数据状态

同步自 OpenRouter Providers · 109 家托管商 · source=openrouter · 2026-09-18T18:47:08.584Z

deepinfra

DeepInfra

总部 美国

78 模型112 端点日可用 96.9%
托管模型78
端点112
日可用率均96.9%
最低输入 $/M$0.019
最大上下文1.0M

托管端点 · 112

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
ling-3.0-flash-fin
inclusionai/ling-3.0-flash-fin
deepinfra/fp4fp4262k$0.060$0.180100.00%100.00%100.00%
ling-3.0-flash-fin
inclusionai/ling-3.0-flash-fin
deepinfra/fp4fp4262k$0.060$0.180100.00%100.00%100.00%
phi-4
microsoft/phi-4
deepinfra/bf16bf1616k$0.070$0.140100.00%100.00%100.00%
llama-guard-4-12b
meta-llama/llama-guard-4-12b
deepinfra/bf16bf16164k$0.180$0.180100.00%100.00%100.00%
nemotron-3.5-content-safety
nvidia/nemotron-3.5-content-safety
deepinfra/bf16bf16131k$0.200$0.200100.00%
nemotron-3.5-content-safety
nvidia/nemotron-3.5-content-safety
deepinfra/bf16bf16131k$0.200$0.200100.00%
hermes-3-llama-3.1-70b
nousresearch/hermes-3-llama-3.1-70b
deepinfra/fp8fp8131k$0.700$0.700100.00%100.00%100.00%
ling-3.0-flash-vl
inclusionai/ling-3.0-flash-vl
deepinfra/fp16fp16131k$0.060$0.180100.00%100.00%100.00%
ling-3.0-flash-vl
inclusionai/ling-3.0-flash-vl
deepinfra/fp16fp16131k$0.060$0.180100.00%100.00%100.00%
gemma-3-4b-it
google/gemma-3-4b-it
deepinfra/bf16bf16131k$0.050$0.100100.00%100.00%
mistral-small-24b-instruct-2501
mistralai/mistral-small-24b-instruct-2501
deepinfra/fp8fp833k$0.050$0.080100.00%100.00%99.99%
gpt-oss-120b
openai/gpt-oss-120b
deepinfra/turbobf16131k$0.150$0.600100.00%100.00%99.98%
gpt-oss-120b
openai/gpt-oss-120b
deepinfra/turbobf16131k$0.150$0.600100.00%100.00%99.98%
granite-4.2-8b
ibm-granite/granite-4.2-8b
deepinfra/bf16bf16131k$0.060$0.250100.00%100.00%99.98%
muse-glimmer-30b
meta/muse-glimmer-30b
deepinfra/bf16bf16131k$0.300$1.20100.00%99.97%
muse-glimmer-30b
meta/muse-glimmer-30b
deepinfra/bf16bf16131k$0.300$1.20100.00%99.97%
qwen3.5-35b-a3b
qwen/qwen3.5-35b-a3b
deepinfra/fp8fp8262k$0.140$1.00100.00%99.96%
deepseek-r1-0528
deepseek/deepseek-r1-0528
deepinfra/fp4fp4164k$0.500$2.15100.00%100.00%99.96%
gemma-3-12b-it
google/gemma-3-12b-it
deepinfra/bf16bf16131k$0.050$0.15099.97%99.92%99.96%
hermes-3-llama-3.1-405b
nousresearch/hermes-3-llama-3.1-405b
deepinfra/fp8fp8131k$1.00$1.00100.00%99.96%99.96%
qwen3.5-9b
qwen/qwen3.5-9b
deepinfra/bf16bf16262k$0.100$0.150100.00%99.99%99.95%
qwen3.5-9b
qwen/qwen3.5-9b
deepinfra/bf16bf16262k$0.100$0.150100.00%99.99%99.95%
deepseek-chat-v3.1
deepseek/deepseek-chat-v3.1
deepinfra/fp4fp4164k$0.250$0.950100.00%99.99%99.95%
llama-4-scout
meta-llama/llama-4-scout
deepinfra/fp8fp8328k$0.100$0.30099.8%99.9%99.93%
qwen3.5-122b-a10b
qwen/qwen3.5-122b-a10b
