Pinned Tweet
llm.buzz is the open market for production inference.
Providers compete on price and speed to give you the best prices on the market.
Building with models: one API, every model, the cheapest healthy provider on each request.
Serving models: list your endpoint, set your price, keep 100%. Your own model too.
A coding agent that reads 2M tokens and writes 300k a day, on Claude Sonnet 5. At Anthropic's list: $7.00. On llm.buzz: $5.67. That is $1.62 in, $8.10 out per 1M, against $2.00 / $10.00 at list, 19% off as an Auto deal, as of 14:42 UTC.
12
Tencent's Hy4-Flash weights are up on Hugging Face: 220B total, 12B active, 1M context, open weights under the Tencent Hy licence. FP8 and base variants came with it, and llm.buzz lists it from today. If you serve it, list yours and set your own price.
23
Mistral Medium 3.5 on llm.buzz: $1.20 in, $5.98 out per 1M tokens.The cheapest other source we track: $1.50 / $7.50.20% under that, as of 14:42 UTC.
14
Inkling 2 Small weights are out. 594B total, 17B active, 1M context, text and image input.Apache 2.0, with day-one recipes for SGLang, vLLM, Unsloth and TokenSpeed.Serving it? List it on llm.buzz.
1
25
Claude Opus 4.8 is 20% off on llm.buzz today, an Auto deal.$4.00 in, $20.00 out per 1M tokens.Anthropic's own API: $5.00 / $25.00.The lowest price we track for it, as of 14:44 UTC.
17
1,000 support tickets on Claude Opus 5.5: $7.56 on llm.buzz, $9.00 at @AnthropicAI's list.
2M tokens in, 50k out.
16% off, an Auto deal.
Prices as of 14:20 UTC.
14
9 text models on llm.buzz have an EU provider live right now.
Put the EU tags in provider.only and the request goes only to those providers.
Failover stays inside that list.
GLM-5.3, Mistral Medium 3.5, Qwen3.8 27B, gpt-oss-120b and 5 more, as of 18:18 UTC.
1
1
36
Sell your own model on llm.buzz. We take 0% of your price.
Apply once, list it from your endpoint and set five prices: input, output, cached input, cache write, reasoning.
We approve a new model once. An automated check sends real requests, and it goes live when it passes.
1
28
Mistral Medium 3.5 on llm.buzz: $1.19 in, $5.95 out per 1M tokens.
@MistralAI's own API: $1.50 / $7.50.
That's 20% under, as an Auto deal.
The lowest price we track for it, as of 07:19 UTC.
1
25
84 models on llm.buzz, and any of them can take another seller.
If you serve one for less than the price you see, list your endpoint next to it.
Apply once and you set the price. An automated check sends real requests, and the listing goes live when it passes.
We take 0%.
1
25
Open weights with no third-party host yet:
Mistral Large 4 from @MistralAI: 1.05T total, 52B active, 1M context.
Flint from @Recursive_SI: 40B total, 2.5B active, Apache 2.0.
Serving one? List it on llm.buzz. The first seller sets the price.
1
23
Claude Sonnet 5 on llm.buzz: $1.60 in, $8 out per million tokens.
@AnthropicAI list: $2 in, $10 out.
Cache reads $0.16, 20% off as an Auto deal.
Prices as of 10:16 UTC today.
1
23












