Tenstorrent — pricing & performance
Models served
4
of 1,191 tracked models
Mean output speed
58
tokens per second, averaged over
4 measured endpoints
4 measured endpoints
Mean latency
0.8s
time to first token, averaged over
4 measured endpoints
4 measured endpoints
Cheapest blended
$0.20
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on Tenstorrent
Output tokens per second for all 4 models on Tenstorrent with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.
All 4 of 4 models⇩
The Known Good
4 models on Tenstorrent
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
MoonshotAI: Kimi K2.7 Code
|
Moonshot AI | $0.85 | $3.00 | $1.39 | 106 | 0.6s | 256k |
Qwen: Qwen3 32B
|
Alibaba | $0.14 | $0.40 | $0.20 | 6 | 1.3s | 20k |
|
Qwen: Qwen3.8 27B
|
Alibaba | $0.040 | $1.35 | $0.37 | 31 | 0.9s | 262k |
Z.ai: GLM 5.3
|
Z.ai | $0.60 | $2.50 | $1.07 | 91 | 0.2s | 1.04M |
The Known Good
Source. Prices, endpoint availability and throughput for Tenstorrent 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.