Together — pricing & performance
Models served
55
of 1,295 tracked models
Mean output speed
106
tokens per second, averaged over
28 measured endpoints
28 measured endpoints
Mean latency
0.9s
time to first token, averaged over
28 measured endpoints
28 measured endpoints
Cheapest blended
$0.075
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on Together
Output tokens per second for the 28 of 55 models on Together with published throughput telemetry, the most recent figure OpenRouter publishes for each host. The full table below lists all 55, measured or not. Higher is better. We do not run these measurements ourselves.
The Known Good
55 models on Together
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
| AA Arcee AI: Virtuoso Large | arcee-ai | $0.75 | $1.20 | $0.86 | — | — | 131k |
| De Deep Cogito: Cogito v2.1 671B | deepcogito | $1.25 | $1.25 | $1.25 | — | — | 128k |
|
|
DeepSeek | $0.14 | $0.28 | $0.17 | 79 | 0.5s | 1.05M |
|
|
DeepSeek | $0.14 | $0.28 | $0.17 | — | — | 1.05M |
|
|
DeepSeek | $1.74 | $3.48 | $2.17 | 39 | 0.6s | 512k |
|
|
DeepSeek | $1.32 | $3.96 | $1.98 | 111 | 0.5s | 1.05M |
|
|
DeepSeek | $1.32 | $3.96 | $1.98 | — | — | 1.05M |
|
|
DeepSeek | $0.30 | $1.20 | $0.53 | 266 | 0.2s | 1.05M |
|
|
DeepSeek | $0.15 | $0.60 | $0.26 | — | — | 1.05M |
|
|
DeepSeek | $0.30 | $1.20 | $0.53 | 188 | 0.5s | 1.05M |
|
|
DeepSeek | $0.15 | $0.60 | $0.26 | — | — | 1.05M |
| El Elorian: Glimpse | elorian | $0.60 | $3.00 | $1.20 | 138 | 9.0s | 262k |
|
|
$0.060 | $0.12 | $0.075 | 33 | 0.3s | 33k | |
|
|
$0.39 | $0.97 | $0.54 | — | — | 262k | |
|
|
$0.39 | $0.97 | $0.54 | — | — | 262k | |
|
|
Meta | $1.04 | $1.04 | $1.04 | 46 | 0.5s | 131k |
|
|
Meta | $0.20 | $0.20 | $0.20 | 14 | 0.1s | 1.05M |
|
|
Meta | $0.35 | $1.50 | $0.64 | 64 | 0.5s | 131k |
|
|
Meta | $0.35 | $1.50 | $0.64 | — | — | 131k |
|
|
Meta | $1.25 | $4.25 | $2.00 | 43 | 1.1s | 1.05M |
|
|
MiniMax | $0.30 | $1.20 | $0.53 | 68 | 0.3s | 197k |
|
|
MiniMax | $0.30 | $1.20 | $0.53 | 75 | 0.8s | 524k |
|
|
MiniMax | $0.30 | $1.20 | $0.53 | — | — | 524k |
|
|
MiniMax | $0.15 | $0.60 | $0.26 | 153 | 0.4s | 1.05M |
|
|
Moonshot AI | $1.20 | $4.50 | $2.02 | 119 | 0.4s | 262k |
|
|
Moonshot AI | $0.95 | $4.00 | $1.71 | — | — | 262k |
|
|
Moonshot AI | $0.95 | $4.00 | $1.71 | — | — | 262k |
|
|
Moonshot AI | $3.00 | $15.00 | $6.00 | 55 | 1.4s | 1.05M |
|
|
Moonshot AI | $3.00 | $15.00 | $6.00 | — | — | 1.05M |
|
|
Moonshot AI | $2.00 | $10.00 | $4.00 | 40 | 1.6s | 1.05M |
|
|
NVIDIA | $0.60 | $3.60 | $1.35 | — | — | 512k |
|
|
NVIDIA | $0.60 | $3.60 | $1.35 | — | — | 512k |
|
|
NVIDIA | $0.15 | $0.50 | $0.24 | 157 | 0.6s | 262k |
|
|
OpenAI | $0.15 | $0.60 | $0.26 | 89 | 0.2s | 131k |
|
|
OpenAI | $0.15 | $0.60 | $0.26 | — | — | 131k |
|
|
OpenAI | $0.050 | $0.20 | $0.087 | — | — | 131k |
|
|
OpenAI | $0.050 | $0.20 | $0.087 | — | — | 131k |
|
|
Alibaba | $0.30 | $0.30 | $0.30 | — | — | 33k |
|
|
Alibaba | $0.17 | $0.25 | $0.19 | 53 | 0.5s | 262k |
|
|
Alibaba | $0.17 | $0.25 | $0.19 | — | — | 262k |
|
|
Alibaba | $2.00 | $6.00 | $3.00 | 21 | 1.2s | 1.01M |
|
|
Alibaba | $2.00 | $6.00 | $3.00 | — | — | 1.01M |
| Re Reflection: Beam 1.0 501B A23B | reflection | $0.40 | $1.20 | $0.60 | 206 | 0.3s | 1.05M |
| Ri Ricursive: Ripple 65B Preview | ricursiveai | $0.20 | $0.60 | $0.30 | 183 | 0.3s | 131k |
| TM Thinking Machines: Inkling | Thinking Machines | $1.00 | $4.05 | $1.76 | 121 | 0.3s | 524k |
| TM Thinking Machines: Inkling (batch) | Thinking Machines | $1.00 | $4.05 | $1.76 | — | — | 524k |
| TM Thinking Machines: Inkling 2 Small | Thinking Machines | $0.30 | $1.00 | $0.47 | 219 | 0.4s | 1.05M |
| TM Thinking Machines: Inkling Small | Thinking Machines | $0.50 | $1.20 | $0.68 | — | — | 524k |
| TM Thinking Machines: Inkling Small (batch) | Thinking Machines | $0.50 | $1.20 | $0.68 | — | — | 524k |
|
|
Z.ai | $1.40 | $4.40 | $2.15 | 171 | 0.4s | 1.05M |
|
|
Z.ai | $1.40 | $4.40 | $2.15 | — | — | 1.05M |
|
|
Z.ai | $1.40 | $4.40 | $2.15 | 97 | 0.5s | 1.05M |
|
|
Z.ai | $0.70 | $2.20 | $1.07 | — | — | 1.05M |
|
|
Z.ai | $0.15 | $0.50 | $0.24 | 122 | 0.7s | 1.05M |
|
|
Z.ai | $0.075 | $0.25 | $0.12 | — | — | 1.05M |
The Known Good
Source. Prices, endpoint availability and throughput for Together 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.