deepinfra/fp4fp4262k$0.290$2.40100.00%99.95%99.93%
llama-3.1-8b-instruct
meta-llama/llama-3.1-8b-instruct
deepinfra/fp8fp8131k$0.020$0.04099.7%99.92%99.93%
l3-lunaris-8b
sao10k/l3-lunaris-8b
deepinfra/turbofp88k$0.040$0.050100.00%99.91%99.93%
kimi-k2.7-code
moonshotai/kimi-k2.7-code
deepinfra/fp4fp4262k$0.680$3.4099.92%
qwen3-30b-a3b
qwen/qwen3-30b-a3b
deepinfra/fp8fp841k$0.120$0.500100.00%100.00%99.92%
gpt-oss-20b
openai/gpt-oss-20b
deepinfra/bf16bf16131k$0.030$0.14099.0%99.4%99.91%
l3.1-euryale-70b
sao10k/l3.1-euryale-70b
deepinfra/fp8fp8131k$0.850$0.850100.00%99.91%
step-3.7-flash
stepfun/step-3.7-flash
deepinfra262k$0.160$0.920100.00%99.9%99.9%
mythomax-l2-13b
gryphe/mythomax-l2-13b
deepinfra/fp16fp164k$0.400$0.400100.00%100.00%99.9%
qwen-2.5-72b-instruct
qwen/qwen-2.5-72b-instruct
deepinfra/fp8fp833k$0.360$0.400100.00%99.96%99.9%
mistral-nemo
mistralai/mistral-nemo
deepinfra/fp8fp8131k$0.019$0.03099.99%99.97%99.9%
mistral-small-3.2-24b-instruct
mistralai/mistral-small-3.2-24b-instruct
deepinfra/fp8fp8128k$0.075$0.200100.00%99.2%99.9%
glm-4.6
z-ai/glm-4.6
deepinfra/fp4fp4203k$0.500$2.00100.00%99.9%99.9%
qwen3.8-2.4t-a95b
qwen/qwen3.8-2.4t-a95b
deepinfra/fp4fp4262k$2.00$6.00100.00%100.00%99.8%
qwen3.8-2.4t-a95b
qwen/qwen3.8-2.4t-a95b
deepinfra/fp4fp4262k$2.00$6.00100.00%100.00%99.8%
nemotron-3.5-lightning
nvidia/nemotron-3.5-lightning
deepinfra/bf16bf16262k$0.080$0.200100.00%99.8%99.8%
nemotron-3.5-lightning
nvidia/nemotron-3.5-lightning
deepinfra/bf16bf16262k$0.080$0.200100.00%99.8%99.8%
nemotron-3-super-120b-a12b
nvidia/nemotron-3-super-120b-a12b
deepinfra/bf16bf16262k$0.085$0.400100.00%100.00%99.8%
nemotron-3-super-120b-a12b
nvidia/nemotron-3-super-120b-a12b
deepinfra/bf16bf16262k$0.085$0.400100.00%100.00%99.8%
deepseek-v4.1-flash
deepseek/deepseek-v4.1-flash
deepinfra/fp8fp81.0M$0.200$0.60099.8%99.8%99.8%
deepseek-v4-flash-0731
deepseek/deepseek-v4-flash-0731
deepinfra/fp8fp81.0M$0.060$0.18099.6%99.6%99.8%
deepseek-v4-flash-0731
deepseek/deepseek-v4-flash-0731
deepinfra/fp8fp81.0M$0.060$0.18099.6%99.6%99.8%
deepseek-v4-flash-0731
deepseek/deepseek-v4-flash-0731
deepinfra/fp8fp81.0M$0.060$0.18099.6%99.6%99.8%
kimi-k2.6
moonshotai/kimi-k2.6
deepinfra/fp4fp4262k$0.750$3.5099.3%99.4%99.7%
llama-4-maverick
meta-llama/llama-4-maverick
deepinfra/basefp81.0M$0.200$0.80099.8%99.91%99.7%
deepseek-v4-flash
deepseek/deepseek-v4-flash
deepinfra/fp8fp81.0M$0.090$0.18099.4%99.6%99.7%
qwen3.6-27b
qwen/qwen3.6-27b
deepinfra/fp8fp8262k$0.320$3.20100.00%100.00%99.6%
qwen3-32b
qwen/qwen3-32b
deepinfra/fp8fp841k$0.080$0.28099.9%99.9%99.5%
qwen3.5-27b
qwen/qwen3.5-27b
