AI Rate CardGemma 4 31B IT vs Kimi K3: API price and specs
Gemma 4 31B IT is 98% cheaper than Kimi K3 on input price.
Gemma 4 31B IT is 98% cheaper than Kimi K3 on output price.
Gemma 4 31B IT is 98% cheaper than Kimi K3 on a 1M-in / 200k-out workload.
Kimi K3 has a 300% larger context than Gemma 4 31B IT.
| Field | Gemma 4 31B IT | Kimi K3 |
|---|---|---|
| Lowest input, per 1M | $0.011 | $0.44 +3900% |
| Median input, per 1M | $0.14 | $3.00 +2042.9% |
| Lowest output, per 1M | $0.035 | $1.61 +4509.5% |
| Median output, per 1M | $0.40 | $15.00 +3650% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.018 | $0.76 +4137% |
| Context | 262K +75% | 1M |
| Max output | 262K +75% | 1M |
| Providers | 37 +38.3% | 60 |
| Regions | CH, EU, GLOBAL, US | APAC, EU, GLOBAL, US |
| Accepts | application/pdf, audio, file, image, image/gif, image/heic, image/heif, image/jpeg, image/png, image/webp, pdf, text, video, video/mp4, video/quicktime, video/webm | 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 | yes | yes |
| Cheapest provider | inferx | 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
abacus, aiand, aihubmix, aiml, amazon-bedrock, berget, chutes, cortecs, deepinfra, digitalocean, edenai, fastrouter, huggingface, impossibl, io-net, kenari, kilo, meganova, melious, neuralwatt, novita, ollama-cloud, openrouter, orcarouter, requesty, siliconflow, tinfoil, togetherai, trustedrouter, vercel, zenmux
Frequently asked questions
Which is cheaper, Gemma 4 31B IT or Kimi K3?
Gemma 4 31B IT is 98% cheaper than Kimi K3 on input price. Gemma 4 31B IT is 98% cheaper than Kimi K3 on output price. Gemma 4 31B IT is 98% cheaper than Kimi K3 on a 1M-in / 200k-out workload.
Which has the larger context, Gemma 4 31B IT or Kimi K3?
Gemma 4 31B IT: 262K tokens; Kimi K3: 1M tokens.
Where can I use both Gemma 4 31B IT and Kimi K3?
abacus, aiand, aihubmix, aiml, amazon-bedrock, berget, chutes, cortecs, deepinfra, digitalocean, edenai, fastrouter, huggingface, impossibl, io-net, kenari, kilo, meganova, melious, neuralwatt, novita, ollama-cloud, openrouter, orcarouter, requesty, siliconflow, tinfoil, togetherai, trustedrouter, vercel, zenmux