数据状态
同步自 OpenRouter Providers · 101 家托管商 · source=openrouter · 2026-08-01T19:40:52.604Z
DeepInfra
总部 美国
68 模型78 端点日可用 98.5%
托管模型68
端点78
日可用率均98.5%
最低输入 $/M$0.019
最大上下文1.0M
托管端点 · 78
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 | 5m | 30m | 1d | 延迟 | 吞吐 | 缓存 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| phi-4 microsoft/phi-4 | deepinfra/bf16 | bf16 | 16k | $0.070 | $0.140 | 100.00% | 100.00% | 100.00% | — | — | — |
| hermes-3-llama-3.1-70b nousresearch/hermes-3-llama-3.1-70b | deepinfra/fp8 | fp8 | 131k | $0.700 | $0.700 | 100.00% | 100.00% | 100.00% | — | — | — |
| mistral-small-24b-instruct-2501 mistralai/mistral-small-24b-instruct-2501 | deepinfra/fp8 | fp8 | 33k | $0.050 | $0.080 | 100.00% | 100.00% | 100.00% | — | — | — |
| hermes-3-llama-3.1-405b nousresearch/hermes-3-llama-3.1-405b | deepinfra/fp8 | fp8 | 131k | $1.00 | $1.00 | 100.00% | 100.00% | 100.00% | — | — | — |
| gemma-3-12b-it google/gemma-3-12b-it | deepinfra/bf16 | bf16 | 131k | $0.050 | $0.150 | 100.00% | 100.00% | 99.99% | — | — | — |
| glm-5 z-ai/glm-5 | deepinfra/fp4 | fp4 | 203k | $0.600 | $2.08 | 100.00% | 100.00% | 99.99% | — | — | — |
| qwen3-30b-a3b qwen/qwen3-30b-a3b | deepinfra/fp8 | fp8 | 41k | $0.120 | $0.500 | 100.00% | 99.9% | 99.97% | — | — | — |
| gemma-3-4b-it google/gemma-3-4b-it | deepinfra/bf16 | bf16 | 131k | $0.050 | $0.100 | 100.00% | 99.99% | 99.97% | — | — | — |
| deepseek-r1-0528 deepseek/deepseek-r1-0528 | deepinfra/fp4 | fp4 | 164k | $0.500 | $2.15 | 100.00% | 100.00% | 99.97% | — | — | — |
| glm-4.6 z-ai/glm-4.6 | deepinfra/fp4 | fp4 | 203k | $0.500 | $2.00 | 100.00% | 100.00% | 99.96% | — | — | — |
| l3-lunaris-8b sao10k/l3-lunaris-8b | deepinfra/turbo | fp8 | 8k | $0.040 | $0.050 | 100.00% | 99.98% | 99.95% | — | — | — |
| qwen3-32b qwen/qwen3-32b | deepinfra/fp8 | fp8 | 41k | $0.080 | $0.280 | 100.00% | 100.00% | 99.94% | — | — | — |
| glm-4.7 z-ai/glm-4.7 | deepinfra/fp4 | fp4 | 203k | $0.400 | $1.75 | 99.92% | 99.97% | 99.93% | — | — | — |
| gpt-oss-120b openai/gpt-oss-120b | deepinfra/bf16 | bf16 | 131k | $0.037 | $0.170 | 99.98% | 99.99% | 99.92% | — | — | — |
| l3.1-euryale-70b sao10k/l3.1-euryale-70b | deepinfra/fp8 | fp8 | 131k | $0.850 | $0.850 | 100.00% | 100.00% | 99.92% | — | — | — |
| gemma-4-31b-it google/gemma-4-31b-it | deepinfra/turbo | fp4 | 262k | $0.090 | $0.340 | 99.98% | 99.96% | 99.92% | — | — | — |
