The Known Good Updated 4 Sep 2026 Subscribe
Providers· Inference host· 8 tracked models

Mancer 2 — pricing & performance

Compare models All providers Data sources
Models served
8
of 1,094 tracked models
Mean output speed
41
tokens per second, averaged over
8 measured endpoints
Mean latency
0.7s
time to first token, averaged over
8 measured endpoints
Cheapest blended
$0.17
per 1M tokens at a 3:1
input:output blend
Output speed on Mancer 2

Output tokens per second for all 8 models on Mancer 2 with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.

All 8 of 8 models⇩
95
56
53
33
30
27
18
16
The Known Good
8 models on Mancer 2
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
DeepSeek: DeepSeek V4 Flash 0423 DeepSeek $0.17 $0.50 $0.26 33 0.8s 1.05M
DeepSeek: DeepSeek V4 Flash 0731 DeepSeek $0.17 $0.50 $0.26 27 0.9s 1.05M
Magnum v4 72B anthracite-org $2.50 $5.00 $3.12 16 1.1s 33k
Mancer: Weaver (alpha) mancer $0.40 $0.75 $0.49 18 0.5s 8k
MythoMax 13B gryphe $0.35 $0.60 $0.41 53 0.3s 8k
OpenAI: gpt-oss-120b OpenAI $0.055 $0.50 $0.17 95 0.4s 131k
ReMM SLERP 13B undi95 $0.35 $0.65 $0.42 56 0.3s 6k
Z.ai: GLM 4.7 Z.ai $0.70 $2.50 $1.15 30 0.9s 131k
The Known Good
Source. Prices, endpoint availability and throughput for Mancer 2 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.