ollama, ollama-cloud, opencode, opencode-go, openrouter, orcarouter, perplexity-agent, poe, requesty, siliconflow, synthetic, tensorx, trustedrouter, vercel, zenmux
Frequently asked questions
Which is cheaper, Kimi K2.7 Code or Kimi K3?
Kimi K3 is 20% cheaper than Kimi K2.7 Code on input price. Kimi K3 is 38% cheaper than Kimi K2.7 Code on output price. Kimi K3 is 29% cheaper than Kimi K2.7 Code on a 1M-in / 200k-out workload.
Which has the larger context, Kimi K2.7 Code or Kimi K3?
Kimi K2.7 Code: 262K tokens; Kimi K3: 1M tokens.
Where can I use both Kimi K2.7 Code and Kimi K3?
302ai, abacus, aiand, aihubmix, aiml, baseten, cometapi, cortecs, deepinfra, edenai, empiriolabs, fastrouter, github-copilot, huggingface, hyper, impossibl, io-net, iteracompute, jiekou, kenari, kilo, meganova, melious, moark, nebius, novita, ofox, ollama, ollama-cloud, opencode, opencode-go, openrouter, orcarouter, perplexity-agent, poe, requesty, siliconflow, synthetic, tensorx, trustedrouter, vercel, zenmux