| gemma-4-31b-it google/gemma-4-31b-it | deepinfra/turbo | fp4 | 262k | $0.090 | $0.340 | 99.98% | 99.96% | 99.92% | — | — | — |
| qwen3-235b-a22b-thinking-2507 qwen/qwen3-235b-a22b-thinking-2507 | deepinfra/fp8 | fp8 | 262k | $0.230 | $2.30 | — | 98.9% | 99.91% | — | — | — |
| gemma-4-26b-a4b-it google/gemma-4-26b-a4b-it | deepinfra/fp8 | fp8 | 262k | $0.070 | $0.340 | 99.97% | 99.96% | 99.91% | — | — | — |
| gemma-4-26b-a4b-it google/gemma-4-26b-a4b-it | deepinfra/fp8 | fp8 | 262k | $0.070 | $0.340 | 99.97% | 99.96% | 99.91% | — | — | — |
| kimi-k2.7-code moonshotai/kimi-k2.7-code | deepinfra/fp4 | fp4 | 262k | $0.740 | $3.50 | 100.00% | 100.00% | 99.90% | — | — | — |
| kimi-k2.5 moonshotai/kimi-k2.5 | deepinfra/fp4 | fp4 | 262k | $0.450 | $2.25 | 100.00% | 100.00% | 99.9% | — | — | — |
| gpt-oss-120b openai/gpt-oss-120b | deepinfra/turbo | bf16 | 131k | $0.150 | $0.600 | 100.00% | 100.00% | 99.9% | — | — | — |
| gpt-oss-20b openai/gpt-oss-20b | deepinfra/bf16 | bf16 | 131k | $0.030 | $0.140 | 99.4% | 99.8% | 99.9% | — | — | — |
| gpt-oss-20b openai/gpt-oss-20b | deepinfra/bf16 | bf16 | 131k | $0.030 | $0.140 | 99.4% | 99.8% | 99.9% | — | — | — |
| mythomax-l2-13b gryphe/mythomax-l2-13b | deepinfra/fp16 | fp16 | 4k | $0.400 | $0.400 | — | 100.00% | 99.9% | — | — | — |
| deepseek-v3.1-terminus deepseek/deepseek-v3.1-terminus | deepinfra/fp4 | fp4 | 164k | $0.270 | $0.950 | 100.00% | 100.00% | 99.9% | — | — | — |
| deepseek-chat-v3.1 deepseek/deepseek-chat-v3.1 | deepinfra/fp4 | fp4 | 164k | $0.250 | $0.950 | 100.00% | 99.98% | 99.9% | — | — | — |
| glm-5.1 z-ai/glm-5.1 | deepinfra/fp4 | fp4 | 203k | $1.05 | $3.50 | 100.00% | 99.7% | 99.9% | — | — | — |
| llama-4-scout meta-llama/llama-4-scout | deepinfra/fp8 | fp8 | 328k | $0.100 | $0.300 | 99.90% | 99.95% | 99.8% | — | — | — |
| qwen3-14b qwen/qwen3-14b | deepinfra/fp8 | fp8 | 41k | $0.120 | $0.240 | 100.00% | 100.00% | 99.8% | — | — | — |
| step-3.7-flash stepfun/step-3.7-flash | deepinfra | — | 262k | $0.200 | $1.15 | — | 100.00% | 99.8% | — | — | — |
| llama-3.1-8b-instruct meta-llama/llama-3.1-8b-instruct | deepinfra/fp8 | fp8 | 131k | $0.020 | $0.040 | 99.94% | 99.94% | 99.8% | — | — | — |
| llama-4-maverick meta-llama/llama-4-maverick | deepinfra/base | fp8 | 1.0M | $0.200 | $0.800 | 99.9% | 99.8% | 99.8% | — | — | — |
