Price per 1M logo

Kimi K2p5 API pricing

Fireworks AI · chat model · 262K context · ranked #968 of 1809 by input price

prices checked 2026-09-13 13:40 UTC
Input / 1M tokens
$0.6
Output / 1M tokens
$3
Cached input / 1M
$0.1
Max output
33K

What Kimi K2p5 costs in practice

Kimi K2p5 is priced at $0.6 per million input tokens and $3 per million output tokens , with cached input billed at $0.1 per million — roughly 83% cheaper than fresh input, which matters if your app resends a large system prompt. Against the median priced chat model ($0.5/1M in), this sits at 1.2×.

Monthly cost examples

Assuming 1,200 prompt + 400 completion tokens per request unless noted, billed 30 days a month and without cache hits.

WorkloadCost / monthCost / day
1,000 requests/day$57.6$1.92
10,000 requests/day$576$19.2
100,000 requests/day$5760$192
1M summaries/month$5699.94$190

Model a different profile in the cost calculator.

Capabilities

tools

Cheaper alternatives

Ranked by blended cost (3× input + 1× output) — cheaper, but check context and capabilities before switching.

#ModelProviderInput $/1MOutput $/1MCached $/1MContext
1Gemini Exp 1114Google Geminifreefree1.0M
2Gemini Exp 1206Google Geminifreefree2.1M
3Gemma 3 27b ItGoogle Geminifreefree131K
4Gemma 4 26b A4b ItGoogle Geminifreefree262K
5Gemma 4 31b ItGoogle Geminifreefree262K
6Learnlm 1.5 Pro ExperimentalGoogle Geminifreefree33K

Data provenance

This page is assembled from the sources below. Where two sources disagree, both are shown.

Primary sources
Cross-check

Only one source publishes this model; no independent cross-check available yet.

More from Fireworks AI

Frequently asked

How much does Kimi K2p5 cost per 1,000 tokens?

About $0.0006 for input and $0.003 for output tokens, based on the per-million rates on this page.

Is Kimi K2p5 cheaper than other models?

By input price it ranks #968 of 1809 priced chat models in this index, putting it in the more expensive half of the market.

How often is Kimi K2p5's price checked?

The dataset was last refreshed 2026-09-13 13:40 UTC. Providers can change pricing at any time — verify with Fireworks AI before committing to a budget.