If you want to run Kimi-2.5 with kimi-cli through

Venice.ai (who have deployed the model really fast), you need this small change:

https://github.com/MoonshotAI/kimi-cli/pull/782

Then it works flawlessly.

So far I'm quite happy about it and it's much cheaper than the frontier models, but I don't think it's much worse.

Here's my model grading:

nostr:nevent1qgsd4dkxqewy8xum47ctpu0ltgxxsfemeewpjkdyzk9ddfcg286s0dspzamhxue69uhhyetvv9ujuurjd9kkzmpwdejhgtcqyrl55cyypkpufzq6rharze44sny597d6w7u8jml25vgartlucwreg47mtkd

Reply to this note

Please Login to reply.

Discussion

Hey Nostriches.

Build something cool. Here's an API key:

VENICE-INFERENCE-KEY-O7Rcb8toRQ3F468aQWxIt4j-9zp64hfmiDz7m16UjY

(Not stolen, it is mine, will work until someone consumes the credits - credit limit resets every day at midnight and until the end of February ).

I recommend using Kimi 2.5 or cheaper models, you will burn the tokens very fast with Opus 4.5 or so. Pricing here (so you know how much you're burning):

https://docs.venice.ai/overview/pricing

Rules:

- not many, be mindful of others and me, don't do anything crazy and unethical

- The credits are not unlimited, if you can afford them or have a subscription, use that, this is to enable people who can't afford a subscription to use premier models (Opus, GPT-5.2, Kimi 2.5, ...)

Recommendation: Create something cool. Nostr / Bitcoin / Freedom expanding code. Pull requests. Open source software. Art. Whatever. Bless us with your creations 😃

Posting what you created as a reply is appreciated, as are zaps. Have fun!

Howtos:

Kimi-cli: nevent1qgsd4dkxqewy8xum47ctpu0ltgxxsfemeewpjkdyzk9ddfcg286s0dspzamhxue69uhhyetvv9ujuurjd9kkzmpwdejhgtcqyptxyrlv4ue9tv46pz4njy2v4zg5vy4yk9p37977lq7ngmsjyd8ux433kwp

Claude Code: https://docs.venice.ai/overview/guides/claude-code