| inkling-small thinkingmachines/inkling-small | deepinfra/fp8 | fp8 | 524k | $0.500 | $1.20 | — | 97.0% | 99.8% | — | — | — |
| deepseek-v4-pro deepseek/deepseek-v4-pro | deepinfra/fp4 | fp4 | 1.0M | $1.30 | $2.60 | 100.00% | 99.7% | 99.8% | — | — | — |
| kimi-k2.6 moonshotai/kimi-k2.6 | deepinfra/fp4 | fp4 | 262k | $0.750 | $3.50 | — | 100.00% | 99.7% | — | — | — |
| qwen3.6-35b-a3b qwen/qwen3.6-35b-a3b | deepinfra/fp8 | fp8 | 262k | $0.100 | $0.950 | 100.00% | 100.00% | 99.7% | — | — | — |
| glm-4.7-flash z-ai/glm-4.7-flash | deepinfra/bf16 | bf16 | 203k | $0.060 | $0.400 | 100.00% | 99.8% | 99.6% | — | — | — |
| qwen3-coder qwen/qwen3-coder | deepinfra/turbo | fp4 | 262k | $0.300 | $1.00 | 100.00% | 99.4% | 99.6% | — | — | — |
| qwen-2.5-72b-instruct qwen/qwen-2.5-72b-instruct | deepinfra/fp8 | fp8 | 33k | $0.360 | $0.400 | 100.00% | 100.00% | 99.6% | — | — | — |
| gemma-3-27b-it google/gemma-3-27b-it | deepinfra/fp8 | fp8 | 131k | $0.080 | $0.160 | 100.00% | 99.7% | 99.6% | — | — | — |
| deepseek-v4-flash deepseek/deepseek-v4-flash | deepinfra/fp4 | fp4 | 1.0M | $0.090 | $0.180 | 99.7% | 99.7% | 99.5% | — | — | — |
| qwen3.5-122b-a10b qwen/qwen3.5-122b-a10b | deepinfra/fp4 | fp4 | 262k | $0.290 | $2.40 | 100.00% | 100.00% | 99.4% | — | — | — |
| llama-guard-4-12b meta-llama/llama-guard-4-12b | deepinfra/bf16 | bf16 | 164k | $0.180 | $0.180 | 100.00% | 99.9% | 99.4% | — | — | — |
| qwen3.5-9b qwen/qwen3.5-9b | deepinfra/bf16 | bf16 | 262k | $0.100 | $0.150 | — | — | 99.3% | — | — | — |
| deepseek-v4-flash-0731 deepseek/deepseek-v4-flash-0731 | deepinfra/fp4 | fp4 | 1.0M | $0.090 | $0.180 | 99.5% | 99.5% | 99.3% | — | — | — |
| qwen3-vl-30b-a3b-instruct qwen/qwen3-vl-30b-a3b-instruct | deepinfra/fp8 | fp8 | 262k | $0.150 | $0.600 | 99.7% | 99.8% | 99.3% | — | — | — |
| mistral-small-3.2-24b-instruct mistralai/mistral-small-3.2-24b-instruct | deepinfra/fp8 | fp8 | 128k | $0.075 | $0.200 | 99.7% | 99.7% | 99.3% | — | — | — |
| minimax-m2.7 minimax/minimax-m2.7 | deepinfra/fp8 | fp8 | 197k | $0.250 | $1.00 | 100.00% | 99.90% | 99.0% | — | — | — |
| qwen3-235b-a22b-2507 qwen/qwen3-235b-a22b-2507 | deepinfra/fp8 | fp8 | 262k | $0.090 | $0.550 | 99.6% | 99.7% | 98.8% | — | — | — |
| qwen3.5-27b qwen/qwen3.5-27b | deepinfra/fp8 | fp8 | 262k | $0.260 | $2.60 | 100.00% | 98.3% | 98.8% | — | — | — |
