Groq
Models on Groq · prices & measurements for models served by Groq’s APIUSD / MTOK · VERIFIED 4 MINUTES AGO
| MODEL | INPUT | OUTPUT | CONTEXT | QUANT | TTFT | TPS | SMOKE | VS BEST ELSEWHERE |
|---|---|---|---|---|---|---|---|---|
 Llama 3.1 8B InstructMeta | $0.05 | $0.08 | 131K | — | 0.66s° | 507° tok/s | 4/5 | $0.02 elsewhere |
 gpt-oss-safeguard-20bOpenAI | $0.075 | $0.30 | 131K | — | 1.1s° | 495° tok/s | — | only provider |
| gpt-oss-20bOpenAI | $0.075 | $0.30 | 131K | — | 0.78s° | 552° tok/s | — | $0.03 elsewhere |
| Llama 4 ScoutMeta | $0.11 | $0.34 | 131K | — | 0.67s° | 439° tok/s | — | $0.10 elsewhere |
| gpt-oss-120bOpenAI | $0.15 | $0.60 | 131K | — | 0.7s | 469 tok/s | — | $0.03 elsewhere |
 Qwen3 32BQwen | $0.29 | $0.59 | 131K | — | 0.92s° | 351° tok/s | — | $0.08 elsewhere |
| Llama 3.3 70B InstructMeta | $0.59 | $0.79 | 131K | — | 0.84s° | 237° tok/s | — | $0.10 elsewhere |
 MiniMax M2.7MiniMax | $0.60 | $1.80 | 197K | — | 0.81s° | 442° tok/s | — | $0.24 elsewhere |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 72h) for Groq’s endpoints · ° = measured via OpenRouter routing · ✕ = probed, no measurable stream · SMOKE: of 5 capability probes passed · methodology on each model page