The Known Good Updated 23 Oct 2026 Subscribe
Providers· Inference host· 13 tracked models

Relace — pricing & performance

Compare models All providers Data sources
Models served
13
of 1,299 tracked models
Mean output speed
256
tokens per second, averaged over
12 measured endpoints
Mean latency
1.0s
time to first token, averaged over
12 measured endpoints
Cheapest blended
$0.044
per 1M tokens at a 3:1
input:output blend
Output speed on Relace

Output tokens per second for the 12 of 13 models on Relace with published throughput telemetry, the most recent figure OpenRouter publishes for each host. The full table below lists all 13, measured or not. Higher is better. We do not run these measurements ourselves.

⇩
2066
140
109
109
107
107
100
84
83
74
50
42
The Known Good
13 models on Relace
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
DeepSeek: DeepSeek V4 Flash 0423 DeepSeek $0.041 $0.45 $0.14 83 0.4s 1.05M
DeepSeek: DeepSeek V4 Flash 0731 DeepSeek $0.042 $0.17 $0.074 74 0.3s 1.05M
DeepSeek: DeepSeek V4 Pro 0423 DeepSeek $0.90 $1.50 $1.05 109 0.7s 1.05M
DeepSeek: DeepSeek V4 Pro 0813 DeepSeek $0.12 $8.00 $2.09 100 0.9s 1.05M
DeepSeek: DeepSeek V4.1 Flash DeepSeek $0.070 $0.50 $0.18 107 0.5s 1.05M
DeepSeek: DeepSeek V4.1 Flash 1017 DeepSeek $0.070 $0.50 $0.18 140 0.9s 1.05M
MoonshotAI: Kimi K3 Moonshot AI $0.30 $12.00 $3.23 84 2.1s 1.05M
Relace: Relace Apply 3 relace $0.85 $1.25 $0.95 2,066 0.4s 256k
Relace: Relace Search relace $1.00 $3.00 $1.50 107 0.9s 256k
Xiaomi: MiMo-V2.6-Flash Xiaomi $0.13 $0.28 $0.17 109 1.2s 1.05M
Z.ai: GLM 5.2 Z.ai $0.40 $4.00 $1.30 — — 1.05M
Z.ai: GLM 5.3 Z.ai $0.75 $2.40 $1.16 42 2.6s 1.05M
Z.ai: GLM 5.3 Flash Z.ai $0.030 $0.085 $0.044 50 1.4s 1.05M
The Known Good
Source. Prices, endpoint availability and throughput for Relace 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.