| qwen3.5-397b-a17b qwen/qwen3.5-397b-a17b | deepinfra/fp8 | fp8 | 262k | $0.450 | $3.00 | — | 99.5% | 98.7% | — | — | — |
| glm-5.2 z-ai/glm-5.2 | deepinfra/fp4 | fp4 | 1.0M | $0.750 | $2.40 | 99.93% | 99.9% | 98.6% | — | — | — |
| hy3 tencent/hy3 | deepinfra/fp8 | fp8 | 262k | $0.140 | $0.580 | 100.00% | 99.3% | 98.6% | — | — | — |
| qwen3.5-35b-a3b qwen/qwen3.5-35b-a3b | deepinfra/fp8 | fp8 | 262k | $0.140 | $1.00 | 100.00% | 100.00% | 98.5% | — | — | — |
| qwen3.6-27b qwen/qwen3.6-27b | deepinfra/fp8 | fp8 | 262k | $0.320 | $3.20 | 91.4% | 94.5% | 98.1% | — | — | — |
| qwen3-next-80b-a3b-instruct qwen/qwen3-next-80b-a3b-instruct | deepinfra/fp8 | fp8 | 262k | $0.090 | $1.10 | 100.00% | 99.3% | 97.9% | — | — | — |
| minimax-m3 minimax/minimax-m3 | deepinfra/fp8 | fp8 | 524k | $0.300 | $1.20 | 100.00% | 99.7% | 97.7% | — | — | — |
| nemotron-3-nano-30b-a3b nvidia/nemotron-3-nano-30b-a3b | deepinfra/fp4 | fp4 | 262k | $0.050 | $0.200 | 97.8% | 95.1% | 97.6% | — | — | — |
| nemotron-3-nano-30b-a3b nvidia/nemotron-3-nano-30b-a3b | deepinfra/fp4 | fp4 | 262k | $0.050 | $0.200 | 97.8% | 95.1% | 97.6% | — | — | — |
| mistral-nemo mistralai/mistral-nemo | deepinfra/fp8 | fp8 | 131k | $0.019 | $0.030 | 96.5% | 95.3% | 97.4% | — | — | — |
| mimo-v2.5 xiaomi/mimo-v2.5 | deepinfra/bf16 | bf16 | 262k | $0.400 | $2.00 | 96.7% | 96.1% | 97.4% | — | — | — |
| llama-3.1-70b-instruct meta-llama/llama-3.1-70b-instruct | deepinfra/turbo | fp8 | 131k | $0.400 | $0.400 | 99.9% | 99.8% | 97.3% | — | — | — |
| inkling thinkingmachines/inkling | deepinfra/fp8 | fp8 | 524k | $1.00 | $4.05 | — | — | 97.2% | — | — | — |
| llama-3.3-70b-instruct meta-llama/llama-3.3-70b-instruct | deepinfra/turbo | fp8 | 131k | $0.100 | $0.320 | 97.8% | 96.9% | 96.7% | — | — | — |
| minimax-m2.7 minimax/minimax-m2.7 | deepinfra/turbo | fp8 | 197k | $0.380 | $1.70 | 95.4% | 97.6% | 96.6% | — | — | — |
| deepseek-v3.2 deepseek/deepseek-v3.2 | deepinfra/fp4 | fp4 | 164k | $0.260 | $0.380 | 85.7% | 92.3% | 96.5% | — | — | — |
| gemma-4-31b-it google/gemma-4-31b-it | deepinfra/fp8 | fp8 | 262k | $0.130 | $0.380 | 99.2% | 99.1% | 95.9% | — | — | — |
| gemma-4-31b-it google/gemma-4-31b-it | deepinfra/fp8 | fp8 | 262k | $0.130 | $0.380 | 99.2% | 99.1% | 95.9% | — | — | — |
| nemotron-3-ultra-550b-a55b nvidia/nemotron-3-ultra-550b-a55b | deepinfra/fp4 | fp4 | 262k | $0.500 | $2.20 | 92.1% | 88.7% | 94.7% | — | — | — |
