数据状态
同步自 OpenRouter Providers · 109 家托管商 · source=openrouter · 2026-09-18T19:57:40.990Z
Parasail
总部 美国
38 模型52 端点日可用 99.3%
托管模型38
端点52
日可用率均99.3%
最低输入 $/M$0.030
最大上下文1.0M
托管端点 · 52
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| ui-tars-1.5-7b bytedance/ui-tars-1.5-7b | parasail/bf16 | bf16 | 128k | $0.100 | $0.200 | — | 100.00% | 100.00% | — | — | — |
| unslopnemo-12b thedrummer/unslopnemo-12b | parasail/bf16 | bf16 | 1.0M | $0.400 | $0.400 | 100.00% | 100.00% | 100.00% | — | — | — |
| skyfall-36b-v2 thedrummer/skyfall-36b-v2 | parasail/fp8 | fp8 | 33k | $0.550 | $0.800 | — | — | 100.00% | — | — | — |
| qwen2.5-vl-72b-instruct qwen/qwen2.5-vl-72b-instruct | parasail/fp8 | fp8 | 128k | $0.800 | $1.00 | 100.00% | 100.00% | 100.00% | — | — | — |
| qwen3-next-80b-a3b-instruct qwen/qwen3-next-80b-a3b-instruct | parasail/fp8 | fp8 | 262k | $0.100 | $1.10 | 100.00% | 99.92% | 99.99% | — | — | — |
| cydonia-24b-v4.1 thedrummer/cydonia-24b-v4.1 | parasail/bf16 | bf16 | 131k | $0.300 | $0.500 | 100.00% | 100.00% | 99.99% | — | — | — |
| llama-3.2-3b-instruct meta-llama/llama-3.2-3b-instruct | parasail/bf16 | bf16 | 131k | $0.050 | $0.330 | — | 100.00% | 99.98% | — | — | — |
| gpt-oss-120b openai/gpt-oss-120b | parasail/fp4 | fp4 | 131k | $0.100 | $0.750 | 100.00% | 100.00% | 99.98% | — | — | — |
| gpt-oss-120b openai/gpt-oss-120b | parasail/fp4 | fp4 | 131k | $0.100 | $0.750 | 100.00% | 100.00% | 99.98% | — | — | — |
| mythomax-l2-13b gryphe/mythomax-l2-13b | parasail/fp16 | fp16 | 4k | $0.080 | $0.110 | 100.00% | 100.00% | 99.98% | — | — | — |
| qwen3.6-35b-a3b qwen/qwen3.6-35b-a3b | parasail/fp8 | fp8 | 262k | $0.150 | $1.00 | 100.00% | 100.00% | 99.97% | — | — | — |
| qwen3-coder-next qwen/qwen3-coder-next | parasail/bf16 | bf16 | 262k | $0.120 | $0.800 | 100.00% | 100.00% | 99.97% | — | — | — |
| llama-4-maverick meta-llama/llama-4-maverick | parasail/fp8 | fp8 | 524k | $0.350 | $1.00 | 99.5% | 99.9% | 99.95% | — | — | — |
| l3-lunaris-8b sao10k/l3-lunaris-8b | parasail/bf16 | bf16 | 8k | $0.040 | $0.050 | 100.00% | 99.95% | 99.93% | — | — | — |
| qwen3.5-9b qwen/qwen3.5-9b | parasail/bf16 | bf16 | 262k | $0.100 | $0.250 | 100.00% | 99.7% | 99.93% | — | — | — |
| qwen3.5-9b qwen/qwen3.5-9b | parasail/bf16 | bf16 | 262k | $0.100 | $0.250 | 100.00% | 99.7% | 99.93% | — | — | — |
| qwen3-235b-a22b-2507 qwen/qwen3-235b-a22b-2507 | parasail/fp8 | fp8 | 131k | $0.140 | $0.800 | 99.9% | 99.8% | 99.91% | — | — | — |
| glm-5.2 z-ai/glm-5.2 | parasail/fp4 | fp4 | 262k | $1.40 | $4.40 | 100.00% | 99.9% | 99.9% | — | — | — |
