The Known Good Updated 8 Sep 2026 Subscribe
Providers· Inference host· 11 tracked models

Chutes — pricing & performance

Compare models All providers Data sources
Models served
11
of 1,109 tracked models
Mean output speed
25
tokens per second, averaged over
10 measured endpoints
Mean latency
2.4s
time to first token, averaged over
10 measured endpoints
Cheapest blended
$0.18
per 1M tokens at a 3:1
input:output blend
Output speed on Chutes

Output tokens per second for the 10 of 11 models on Chutes with published throughput telemetry, the most recent figure OpenRouter publishes for each host. The full table below lists all 11, measured or not. Higher is better. We do not run these measurements ourselves.

All 10 of 10 models⇩
45
32
30
30
29
29
21
18
11
4
The Known Good
11 models on Chutes
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
Google: Gemma 4 31B Google $0.12 $0.37 $0.18 11 2.5s 131k
MiniMax: MiniMax M2.5 MiniMax $0.15 $1.20 $0.41 18 1.7s 197k
MoonshotAI: Kimi K2.5 Moonshot AI $0.44 $2.00 $0.83 29 1.3s 262k
MoonshotAI: Kimi K2.6 Moonshot AI $0.58 $3.40 $1.28 21 3.6s 262k
MoonshotAI: Kimi K3 Moonshot AI $3.00 $15.00 $6.00 29 1.8s 1.05M
Qwen: Qwen3.5 397B A17B Alibaba $0.45 $3.00 $1.09 — — 262k
Qwen: Qwen3.6 27B Alibaba $0.30 $2.00 $0.72 30 2.2s 262k
Qwen: Qwen3.8 27B Alibaba $0.32 $2.50 $0.86 32 2.6s 262k
Z.ai: GLM 5 Z.ai $0.95 $2.55 $1.35 45 1.9s 203k
Z.ai: GLM 5.1 Z.ai $0.98 $3.08 $1.50 30 4.0s 203k
Z.ai: GLM 5.2 Z.ai $1.25 $3.95 $1.93 4 2.1s 1.05M
The Known Good
Source. Prices, endpoint availability and throughput for Chutes 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.