| nemotron-3-ultra-550b-a55b nvidia/nemotron-3-ultra-550b-a55b | deepinfra/fp4 | fp4 | 262k | $0.500 | $2.20 | 92.1% | 88.7% | 94.7% | — | — | — |
| nemotron-3-super-120b-a12b nvidia/nemotron-3-super-120b-a12b | deepinfra/bf16 | bf16 | 262k | $0.085 | $0.400 | 93.8% | 94.7% | 94.6% | — | — | — |
| nemotron-3-super-120b-a12b nvidia/nemotron-3-super-120b-a12b | deepinfra/bf16 | bf16 | 262k | $0.085 | $0.400 | 93.8% | 94.7% | 94.6% | — | — | — |
| deepseek-chat deepseek/deepseek-chat | deepinfra/fp4 | fp4 | 164k | $0.320 | $0.890 | 99.3% | 98.5% | 94.5% | — | — | — |
| mimo-v2.5-pro xiaomi/mimo-v2.5-pro | deepinfra/fp8 | fp8 | 1.0M | $1.00 | $3.00 | 95.1% | 93.3% | 92.1% | — | — | — |
| deepseek-chat-v3-0324 deepseek/deepseek-chat-v3-0324 | deepinfra/fp4 | fp4 | 164k | $0.240 | $0.900 | 99.3% | 89.6% | 89.8% | — | — | — |
| qwen3-vl-235b-a22b-instruct qwen/qwen3-vl-235b-a22b-instruct | deepinfra/fp8 | fp8 | 262k | $0.200 | $0.880 | — | 74.1% | 83.7% | — | — | — |
覆盖模型 · 68
phi-4hermes-3-llama-3.1-70bmistral-small-24b-instruct-2501hermes-3-llama-3.1-405bgemma-3-12b-itglm-5qwen3-30b-a3bgemma-3-4b-itdeepseek-r1-0528glm-4.6l3-lunaris-8bqwen3-32bglm-4.7gpt-oss-120bl3.1-euryale-70bgemma-4-31b-itqwen3-235b-a22b-thinking-2507gemma-4-26b-a4b-itkimi-k2.7-codekimi-k2.5gpt-oss-20bmythomax-l2-13bdeepseek-v3.1-terminusdeepseek-chat-v3.1glm-5.1llama-4-scoutqwen3-14bstep-3.7-flashllama-3.1-8b-instructllama-4-maverickinkling-smalldeepseek-v4-prokimi-k2.6qwen3.6-35b-a3bglm-4.7-flashqwen3-coderqwen-2.5-72b-instructgemma-3-27b-itdeepseek-v4-flashqwen3.5-122b-a10bllama-guard-4-12bqwen3.5-9bdeepseek-v4-flash-0731qwen3-vl-30b-a3b-instructmistral-small-3.2-24b-instructminimax-m2.7qwen3-235b-a22b-2507qwen3.5-27bqwen3.5-397b-a17bglm-5.2hy3qwen3.5-35b-a3bqwen3.6-27bqwen3-next-80b-a3b-instructminimax-m3nemotron-3-nano-30b-a3bmistral-nemomimo-v2.5llama-3.1-70b-instructinkling…另有 8 个
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。
站内推荐
同系工具:Clavue CLI / imux IDE / clavue-2.1
Clavue · CLI 与 Agent 平台
CLI / GUI Agent 运行时、设备登录、会员额度与 OpenAI 兼容 API(api.clavue.com)。开发脚本、CI 与本地工具一条链路。
打开 Clavue ↗imux · 原生 macOS AI IDE
Clavue 平台的原生 IDE:多 Agent 分屏、Ghostty 级终端、Agent Chat、浏览器自动化与 Supervisor——不是又一个 Electron 壳。
了解 imux ↗Clavue 2.1 · 产品级大模型
旗舰模型 clavue-2.1(及 fast / pro / rev):适合复杂推理与长程 Agent 循环。Chat、imux、API 共用会员额度。
查看模型 ↗