| glm-5.2 z-ai/glm-5.2 | parasail/fp4 | fp4 | 262k | $1.40 | $4.40 | 100.00% | 99.9% | 99.9% | — | — | — |
| glm-5.2 z-ai/glm-5.2 | parasail/fp4 | fp4 | 262k | $1.40 | $4.40 | 100.00% | 99.9% | 99.9% | — | — | — |
| kimi-k2.6 moonshotai/kimi-k2.6 | parasail/int4 | int4 | 262k | $0.750 | $3.50 | 100.00% | 99.97% | 99.9% | — | — | — |
| qwen3.5-397b-a17b qwen/qwen3.5-397b-a17b | parasail/fp8 | fp8 | 262k | $0.500 | $3.60 | 97.1% | 97.7% | 99.9% | — | — | — |
| gpt-oss-20b openai/gpt-oss-20b | parasail/fp4 | fp4 | 131k | $0.030 | $0.150 | 99.98% | 99.95% | 99.8% | — | — | — |
| mistral-small-3.2-24b-instruct mistralai/mistral-small-3.2-24b-instruct | parasail/bf16 | bf16 | 131k | $0.090 | $0.300 | 100.00% | 99.8% | 99.8% | — | — | — |
| qwen3.8-27b qwen/qwen3.8-27b | parasail/fp8 | fp8 | 262k | $0.240 | $2.20 | 99.92% | 99.92% | 99.8% | — | — | — |
| qwen3.8-27b qwen/qwen3.8-27b | parasail/fp8 | fp8 | 262k | $0.240 | $2.20 | 99.92% | 99.92% | 99.8% | — | — | — |
| llama-3.3-70b-instruct meta-llama/llama-3.3-70b-instruct | parasail/fp8 | fp8 | 131k | $0.220 | $0.500 | 100.00% | 99.93% | 99.7% | — | — | — |
| deepseek-v4-pro-0813 deepseek/deepseek-v4-pro-0813 | parasail/fp8 | fp8 | 1.0M | $1.32 | $3.96 | 100.00% | 100.00% | 99.7% | — | — | — |
| deepseek-v4-pro-0813 deepseek/deepseek-v4-pro-0813 | parasail/fp8 | fp8 | 1.0M | $1.32 | $3.96 | 100.00% | 100.00% | 99.7% | — | — | — |
| qwen3.5-35b-a3b qwen/qwen3.5-35b-a3b | parasail/fp8 | fp8 | 262k | $0.150 | $1.00 | — | 100.00% | 99.7% | — | — | — |
| deepseek-v4-flash-0731 deepseek/deepseek-v4-flash-0731 | parasail/fp8 | fp8 | 1.0M | $0.140 | $0.280 | 98.6% | 99.2% | 99.7% | — | — | — |
| deepseek-v4-flash-0731 deepseek/deepseek-v4-flash-0731 | parasail/fp8 | fp8 | 1.0M | $0.140 | $0.280 | 98.6% | 99.2% | 99.7% | — | — | — |
| deepseek-v4-flash-0731 deepseek/deepseek-v4-flash-0731 | parasail/fp8 | fp8 | 1.0M | $0.140 | $0.280 | 98.6% | 99.2% | 99.7% | — | — | — |
| deepseek-v4-pro deepseek/deepseek-v4-pro | parasail/fp8 | fp8 | 1.0M | $1.74 | $3.48 | 100.00% | 100.00% | 99.6% | — | — | — |
| deepseek-v4-flash deepseek/deepseek-v4-flash | parasail/fp8 | fp8 | 1.0M | $0.140 | $0.280 | 99.1% | 99.0% | 99.6% | — | — | — |
| kimi-k3 moonshotai/kimi-k3 | parasail/fp4 | fp4 | 1.0M | $3.00 | $15.0 | 99.5% | 98.6% | 99.5% | — | — | — |
| kimi-k3 moonshotai/kimi-k3 | parasail/fp4 | fp4 | 1.0M | $3.00 | $15.0 | 99.5% | 98.6% | 99.5% | — | — | — |
