数据状态
同步自 OpenRouter Providers · 101 家托管商 · source=openrouter · 2026-08-01T19:40:54.797Z
CoreWeave
总部 美国 · 机房 US
20 模型22 端点日可用 99.5%
托管模型20
端点22
日可用率均99.5%
最低输入 $/M$0.030
最大上下文1.0M
托管端点 · 22
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| granite-4.1-8b ibm-granite/granite-4.1-8b | coreweave/bf16 | bf16 | 131k | $0.050 | $0.100 | 100.00% | 100.00% | 100.00% | — | — | — |
| llama-3.1-8b-instruct meta-llama/llama-3.1-8b-instruct | coreweave/bf16 | bf16 | 128k | $0.220 | $0.220 | 100.00% | 100.00% | 100.00% | — | — | — |
| llama-3.1-70b-instruct meta-llama/llama-3.1-70b-instruct | coreweave/bf16 | bf16 | 128k | $0.800 | $0.800 | 100.00% | 100.00% | 100.00% | — | — | — |
| glm-5.1 z-ai/glm-5.1 | coreweave/fp8 | fp8 | 203k | $1.40 | $4.40 | 100.00% | 100.00% | 99.99% | — | — | — |
| llama-3.3-70b-instruct meta-llama/llama-3.3-70b-instruct | coreweave/fp16 | fp16 | 128k | $0.710 | $0.710 | 100.00% | 100.00% | 99.97% | — | — | — |
| qwen3-30b-a3b-instruct-2507 qwen/qwen3-30b-a3b-instruct-2507 | coreweave/bf16 | bf16 | 262k | $0.100 | $0.300 | 100.00% | 100.00% | 99.96% | — | — | — |
| qwen3.5-35b-a3b qwen/qwen3.5-35b-a3b | coreweave/fp8 | fp8 | 262k | $0.250 | $1.25 | 100.00% | 100.00% | 99.96% | — | — | — |
| deepseek-chat-v3.1 deepseek/deepseek-chat-v3.1 | coreweave/fp8 | fp8 | 161k | $0.550 | $1.65 | 100.00% | 100.00% | 99.9% | — | — | — |
| kimi-k2.7-code moonshotai/kimi-k2.7-code | coreweave/int4 | int4 | 262k | $0.710 | $3.50 | — | 100.00% | 99.9% | — | — | — |
| gemma-4-31b-it google/gemma-4-31b-it | coreweave/bf16 | bf16 | 262k | $0.100 | $0.340 | 99.9% | 99.93% | 99.8% | — | — | — |
| gemma-4-31b-it google/gemma-4-31b-it | coreweave/bf16 | bf16 | 262k | $0.100 | $0.340 | 99.9% | 99.93% | 99.8% | — | — | — |
| qwen3.6-27b qwen/qwen3.6-27b | coreweave/fp8 | fp8 | 262k | $0.600 | $3.60 | — | 100.00% | 99.7% | — | — | — |
| gpt-oss-20b openai/gpt-oss-20b | coreweave/fp4 | fp4 | 131k | $0.030 | $0.130 | 99.97% | 99.91% | 99.6% | — | — | — |
| gpt-oss-20b openai/gpt-oss-20b | coreweave/fp4 | fp4 | 131k | $0.030 | $0.130 | 99.97% | 99.91% | 99.6% | — | — | — |
| minimax-m2.5 minimax/minimax-m2.5 | coreweave/fp8 | fp8 | 197k | $0.300 | $1.20 | 100.00% | 99.7% | 99.5% | — | — | — |
| kimi-k2.6 moonshotai/kimi-k2.6 | coreweave/fp4 | fp4 | 262k | $0.650 | $3.41 | 100.00% | 99.90% | 99.4% | — | — | — |
| qwen3.6-35b-a3b qwen/qwen3.6-35b-a3b | coreweave/fp8 | fp8 | 262k | $0.250 | $1.25 | 100.00% | 99.92% | 99.4% | — | — | — |
| deepseek-v4-pro deepseek/deepseek-v4-pro | coreweave/fp8 | fp8 | 1.0M | $1.74 | $3.48 | — | — | 99.4% | — | — | — |
| glm-5.2 z-ai/glm-5.2 | coreweave/fp4 | fp4 | 262k | $0.760 | $2.42 | 100.00% | 99.92% | 99.2% | — | — | — |
| deepseek-v4-flash deepseek/deepseek-v4-flash | coreweave/fp8 | fp8 | 1.0M | $0.140 | $0.280 | 92.4% | 97.7% | 98.5% | — | — | — |
| gpt-oss-120b openai/gpt-oss-120b | coreweave/fp4 | fp4 | 131k | $0.030 | $0.170 | 99.4% | 98.9% | 98.1% | — | — | — |
| qwen3-coder qwen/qwen3-coder | coreweave/bf16 | bf16 | 262k | $1.00 | $1.50 | — | — | 97.8% | — | — | — |
覆盖模型 · 20
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 ↗