Decart — pricing & performance
Models served
9
of 1,299 tracked models
Mean output speed
107
tokens per second, averaged over
9 measured endpoints
9 measured endpoints
Mean latency
1.0s
time to first token, averaged over
9 measured endpoints
9 measured endpoints
Cheapest blended
$0.000
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on Decart
Output tokens per second for all 9 models on Decart with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.
All 9 of 9 models⇩
The Known Good
9 models on Decart
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
DeepSeek: DeepSeek V4 Flash 0731
|
DeepSeek | $0.064 | $0.13 | $0.080 | 55 | 0.8s | 262k |
|
DeepSeek: DeepSeek V4.1 Flash
|
DeepSeek | $0.090 | $0.18 | $0.11 | 80 | 0.6s | 1.05M |
|
DeepSeek: DeepSeek V4.1 Flash 1017
|
DeepSeek | $0.14 | $0.55 | $0.24 | 110 | 0.9s | 1.05M |
MoonshotAI: Kimi K2.6
|
Moonshot AI | $0.59 | $2.47 | $1.06 | 33 | 0.7s | 262k |
|
MoonshotAI: Kimi K3
|
Moonshot AI | $1.65 | $8.25 | $3.30 | 73 | 1.0s | 1.05M |
Z.ai: GLM 5.2
|
Z.ai | $1.20 | $8.00 | $2.90 | 379 | 0.5s | 1.05M |
|
Z.ai: GLM 5.2 (free)
|
Z.ai | $0.000 | $0.000 | $0.000 | 45 | 2.1s | 131k |
|
Z.ai: GLM 5.3
|
Z.ai | $0.84 | $2.71 | $1.31 | 107 | 0.9s | 1.05M |
|
Z.ai: GLM 5.3 Flash
|
Z.ai | $0.083 | $0.28 | $0.13 | 78 | 1.1s | 1.05M |
The Known Good
Source. Prices, endpoint availability and throughput for Decart 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.