deepinfra/fp8fp8262k$0.260$2.60100.00%99.9%99.5%
glm-5.1
z-ai/glm-5.1
deepinfra/fp4fp4203k$1.05$3.5099.2%98.3%99.5%
deepseek-v4-pro
deepseek/deepseek-v4-pro
deepinfra/fp8fp81.0M$1.30$2.60100.00%99.3%99.5%
deepseek-v4-flash-vision-exp
deepseek/deepseek-v4-flash-vision-exp
deepinfra/fp8fp81.0M$0.216$0.64799.4%99.3%99.4%
deepseek-v4-flash-vision-exp
deepseek/deepseek-v4-flash-vision-exp
deepinfra/fp8fp81.0M$0.216$0.64799.4%99.3%99.4%
nemotron-3-nano-30b-a3b
nvidia/nemotron-3-nano-30b-a3b
deepinfra/fp4fp4262k$0.050$0.200100.00%99.7%99.3%
gemma-3-27b-it
google/gemma-3-27b-it
deepinfra/fp8fp8131k$0.080$0.16099.2%99.9%99.3%
deepseek-v3.2
deepseek/deepseek-v3.2
deepinfra/fp4fp4164k$0.260$0.380100.00%99.97%99.2%
deepseek-v4-pro-0813
deepseek/deepseek-v4-pro-0813
deepinfra/fp8fp81.0M$1.30$2.60100.00%98.4%99.2%
deepseek-v4-pro-0813
deepseek/deepseek-v4-pro-0813
deepinfra/fp8fp81.0M$1.30$2.60100.00%98.4%99.2%
inkling-small
thinkingmachines/inkling-small
deepinfra/fp8fp8524k$0.450$1.20100.00%99.2%
inkling-small
thinkingmachines/inkling-small
deepinfra/fp8fp8524k$0.450$1.20100.00%99.2%
gemma-4-31b-it
google/gemma-4-31b-it
deepinfra/turbofp4262k$0.090$0.34098.1%98.5%99.2%
gemma-4-31b-it
google/gemma-4-31b-it
deepinfra/turbofp4262k$0.090$0.34098.1%98.5%99.2%
ling-3.0-flash
inclusionai/ling-3.0-flash
deepinfra/bf16bf16131k$0.060$0.180100.00%99.91%99.1%
hy3
tencent/hy3
deepinfra/fp4fp4262k$0.105$0.43597.3%96.0%99.0%
qwen3-14b
qwen/qwen3-14b
deepinfra/fp8fp841k$0.120$0.24098.6%98.9%99.0%
minimax-m3
minimax/minimax-m3
deepinfra/fp8fp8524k$0.280$1.1099.0%
minimax-m3
minimax/minimax-m3
deepinfra/fp8fp8524k$0.280$1.1099.0%
gemma-4-26b-a4b-it
google/gemma-4-26b-a4b-it
deepinfra/fp8fp8262k$0.070$0.34099.0%99.6%99.0%
gemma-4-26b-a4b-it
google/gemma-4-26b-a4b-it
deepinfra/fp8fp8262k$0.070$0.34099.0%99.6%99.0%
qwen3-next-80b-a3b-instruct
qwen/qwen3-next-80b-a3b-instruct
deepinfra/fp8fp8262k$0.090$1.10100.00%100.00%98.9%
qwen3.5-397b-a17b
qwen/qwen3.5-397b-a17b
deepinfra/fp8fp8262k$0.450$3.00100.00%99.94%98.8%
nemotron-3-ultra-550b-a55b
nvidia/nemotron-3-ultra-550b-a55b
deepinfra/fp4fp4262k$0.500$2.20100.00%98.7%
nemotron-3-ultra-550b-a55b
nvidia/nemotron-3-ultra-550b-a55b
deepinfra/fp4fp4262k$0.500$2.20100.00%98.7%
llama-3.3-70b-instruct
meta-llama/llama-3.3-70b-instruct
deepinfra/turbofp8131k$0.100$0.32099.4%97.7%98.7%
glm-5.2
z-ai/glm-5.2
deepinfra/fp4fp41.0M$0.563$1.8096.7%98.4%98.6%
glm-5.2
z-ai/glm-5.2
deepinfra/fp4fp41.0M$0.563$1.8096.7%98.4%98.6%
glm-5.2
z-ai/glm-5.2
deepinfra/fp4fp41.0M$0.563$1.8096.7%98.4%98.6%
gpt-oss-120b
openai/gpt-oss-120b
deepinfra/bf16bf16131k$0.037$0.170100.00%99.94%98.5%
