Providers/Together
Together logo

Together

Inference providertogether.ai ↗Status ↗
MODELS
20
ENDPOINTS
20
MIN INPUT
$0.15
MEDIAN BLENDED
$0.619
AVG UPTIME
99.8%
CHEAPEST FOR
3 models
Models on Together · prices & measurements for models served by Together’s APIUSD / MTOK · VERIFIED 15 MINUTES AGO
MODELINPUTOUTPUTCONTEXTQUANTTTFTTPSSMOKEVS BEST ELSEWHERE
MiniMax logoMiniMax M3.1 FlashMiniMax$0.15$0.601.05M—0.68s°233° tok/s—$0.135 elsewhere
NVIDIA logoNemotron 3.5 Super VLNVIDIA$0.15$0.50262K—0.5s°267° tok/s—$0.06 elsewhere
Z.ai logoGLM 5.3 FlashZ.ai$0.15$0.501.05M—0.52s°227° tok/s—$0.04 elsewhere
OpenAI logogpt-oss-120bOpenAI$0.15$0.60131K—0.37s°155° tok/s—$0.03 elsewhere
Qwen logoQwen3.5-9BQwen$0.17$0.25262K—0.42s°152° tok/s—$0.08 elsewhere
RIRipple 65B PreviewRicursiveai$0.20$0.60131K————$0.10 elsewhere
Thinking Machines logoInkling 2 SmallThinking Machines$0.30$1.001.05M—0.28s°337° tok/s—$0.15 elsewhere
DeepSeek logoDeepSeek V4.1 Flash 1017DeepSeek$0.30$1.201.05M—0.22s°223° tok/s—$0.036 elsewhere
DeepSeek logoDeepSeek V4.1 FlashDeepSeek$0.30$1.201.05M—0.23s°382° tok/s—$0.05 elsewhere
Meta logoMuse Glimmer 30BMeta$0.35$1.50131K—0.65s°88° tok/s—$0.30 elsewhere
REBeam 1.0 501B A23BReflection$0.40$1.201.05M—0.4s°303° tok/s—$0.25 elsewhere
ELGlimpseElorian$0.60$3.00262K—0.57s°214° tok/s—only provider
Tencent logoHy4Tencent$0.834$2.501.05M————$0.417 elsewhere
Thinking Machines logoInklingThinking Machines$1.00$4.05524K—0.51s°117° tok/s—only provider
Meta logoMuse Spark OpenMetaBEST PRICE$1.25$4.251.05M—0.43s°304° tok/s—cheapest here
DeepSeek logoDeepSeek V4 Pro 0813DeepSeek$1.32$3.961.05M—2.2s°207° tok/s4/5$0.10 elsewhere
Z.ai logoGLM 5.3Z.ai$1.40$4.401.05M—0.56s°155° tok/s—$0.07 elsewhere
Z.ai logoGLM 5.2Z.ai$1.40$4.401.05M—0.54s°355° tok/s—$0.007 elsewhere
Moonshot AI logoKimi K3.1 ProMoonshot AI$2.00$10.001.05M————$0.24 elsewhere
Moonshot AI logoKimi K3Moonshot AI$3.00$15.001.05M—0.81s°122° tok/s—$0.182 elsewhere
TTFT/TPS: ModelIndex-measured medians (P50, trailing 21d) for Together’s endpoints · ° = measured via OpenRouter routing · ✕ = probed, no measurable stream · SMOKE: of 5 capability probes passed · methodology on each model page