PrimeIntellect
Inference provider
Models on PrimeIntellect · prices & measurements for models served by PrimeIntellect’s APIUSD / MTOK · VERIFIED 19 MINUTES AGO
| MODEL | INPUT | OUTPUT | CONTEXT | QUANT | TTFT | TPS | VS BEST ELSEWHERE |
|---|---|---|---|---|---|---|---|
 Qwen3.6 35B A3BQwenBEST PRICE | $0.011 | $0.101 | 262K | fp8 | — | — | cheapest here |
 gpt-oss-20bOpenAI | $0.02 | $0.03 | 131K | fp4 | — | — | $0.018 elsewhere |
| gpt-oss-120bOpenAI | $0.035 | $0.075 | 131K | fp4 | 11.8s° | 97° tok/s | $0.03 elsewhere |
 Gemma 4 26B A4B GoogleBEST PRICE | $0.036 | $0.107 | 262K | bf16 | 1.1s° | 106° tok/s | cheapest here |
 DeepSeek V4.1 FlashDeepSeek | $0.039 | $1.20 | 1.05M | — | 0.65s° | 316° tok/s | $0.006 elsewhere |
| DeepSeek V4.1 Flash 1017DeepSeek | $0.044 | $0.70 | 1.05M | — | 0.58s° | 204° tok/s | $0.006 elsewhere |
| Qwen3.5-9BQwenBEST PRICE | $0.046 | $0.068 | 262K | bf16 | — | — | cheapest here |
 GLM 5.3 FlashZ.ai | $0.052 | $0.25 | 1.05M | — | ✕ | ✕ | $0.034 elsewhere |
 Nemotron 3.5 Super VLNVIDIA | $0.15 | $0.50 | 1.05M | nvfp4 | — | — | $0.06 elsewhere |
| MOMoondream 3 PreviewMoondream | $0.30 | $2.50 | 32K | fp8 | 0.95s° | 303° tok/s | only provider |
| MOMoondream 3.1Moondream | $0.30 | $2.50 | 32K | fp8 | 0.39s° | 299° tok/s | only provider |
| Gemma 4 31BGoogle | $0.40 | $0.67 | 262K | fp4 | 1.4s° | 45° tok/s | $0.10 elsewhere |
| DeepSeek V4 Flash 0731DeepSeek | $0.44 | $1.32 | 1.05M | fp4 | — | — | $0.043 elsewhere |
| Qwen3.8 27BQwen | $0.45 | $3.20 | 262K | fp8 | 0.93s° | 87° tok/s | $0.03 elsewhere |
| GLM 5.3Z.ai | $0.50 | $3.08 | 1.05M | — | 1.1s° | 267° tok/s | $0.07 elsewhere |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 21d) for PrimeIntellect’s endpoints · ° = measured via OpenRouter routing · ✕ = probed, no measurable stream · SMOKE: of 5 capability probes passed · methodology on each model page