Ne Providers· Inference host· 12 tracked models

NextBit — pricing & performance

Compare models All providers Data sources

Models served

of 947 tracked models

Mean output speed

tokens per second, averaged over
11 measured endpoints

Mean latency

1.2s

time to first token, averaged over
11 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 the 11 of 12 models on NextBit with published throughput telemetry from OpenRouter. The full table below lists all 12, measured or not. Higher is better. We do not run these measurements ourselves.

⇩

Llama 3.3 Euryale
70B

Qwen3 14B

Gemma 4 31B

The Known Good

12 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	31	0.7s	8k
Google: Gemma 4 26B A4B	Google	$0.15	$0.45	$0.23	42	0.8s	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	27	0.7s	262k
Gr MythoMax 13B	gryphe	$0.060	$0.060	$0.060	45	0.6s	4k
Qwen: Qwen3 14B	Alibaba	$0.10	$0.24	$0.14	7	0.6s	41k
Qwen: Qwen3 30B A3B	Alibaba	$0.14	$0.55	$0.24	17	0.8s	33k
Qwen: Qwen3.5-35B-A3B	Alibaba	$0.23	$1.60	$0.57	54	1.7s	262k
Un ReMM SLERP 13B	undi95	$0.45	$0.65	$0.50	19	1.0s	6k
Sa Sao10K: Llama 3.3 Euryale 70B	sao10k	$0.65	$0.75	$0.68	11	2.6s	131k
Th TheDrummer: UnslopNemo 12B	thedrummer	$0.40	$0.40	$0.40	—	—	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.