Bertrande

Which model for what you are building

Say what you are building. We show the offers that fit, ranked on a criterion we name, with every figure carrying the day we observed it.

What are you building
Narrow it down

A chatbot people talk to. Answers have to start fast, so time to first token matters more than raw throughput, and a cached system prompt is what makes it affordable. Ranked by lowest time to first token, then lowest output price, across 1 045 offers for which we hold a published output price.

#OfferOutputCached inputFirst tokenEntityObserved
1Muse Glimmer 30BFireworks AI$1.50$0.040102 msnot established16 September 2026
2openai/gpt-oss-120bCerebras$0.750not measured188 ms🇺🇸16 September 2026
3Qwen/Qwen3.8-27BCerebras$1.49not measured192 ms🇺🇸17 September 2026
4NousResearch/Hermes-3-Llama-3.1-70BDeepInfra$0.700not measured212 ms🇺🇸15 September 2026
5Qwen/Qwen3-14BDeepInfra$0.240not measured220 ms🇺🇸15 September 2026
6ibm-granite/granite-4.2-3bDeepInfra$0.120not measured220 ms🇺🇸15 September 2026
7Qwen/Qwen3-30B-A3BDeepInfra$0.500not measured228 ms🇺🇸15 September 2026
8Qwen/Qwen3.6-27BDeepInfra$3.20not measured242 ms🇺🇸15 September 2026
9meta-models/Muse-Glimmer-30BDeepInfra$1.20not measured246 ms🇺🇸15 September 2026
10GPT OSS 20BGroq$0.300$0.037247 ms🇬🇧🇺🇸18 September 2026
11InklingBaseten$4.05$0.170249 ms🇺🇸18 September 2026
12ibm-granite/granite-4.2-8bDeepInfra$0.250not measured257 ms🇺🇸15 September 2026

What this does, and what it refuses to do

It computes no score. It applies the filters named above and sorts on the criterion printed with the result. A single score would mix dollars with milliseconds and weight them according to an opinion, and the opinion would be ours rather than yours. You can see the criterion, so you can disagree with it.

It says what it does not know. An offer with no measured latency is not slow, it is unmeasured, and it stays in the list saying so rather than being pushed down. Speed comes from the Hugging Face router and availability from OpenRouter's router, neither is our own measurement, and both are the median of our own daily readings rather than the latest figure alone.

It ignores what it cannot check. Nothing here says a model is good at your task. Capability scores are relayed from Artificial Analysis and measure the model, not the seller. Whether a model suits you is a judgement we do not make.

Every row links to the offer page, where each figure carries its date, its source URL and a fingerprint of that source. The complete set of 1 045 offers is in the catalogue and in prices.json.