数据状态
同步自 OpenRouter Providers · 117 家托管商 · source=openrouter · 2026-10-31T00:34:34.775Z
CoreWeave
总部 美国 · 机房 US
22 模型31 端点日可用 99.8%
托管模型22
端点31
日可用率均99.8%
最低输入 $/M$0.030
最大上下文1.0M
托管端点 · 31
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| gpt-oss-120b openai/gpt-oss-120b | coreweave/fp4 | fp4 | 131k | $0.030 | $0.170 | 100.00% | 100.00% | 100.00% | — | — | 是 |
| gpt-oss-120b openai/gpt-oss-120b | coreweave/fp4 | fp4 | 131k | $0.030 | $0.170 | 100.00% | 100.00% | 100.00% | — | — | 是 |
| nemotron-3.5-lightning nvidia/nemotron-3.5-lightning | coreweave/bf16 | bf16 | 262k | $0.070 | $0.200 | 100.00% | 100.00% | 100.00% | — | — | 是 |
| nemotron-3.5-lightning nvidia/nemotron-3.5-lightning | coreweave/bf16 | bf16 | 262k | $0.070 | $0.200 | 100.00% | 100.00% | 100.00% | — | — | 是 |
| qwen3.6-35b-a3b qwen/qwen3.6-35b-a3b | coreweave/fp8 | fp8 | 262k | $0.100 | $0.950 | 100.00% | 100.00% | 100.00% | — | — | 是 |
| gemma-4-26b-a4b-it google/gemma-4-26b-a4b-it | coreweave/bf16 | bf16 | 262k | $0.100 | $0.300 | 100.00% | 100.00% | 100.00% | — | — | 是 |
| gemma-4-26b-a4b-it google/gemma-4-26b-a4b-it | coreweave/bf16 | bf16 | 262k | $0.100 | $0.300 | 100.00% | 100.00% | 100.00% | — | — | 是 |
| gemma-4-31b-it google/gemma-4-31b-it | coreweave/fp4 | fp4 | 262k | $0.100 | $0.340 | 100.00% | 100.00% | 100.00% | — | — | 是 |
| gemma-4-31b-it google/gemma-4-31b-it | coreweave/fp4 | fp4 | 262k | $0.100 | $0.340 | 100.00% | 100.00% | 100.00% | — | — | 是 |
| deepseek-v4-flash-0731 deepseek/deepseek-v4-flash-0731 | coreweave/fp8 | fp8 | 262k | $0.130 | $0.280 | 100.00% | 100.00% | 100.00% | — | — | 是 |
| llama-3.1-8b-instruct meta-llama/llama-3.1-8b-instruct | coreweave/bf16 | bf16 | 131k | $0.220 | $0.220 | 100.00% | 100.00% | 100.00% | — | — | 是 |
| deepseek-chat-v3.1 deepseek/deepseek-chat-v3.1 | coreweave/fp8 | fp8 | 161k | $0.550 | $1.65 | 100.00% | 100.00% | 100.00% | — | — | 是 |
| kimi-k2.7-code moonshotai/kimi-k2.7-code | coreweave/int4 | int4 | 262k | $0.600 | $3.00 | 100.00% | 100.00% | 100.00% | — | — | 是 |
| llama-3.3-70b-instruct meta-llama/llama-3.3-70b-instruct | coreweave/fp16 | fp16 | 128k | $0.710 | $0.710 | 100.00% | 100.00% | 100.00% | — | — | 是 |
| deepseek-v4.1-flash deepseek/deepseek-v4.1-flash | coreweave/fp8 | fp8 | 1.0M | $0.130 | $0.650 | 100.00% | 100.00% | 99.93% | — | — | 是 |
| deepseek-v4.1-flash deepseek/deepseek-v4.1-flash | coreweave/fp8 | fp8 | 1.0M | $0.130 | $0.650 | 100.00% | 100.00% | 99.93% | — | — | 是 |
