Groq — pricing & performance
Models served
9
of 908 tracked models
Mean output speed
257
tokens per second, averaged over
9 measured endpoints
9 measured endpoints
Mean latency
0.3s
time to first token, averaged over
9 measured endpoints
9 measured endpoints
Cheapest blended
$0.058
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on Groq
Median output tokens per second for each model this host serves, derived from OpenRouter endpoint telemetry. Higher is better. We do not run these measurements ourselves.
9 of 9 models ▾
☰⚙⇩
+Add model from specific provider
The Known Good
9 models on Groq
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
Meta: Llama 3.1 8B Instruct
|
Meta | $0.050 | $0.080 | $0.058 | 102 | 0.3s | 131k |
|
Meta: Llama 3.3 70B Instruct
|
Meta | $0.59 | $0.79 | $0.64 | 178 | 0.2s | 131k |
|
Meta: Llama 4 Scout
|
Meta | $0.11 | $0.34 | $0.17 | 164 | 0.4s | 131k |
MiniMax: MiniMax M2.7
|
MiniMax | $0.60 | $1.80 | $0.90 | 169 | 1.0s | 197k |
MoonshotAI: Kimi K2 0905
|
Moonshot AI | $1.00 | $3.00 | $1.50 | 65 | 0.3s | 262k |
OpenAI: gpt-oss-120b
|
OpenAI | $0.15 | $0.60 | $0.26 | 411 | 0.1s | 131k |
|
OpenAI: gpt-oss-20b
|
OpenAI | $0.075 | $0.30 | $0.13 | 393 | 0.3s | 131k |
|
OpenAI: gpt-oss-safeguard-20b
|
OpenAI | $0.075 | $0.30 | $0.13 | 394 | 0.2s | 131k |
Qwen: Qwen3 32B
|
Alibaba | $0.29 | $0.59 | $0.36 | 441 | 0.3s | 131k |
The Known Good
Source. Prices, endpoint availability and throughput for Groq 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.