The Known Good Updated 25 Jul 2026
Providers· Inference host· 10 tracked models

NextBit — pricing & performance

Compare models All providers Data sources
Models served
10
of 908 tracked models
Mean output speed
42
tokens per second, averaged over
9 measured endpoints
Mean latency
0.7s
time to first token, averaged over
9 measured endpoints
Cheapest blended
$0.060
per 1M tokens at a 3:1
input:output blend
Output speed on NextBit

Median output tokens per second for each model this host serves, derived from OpenRouter endpoint telemetry. Higher is better. We do not run these measurements ourselves.

9 of 10 models ▾ ☰⚙⇩ +Add model from specific provider
100
75
59
54
39
21
17
10
8
The Known Good
10 models on NextBit
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
Google: Gemma 2 27B Google $0.65 $0.65 $0.65 — — 8k
Google: Gemma 4 26B A4B Google $0.12 $0.35 $0.18 54 0.6s 262k
Mistral: Ministral 3 8B 2512 Mistral $0.30 $0.30 $0.30 8 0.5s 262k
MythoMax 13B gryphe $0.060 $0.060 $0.060 39 0.6s 4k
Qwen: Qwen3 14B Alibaba $0.10 $0.24 $0.14 59 0.7s 41k
Qwen: Qwen3 30B A3B Alibaba $0.14 $0.55 $0.24 17 1.0s 33k
Qwen: Qwen3.5-35B-A3B Alibaba $0.23 $1.60 $0.57 100 0.6s 262k
ReMM SLERP 13B undi95 $0.45 $0.65 $0.50 21 0.6s 6k
Sao10K: Llama 3.3 Euryale 70B sao10k $0.65 $0.75 $0.68 10 1.4s 131k
TheDrummer: UnslopNemo 12B thedrummer $0.40 $0.40 $0.40 75 0.6s 33k
The Known Good
Source. Prices, endpoint availability and throughput for NextBit are ingested from OpenRouter; model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint — it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this site; see methodology. Quality scores are not provider-specific: a model scores the same wherever it is hosted, so quality lives on the model pages.