数据状态

同步自 OpenRouter Providers · 109 家托管商 · source=openrouter · 2026-09-18T19:57:16.903Z

baseten

BaseTen

总部 美国

14 模型59 端点日可用 98.2%
托管模型14
端点59
日可用率均98.2%
最低输入 $/M$0.100
最大上下文1.0M

托管端点 · 59

来自 OpenRouter 各模型 Endpoints API:同一模型可能有多量化 / 多区域端点。

模型Tag量化上下文输入输出5m30m1d延迟吞吐缓存
nemotron-3-ultra-550b-a55b
nvidia/nemotron-3-ultra-550b-a55b
baseten/fp4fp4203k$0.600$2.40100.00%100.00%100.00%
nemotron-3-ultra-550b-a55b
nvidia/nemotron-3-ultra-550b-a55b
baseten/fp4fp4203k$0.600$2.40100.00%100.00%100.00%
nemotron-3-ultra-550b-a55b
nvidia/nemotron-3-ultra-550b-a55b
baseten/fp4fp4203k$0.600$2.40100.00%100.00%100.00%
nemotron-3-ultra-550b-a55b
nvidia/nemotron-3-ultra-550b-a55b
baseten/fp4fp4203k$0.600$2.40100.00%100.00%100.00%
inkling-small
thinkingmachines/inkling-small
baseten/fp8fp81.0M$0.500$1.20100.00%99.99%
inkling-small
thinkingmachines/inkling-small
baseten/fp8fp81.0M$0.500$1.20100.00%99.99%
deepseek-v4-flash-0731
deepseek/deepseek-v4-flash-0731
baseten/fp8fp81.0M$0.130$0.260100.00%99.95%99.97%
deepseek-v4-flash-0731
deepseek/deepseek-v4-flash-0731
baseten/fp8fp81.0M$0.130$0.260100.00%99.95%99.97%
deepseek-v4-flash-0731
deepseek/deepseek-v4-flash-0731
baseten/fp8fp81.0M$0.130$0.260100.00%99.95%99.97%
deepseek-v4-flash-0731
deepseek/deepseek-v4-flash-0731
baseten/fp8fp81.0M$0.130$0.260100.00%100.00%99.97%
deepseek-v4-flash-0731
deepseek/deepseek-v4-flash-0731
baseten/fp8fp81.0M$0.130$0.260100.00%100.00%99.97%
deepseek-v4-flash-0731
deepseek/deepseek-v4-flash-0731
baseten/fp8fp81.0M$0.130$0.260100.00%100.00%99.97%
glm-5.2
z-ai/glm-5.2
baseten/fp8fp81.0M$1.40$4.40100.00%100.00%99.96%
glm-5.2
z-ai/glm-5.2
baseten/fp8fp81.0M$1.40$4.40100.00%100.00%99.96%
glm-5.2
z-ai/glm-5.2
baseten/fp8fp81.0M$1.40$4.40100.00%100.00%99.96%
glm-5.2
z-ai/glm-5.2
baseten/fastfp81.0M$2.10$6.6093.2%99.2%99.96%
glm-5.2
z-ai/glm-5.2
baseten/fastfp81.0M$2.10$6.6093.2%99.2%99.96%
glm-5.2
z-ai/glm-5.2
baseten/fastfp81.0M$2.10$6.6093.2%99.2%99.96%
glm-5.2
z-ai/glm-5.2
baseten/fastfp81.0M$2.10$6.6092.0%98.5%99.94%
glm-5.2
z-ai/glm-5.2
baseten/fastfp81.0M$2.10$6.6092.0%98.5%99.94%
glm-5.2
z-ai/glm-5.2
baseten/fastfp81.0M$2.10$6.6092.0%98.5%99.94%
gpt-oss-120b
openai/gpt-oss-120b
baseten/fp4fp4128k$0.100$0.500100.00%100.00%99.94%
gpt-oss-120b
openai/gpt-oss-120b
baseten/fp4fp4128k$0.100$0.500100.00%100.00%99.94%
glm-5.2
z-ai/glm-5.2
baseten/fp8fp81.0M$1.40$4.40100.00%100.00%99.92%
glm-5.2
z-ai/glm-5.2
baseten/fp8fp81.0M$1.40$4.40100.00%100.00%99.92%
glm-5.2
z-ai/glm-5.2
baseten/fp8fp81.0M$1.40$4.40100.00%100.00%99.92%
glm-5.3
z-ai/glm-5.3
baseten/fp4fp41.0M$1.40$4.40100.00%99.9%99.91%
glm-5.3