| glm-5.2 z-ai/glm-5.2 | coreweave/fp4 | fp4 | 1.0M | $0.620 | $2.42 | 100.00% | 100.00% | 99.93% | — | — | 是 |
| deepseek-v4-pro-0813 deepseek/deepseek-v4-pro-0813 | coreweave/fp8 | fp8 | 1.0M | $1.31 | $3.96 | 100.00% | 100.00% | 99.93% | — | — | 是 |
| granite-4.2-8b ibm-granite/granite-4.2-8b | coreweave/bf16 | bf16 | 131k | $0.060 | $0.150 | 100.00% | 100.00% | 99.92% | — | — | 是 |
| glm-5.3-flash z-ai/glm-5.3-flash | coreweave/nvfp4 | nvfp4 | 1.0M | $0.120 | $0.380 | 100.00% | 100.00% | 99.9% | — | — | 是 |
| glm-5.3-flash z-ai/glm-5.3-flash | coreweave/nvfp4 | nvfp4 | 1.0M | $0.120 | $0.380 | 100.00% | 100.00% | 99.9% | — | — | 是 |
| gpt-oss-20b openai/gpt-oss-20b | coreweave/fp4 | fp4 | 131k | $0.030 | $0.130 | 100.00% | 100.00% | 99.7% | — | — | 是 |
| gpt-oss-20b openai/gpt-oss-20b | coreweave/fp4 | fp4 | 131k | $0.030 | $0.130 | 100.00% | 100.00% | 99.7% | — | — | 是 |
| minimax-m3 minimax/minimax-m3 | coreweave/fp4 | fp4 | 262k | $0.230 | $0.960 | 100.00% | 100.00% | 99.6% | — | — | 是 |
| nemotron-3.5-super-vl nvidia/nemotron-3.5-super-vl | coreweave/nvfp4 | nvfp4 | 1.0M | $0.150 | $0.500 | 100.00% | 100.00% | 99.6% | — | — | 是 |
| nemotron-3.5-super-vl nvidia/nemotron-3.5-super-vl | coreweave/nvfp4 | nvfp4 | 1.0M | $0.150 | $0.500 | 100.00% | 100.00% | 99.6% | — | — | 是 |
| beam-1.0-501b-a23b reflection/beam-1.0-501b-a23b | coreweave/fp4 | fp4 | 1.0M | $0.300 | $1.00 | 100.00% | 100.00% | 99.3% | — | — | 是 |
| glm-5.3 z-ai/glm-5.3 | coreweave/fp8 | fp8 | 1.0M | $1.20 | $4.00 | 100.00% | 100.00% | 99.2% | — | — | 是 |
| glm-5.3 z-ai/glm-5.3 | coreweave/fp8 | fp8 | 1.0M | $1.20 | $4.00 | 100.00% | 100.00% | 99.2% | — | — | 是 |
| kimi-k2.6 moonshotai/kimi-k2.6 | coreweave/fp4 | fp4 | 262k | $0.650 | $3.41 | 100.00% | 100.00% | 99.0% | — | — | 是 |
| qwen3.8-27b qwen/qwen3.8-27b | coreweave/fp8 | fp8 | 262k | $0.400 | $3.00 | — | 100.00% | 98.8% | — | — | 是 |
覆盖模型 · 22
gpt-oss-120bnemotron-3.5-lightningqwen3.6-35b-a3bgemma-4-26b-a4b-itgemma-4-31b-itdeepseek-v4-flash-0731llama-3.1-8b-instructdeepseek-chat-v3.1kimi-k2.7-codellama-3.3-70b-instructdeepseek-v4.1-flashglm-5.2deepseek-v4-pro-0813granite-4.2-8bglm-5.3-flashgpt-oss-20bminimax-m3nemotron-3.5-super-vlbeam-1.0-501b-a23bglm-5.3kimi-k2.6qwen3.8-27b
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、会员额度与通用对话 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 ↗