| glm-5.3-flash z-ai/glm-5.3-flash | parasail/fp8 | fp8 | 1.0M | $0.150 | $0.500 | 99.7% | 99.6% | 99.2% | — | — | — |
| glm-5.3-flash z-ai/glm-5.3-flash | parasail/fp8 | fp8 | 1.0M | $0.150 | $0.500 | 99.7% | 99.6% | 99.2% | — | — | — |
| qwen3-vl-8b-instruct qwen/qwen3-vl-8b-instruct | parasail/bf16 | bf16 | 262k | $0.250 | $0.750 | 97.7% | 99.0% | 99.2% | — | — | — |
| qwen3-vl-235b-a22b-instruct qwen/qwen3-vl-235b-a22b-instruct | parasail/fp8 | fp8 | 131k | $0.210 | $1.90 | 99.0% | 99.6% | 99.1% | — | — | — |
| glm-5.3 z-ai/glm-5.3 | parasail/fp8 | fp8 | 1.0M | $1.40 | $4.40 | 98.7% | 99.5% | 99.0% | — | — | — |
| glm-5.3 z-ai/glm-5.3 | parasail/fp8 | fp8 | 1.0M | $1.40 | $4.40 | 98.7% | 99.5% | 99.0% | — | — | — |
| gemma-3-27b-it google/gemma-3-27b-it | parasail/fp8 | fp8 | 131k | $0.080 | $0.450 | 99.2% | 99.1% | 99.0% | — | — | — |
| gemma-4-31b-it google/gemma-4-31b-it | parasail/fp8 | fp8 | 262k | $0.150 | $0.400 | 98.5% | 99.2% | 99.0% | — | — | — |
| gemma-4-31b-it google/gemma-4-31b-it | parasail/fp8 | fp8 | 262k | $0.150 | $0.400 | 98.5% | 99.2% | 99.0% | — | — | — |
| gemma-4-26b-a4b-it google/gemma-4-26b-a4b-it | parasail/bf16 | bf16 | 262k | $0.130 | $0.400 | 99.8% | 99.7% | 97.7% | — | — | — |
| gemma-4-26b-a4b-it google/gemma-4-26b-a4b-it | parasail/bf16 | bf16 | 262k | $0.130 | $0.400 | 99.8% | 99.7% | 97.7% | — | — | — |
| minimax-m3 minimax/minimax-m3 | parasail/fp8 | fp8 | 1.0M | $0.300 | $1.20 | 63.8% | 88.1% | 96.3% | — | — | — |
| minimax-m3 minimax/minimax-m3 | parasail/fp8 | fp8 | 1.0M | $0.300 | $1.20 | 63.8% | 88.1% | 96.3% | — | — | — |
| deepseek-v4.1-flash deepseek/deepseek-v4.1-flash | parasail/fp8 | fp8 | 1.0M | $0.300 | $1.20 | 98.5% | 98.7% | 96.3% | — | — | — |
| mistral-nemo mistralai/mistral-nemo | parasail/fp8 | fp8 | 131k | $0.030 | $0.030 | 88.5% | 94.6% | 92.4% | — | — | — |
覆盖模型 · 38
ui-tars-1.5-7bunslopnemo-12bskyfall-36b-v2qwen2.5-vl-72b-instructqwen3-next-80b-a3b-instructcydonia-24b-v4.1llama-3.2-3b-instructgpt-oss-120bmythomax-l2-13bqwen3.6-35b-a3bqwen3-coder-nextllama-4-maverickl3-lunaris-8bqwen3.5-9bqwen3-235b-a22b-2507glm-5.2kimi-k2.6qwen3.5-397b-a17bgpt-oss-20bmistral-small-3.2-24b-instructqwen3.8-27bllama-3.3-70b-instructdeepseek-v4-pro-0813qwen3.5-35b-a3bdeepseek-v4-flash-0731deepseek-v4-prodeepseek-v4-flashkimi-k3glm-5.3-flashqwen3-vl-8b-instructqwen3-vl-235b-a22b-instructglm-5.3gemma-3-27b-itgemma-4-31b-itgemma-4-26b-a4b-itminimax-m3deepseek-v4.1-flashmistral-nemo
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。
站內推薦
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 ↗