The Known Good Updated 24 Oct 2026 Subscribe
Providers· Inference host· 10 tracked models

Mancer 2 — pricing & performance

Compare models All providers Data sources
Models served
10
of 1,302 tracked models
Mean output speed
54
tokens per second, averaged over
10 measured endpoints
Mean latency
6.4s
time to first token, averaged over
10 measured endpoints
Cheapest blended
$0.10
per 1M tokens at a 3:1
input:output blend
Output speed on Mancer 2

Output tokens per second for all 10 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 10 of 10 models⇩
97
76
74
70
53
51
50
26
25
17
The Known Good
10 models on Mancer 2
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
DeepSeek: DeepSeek V4 Flash 0423 DeepSeek $0.19 $0.50 $0.27 50 1.0s 1.05M
DeepSeek: DeepSeek V4 Flash 0731 DeepSeek $0.20 $0.60 $0.30 74 0.7s 1.05M
DeepSeek: DeepSeek V4.1 Flash DeepSeek $0.20 $1.00 $0.40 25 55.0s 1.05M
Magnum v4 72B anthracite-org $2.50 $5.00 $3.12 17 1.1s 33k
Mancer: Weaver (alpha) mancer $0.40 $0.75 $0.49 76 0.9s 8k
MythoMax 13B gryphe $0.35 $0.60 $0.41 70 0.5s 8k
OpenAI: gpt-oss-120b OpenAI $0.050 $0.25 $0.10 97 0.5s 131k
Qwen: Qwen3.8 27B Alibaba $0.18 $2.50 $0.76 53 2.0s 262k
ReMM SLERP 13B undi95 $0.35 $0.65 $0.42 51 1.0s 6k
Z.ai: GLM 4.7 Z.ai $0.70 $2.50 $1.15 26 1.2s 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.