The Known Good Updated 8 Oct 2026 Subscribe
Providers· Inference host· 20 tracked models

NextBit — pricing & performance

Compare models All providers Data sources
Models served
20
of 1,191 tracked models
Mean output speed
48
tokens per second, averaged over
19 measured endpoints
Mean latency
1.6s
time to first token, averaged over
19 measured endpoints
Cheapest blended
$0.060
per 1M tokens at a 3:1
input:output blend
Output speed on NextBit

Output tokens per second for the 19 of 20 models on NextBit with published throughput telemetry, the most recent figure OpenRouter publishes for each host. The full table below lists all 20, measured or not. Higher is better. We do not run these measurements ourselves.

⇩
128
83
77
70
61
55
53
53
52
52
45
43
The Known Good
20 models on NextBit
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
DeepSeek: DeepSeek V4 Flash 0423 DeepSeek $0.15 $0.30 $0.19 61 2.2s 1.05M
DeepSeek: DeepSeek V4 Flash 0731 DeepSeek $0.35 $1.06 $0.53 70 2.0s 1.05M
DeepSeek: DeepSeek V4 Pro 0423 DeepSeek $1.74 $3.48 $2.17 45 4.0s 1.05M
DeepSeek: DeepSeek V4 Pro 0813 DeepSeek $1.06 $3.17 $1.58 39 2.7s 1.05M
DeepSeek: DeepSeek V4.1 Flash DeepSeek $0.21 $0.84 $0.37 53 2.4s 1.05M
Google: Gemma 2 27B Google $0.65 $0.65 $0.65 52 1.2s 8k
Google: Gemma 3 12B Google $0.050 $0.15 $0.075 43 0.5s 131k
Google: Gemma 3 27B Google $0.080 $0.30 $0.14 15 1.1s 131k
Google: Gemma 4 26B A4B Google $0.076 $0.26 $0.12 83 0.2s 262k
Google: Gemma 4 31B Google $0.15 $0.40 $0.21 4 2.4s 262k
MiniMax: MiniMax M2.7 MiniMax $0.30 $1.30 $0.55 52 1.8s 197k
Mistral: Ministral 3 8B 2512 Mistral $0.30 $0.30 $0.30 17 0.7s 262k
MythoMax 13B gryphe $0.060 $0.060 $0.060 55 0.3s 4k
Qwen: Qwen3 14B Alibaba $0.10 $0.22 $0.13 53 0.4s 41k
Qwen: Qwen3 30B A3B Alibaba $0.12 $0.52 $0.22 128 0.7s 33k
Qwen: Qwen3.5-35B-A3B Alibaba $0.22 $1.40 $0.52 — — 262k
ReMM SLERP 13B undi95 $0.45 $0.65 $0.50 21 1.2s 6k
Sao10K: Llama 3.3 Euryale 70B sao10k $0.65 $0.75 $0.68 17 1.0s 131k
TheDrummer: UnslopNemo 12B thedrummer $0.40 $0.40 $0.40 77 0.3s 33k
Z.ai: GLM 5.3 Flash Z.ai $0.17 $0.55 $0.26 33 4.4s 1.05M
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.