z-ai/glm-5.3
baseten/fp4fp41.0M$1.40$4.40100.00%99.9%99.91%
gpt-oss-120b
openai/gpt-oss-120b
baseten/fp4fp4128k$0.100$0.500100.00%99.97%99.9%
gpt-oss-120b
openai/gpt-oss-120b
baseten/fp4fp4128k$0.100$0.500100.00%99.97%99.9%
glm-5.3
z-ai/glm-5.3
baseten/fp4fp41.0M$1.40$4.40100.00%100.00%99.9%
glm-5.3
z-ai/glm-5.3
baseten/fp4fp41.0M$1.40$4.40100.00%100.00%99.9%
glm-5.3-flash
z-ai/glm-5.3-flash
baseten/fp8fp81.0M$0.150$0.50099.92%99.7%99.6%
glm-5.3-flash
z-ai/glm-5.3-flash
baseten/fp8fp81.0M$0.150$0.50099.92%99.7%99.6%
glm-5.3-flash
z-ai/glm-5.3-flash
baseten/fp8fp81.0M$0.150$0.500100.00%99.92%99.5%
glm-5.3-flash
z-ai/glm-5.3-flash
baseten/fp8fp81.0M$0.150$0.500100.00%99.92%99.5%
deepseek-v4-pro
deepseek/deepseek-v4-pro
baseten/fp4fp41.0M$1.74$3.48100.00%99.8%99.4%
deepseek-v4-pro
deepseek/deepseek-v4-pro
baseten/fp4fp41.0M$1.74$3.48100.00%99.7%99.3%
deepseek-v4.1-flash
deepseek/deepseek-v4.1-flash
baseten/fp8fp81.0M$0.300$1.20100.00%100.00%99.0%
kimi-k2.6
moonshotai/kimi-k2.6
baseten/fp4fp4262k$0.950$4.00100.00%100.00%98.9%
deepseek-v4.1-flash
deepseek/deepseek-v4.1-flash
baseten/fp8fp81.0M$0.300$1.20100.00%100.00%98.7%
deepseek-v4-pro-0813
deepseek/deepseek-v4-pro-0813
baseten/fp4fp41.0M$1.32$3.96100.00%98.2%
deepseek-v4-pro-0813
deepseek/deepseek-v4-pro-0813
baseten/fp4fp41.0M$1.32$3.96100.00%98.2%
deepseek-v4-pro-0813
deepseek/deepseek-v4-pro-0813
baseten/fp4fp41.0M$1.32$3.9699.4%99.4%98.1%
deepseek-v4-pro-0813
deepseek/deepseek-v4-pro-0813
baseten/fp4fp41.0M$1.32$3.9699.4%99.4%98.1%
kimi-k2.7-code
moonshotai/kimi-k2.7-code
baseten/fp4fp4262k$0.950$4.00100.00%100.00%97.6%
kimi-k3
moonshotai/kimi-k3
baseten/fp8fp81.0M$3.00$15.096.5%
kimi-k3
moonshotai/kimi-k3
baseten/fp8fp81.0M$3.00$15.096.5%
glm-5.3
z-ai/glm-5.3
baseten/fp8fp81.0M$2.10$6.60100.00%100.00%93.7%
glm-5.3
z-ai/glm-5.3
baseten/fp8fp81.0M$2.10$6.60100.00%100.00%93.7%
glm-5.3
z-ai/glm-5.3
baseten/fp8fp81.0M$2.10$6.6092.6%
glm-5.3
z-ai/glm-5.3
baseten/fp8fp81.0M$2.10$6.6092.6%
inkling
thinkingmachines/inkling
baseten/fp8fp81.0M$1.00$4.0592.9%89.1%91.2%
inkling
thinkingmachines/inkling
baseten/fp8fp81.0M$1.00$4.0592.9%89.1%91.2%
inkling
thinkingmachines/inkling
baseten/fp8fp81.0M$1.00$4.0592.9%89.1%91.2%
inkling
thinkingmachines/inkling
baseten/fp8fp81.0M$1.00$4.0579.7%86.4%91.0%
inkling
thinkingmachines/inkling
baseten/fp8fp81.0M$1.00$4.0579.7%86.4%91.0%
inkling
thinkingmachines/inkling
baseten/fp8fp81.0M$1.00$4.0579.7%86.4%91.0%
kimi-k2.6
moonshotai/kimi-k2.6
baseten/fp4fp4262k$0.950$4.00

覆盖模型 · 14

元数据与端点观测同步自 OpenRouter 公开 API。GrokCode 不做路由转发;自建测速请用 API 实验室

BaseTen Provider · 模型与 uptime · GrokCode 倍率榜