gpt-oss-120b
openai/gpt-oss-120b
deepinfra/bf16bf16131k$0.037$0.170100.00%99.94%98.5%
gemma-4-31b-it
google/gemma-4-31b-it
deepinfra/fp8fp8262k$0.130$0.38098.3%96.8%98.5%
gemma-4-31b-it
google/gemma-4-31b-it
deepinfra/fp8fp8262k$0.130$0.38098.3%96.8%98.5%
glm-5.3-flash
z-ai/glm-5.3-flash
deepinfra/fp4fp41.0M$0.075$0.25099.3%99.5%98.5%
glm-5.3-flash
z-ai/glm-5.3-flash
deepinfra/fp4fp41.0M$0.075$0.25099.3%99.5%98.5%
kimi-k3
moonshotai/kimi-k3
deepinfra/bf16bf161.0M$2.85$14.3100.00%99.0%98.1%
kimi-k3
moonshotai/kimi-k3
deepinfra/bf16bf161.0M$2.85$14.3100.00%99.0%98.1%
qwen3-235b-a22b-2507
qwen/qwen3-235b-a22b-2507
deepinfra/fp8fp8262k$0.090$0.55096.0%99.2%97.8%
qwen3-vl-235b-a22b-instruct
qwen/qwen3-vl-235b-a22b-instruct
deepinfra/fp8fp8262k$0.200$0.88099.3%98.6%97.7%
deepseek-chat
deepseek/deepseek-chat
deepinfra/fp4fp4164k$0.320$0.89098.8%98.8%97.4%
glm-4.7
z-ai/glm-4.7
deepinfra/fp4fp4203k$0.400$1.7599.9%99.8%97.0%
qwen3-coder
qwen/qwen3-coder
deepinfra/turbofp4262k$0.300$1.0094.1%96.5%
minimax-m2.7
minimax/minimax-m2.7
deepinfra/turbofp8197k$0.380$1.7099.3%96.4%
glm-5.3
z-ai/glm-5.3
deepinfra/fp4fp41.0M$0.900$3.0083.3%88.3%95.6%
glm-5.3
z-ai/glm-5.3
deepinfra/fp4fp41.0M$0.900$3.0083.3%88.3%95.6%
mimo-v2.5
xiaomi/mimo-v2.5
deepinfra/fp8fp8262k$0.133$0.26699.8%99.6%95.1%
qwen3.6-35b-a3b
qwen/qwen3.6-35b-a3b
deepinfra/fp8fp8262k$0.100$0.950100.00%100.00%95.0%
qwen3-vl-30b-a3b-instruct
qwen/qwen3-vl-30b-a3b-instruct
deepinfra/fp8fp8262k$0.150$0.60018.2%92.5%
qwen3.8-27b
qwen/qwen3.8-27b
deepinfra/bf16bf16262k$0.150$1.8897.6%97.2%91.0%
qwen3.8-27b
qwen/qwen3.8-27b
deepinfra/bf16bf16262k$0.150$1.8897.6%97.2%91.0%
deepseek-chat-v3-0324
deepseek/deepseek-chat-v3-0324
deepinfra/fp4fp4164k$0.240$0.900100.00%59.7%91.0%
inkling
thinkingmachines/inkling
deepinfra/fp8fp8524k$0.950$4.0590.8%
inkling
thinkingmachines/inkling
deepinfra/fp8fp8524k$0.950$4.0590.8%
inkling
thinkingmachines/inkling
deepinfra/fp8fp8524k$0.950$4.0590.8%
mimo-v2.5-pro
xiaomi/mimo-v2.5-pro
deepinfra/fp8fp81.0M$0.390$1.17100.00%100.00%90.6%
llama-3.1-70b-instruct
meta-llama/llama-3.1-70b-instruct
deepinfra/turbofp8131k$0.400$0.40094.5%94.7%89.9%
gpt-oss-120b
openai/gpt-oss-120b
deepinfra/fp8fp8131k$0.200$0.950100.00%99.7%59.9%
gpt-oss-120b
openai/gpt-oss-120b
deepinfra/fp8fp8131k$0.200$0.950100.00%99.7%59.9%
gemma-4-31b-it
google/gemma-4-31b-it
deepinfra/ultrafp8131k$0.270$0.760100.00%99.6%48.7%
gemma-4-31b-it
google/gemma-4-31b-it
deepinfra/ultrafp8131k$0.270$0.760100.00%99.6%48.7%

覆盖模型 · 78

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

DeepInfra Provider · 模型与 uptime · GrokCode 倍率榜