返回列表
Modelflare
价格没加载出来，过一会儿再试。
序号 | 模型 | 分组 | 单位 | 输入价格 | 输出价格 | 缓存读取价格 | 缓存写入价格 |
|---|---|---|---|---|---|---|---|
| 1 | codex-auto-review | Price-priority routing for budget-sensitive, retryable development, testing, and flexible workloads. Eligible requests receive 65% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 65% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.075 | 0.45 | 0.0075 | - |
| 2 | codex-auto-review | Enterprise-only OpenAI stability route for authorized production workloads; no platform-level group RPM limit. Actual availability and throughput are subject to the enterprise service agreement and upstream quotas. | CNY / 1M tokens | 1.25 | 7.5 | 0.125 | - |
| 3 | codex-auto-review | openai-first-topup | CNY / 1M tokens | 2.5 | 15 | 0.25 | - |
| 4 | codex-auto-review | Premium OpenAI route for workloads that prioritize continuity and request success, billed at 13% of official list pricing. Eligible requests receive 85% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 85% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.325 | 1.95 | 0.0325 | - |
| 5 | codex-auto-review | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. Eligible requests receive 75% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 75% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.2 | 1.2 | 0.02 | - |
| 6 | gpt-5.5 | Price-priority routing for budget-sensitive, retryable development, testing, and flexible workloads. Eligible requests receive 65% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 65% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.15 | 0.9 | 0.015 | - |
| 7 | gpt-5.5 | Enterprise-only OpenAI stability route for authorized production workloads; no platform-level group RPM limit. Actual availability and throughput are subject to the enterprise service agreement and upstream quotas. | CNY / 1M tokens | 2.5 | 15 | 0.25 | - |
| 8 | gpt-5.5 | openai-first-topup | CNY / 1M tokens | 5 | 30 | 0.5 | - |
| 9 | gpt-5.5 | Premium OpenAI route for workloads that prioritize continuity and request success, billed at 13% of official list pricing. Eligible requests receive 85% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 85% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.65 | 3.9 | 0.065 | - |
| 10 | gpt-5.5 | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. Eligible requests receive 75% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 75% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.4 | 2.4 | 0.04 | - |
| 11 | gpt-5.6-sol | Price-priority routing for budget-sensitive, retryable development, testing, and flexible workloads. Eligible requests receive 65% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 65% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.15 | 0.9 | 0.015 | 0.1875 |
| 12 | gpt-5.6-sol | Enterprise-only OpenAI stability route for authorized production workloads; no platform-level group RPM limit. Actual availability and throughput are subject to the enterprise service agreement and upstream quotas. | CNY / 1M tokens | 2.5 | 15 | 0.25 | 3.125 |
| 13 | gpt-5.6-sol | openai-first-topup | CNY / 1M tokens | 5 | 30 | 0.5 | 6.25 |
| 14 | gpt-5.6-sol | Premium OpenAI route for workloads that prioritize continuity and request success, billed at 13% of official list pricing. Eligible requests receive 85% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 85% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.65 | 3.9 | 0.065 | 0.8125 |
| 15 | gpt-5.6-sol | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. Eligible requests receive 75% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 75% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.4 | 2.4 | 0.04 | 0.5 |
| 16 | gpt-5.6-terra | Price-priority routing for budget-sensitive, retryable development, testing, and flexible workloads. Eligible requests receive 65% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 65% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.06 | 0.36 | 0.006 | 0.075 |
| 17 | gpt-5.6-terra | Enterprise-only OpenAI stability route for authorized production workloads; no platform-level group RPM limit. Actual availability and throughput are subject to the enterprise service agreement and upstream quotas. | CNY / 1M tokens | 1 | 6 | 0.1 | 1.25 |
| 18 | gpt-5.6-terra | openai-first-topup | CNY / 1M tokens | 2 | 12 | 0.2 | 2.5 |
| 19 | gpt-5.6-terra | Premium OpenAI route for workloads that prioritize continuity and request success, billed at 13% of official list pricing. Eligible requests receive 85% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 85% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.26 | 1.56 | 0.026 | 0.325 |
| 20 | gpt-5.6-terra | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. Eligible requests receive 75% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 75% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.16 | 0.96 | 0.016 | 0.2 |
| 21 | gpt-6.1-sol | Price-priority routing for budget-sensitive, retryable development, testing, and flexible workloads. Eligible requests receive 65% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 65% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.06 | 0.3 | 0.003 | 0.075 |
| 22 | gpt-6.1-sol | Enterprise-only OpenAI stability route for authorized production workloads; no platform-level group RPM limit. Actual availability and throughput are subject to the enterprise service agreement and upstream quotas. | CNY / 1M tokens | 1 | 5 | 0.05 | 1.25 |
| 23 | gpt-6.1-sol | openai-first-topup | CNY / 1M tokens | 2 | 10 | 0.1 | 2.5 |
| 24 | gpt-6.1-sol | Premium OpenAI route for workloads that prioritize continuity and request success, billed at 13% of official list pricing. Eligible requests receive 85% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 85% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.26 | 1.3 | 0.013 | 0.325 |
| 25 | gpt-6.1-sol | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. Eligible requests receive 75% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 75% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.16 | 0.8 | 0.008 | 0.2 |
| 26 | gpt-6.1-terra | Price-priority routing for budget-sensitive, retryable development, testing, and flexible workloads. Eligible requests receive 65% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 65% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.03 | 0.15 | 0.0015 | 0.0375 |
| 27 | gpt-6.1-terra | Enterprise-only OpenAI stability route for authorized production workloads; no platform-level group RPM limit. Actual availability and throughput are subject to the enterprise service agreement and upstream quotas. | CNY / 1M tokens | 0.5 | 2.5 | 0.025 | 0.625 |
| 28 | gpt-6.1-terra | openai-first-topup | CNY / 1M tokens | 1 | 5 | 0.05 | 1.25 |
| 29 | gpt-6.1-terra | Premium OpenAI route for workloads that prioritize continuity and request success, billed at 13% of official list pricing. Eligible requests receive 85% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 85% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.13 | 0.65 | 0.0065 | 0.1625 |
| 30 | gpt-6.1-terra | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. Eligible requests receive 75% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 75% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.08 | 0.4 | 0.004 | 0.1 |
| 31 | gpt-6-astra | Price-priority routing for budget-sensitive, retryable development, testing, and flexible workloads. Eligible requests receive 65% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 65% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.3 | 1.5 | 0.03 | 0.375 |
| 32 | gpt-6-astra | Enterprise-only OpenAI stability route for authorized production workloads; no platform-level group RPM limit. Actual availability and throughput are subject to the enterprise service agreement and upstream quotas. | CNY / 1M tokens | 5 | 25 | 0.5 | 6.25 |
| 33 | gpt-6-astra | openai-first-topup | CNY / 1M tokens | 10 | 50 | 1 | 12.5 |
| 34 | gpt-6-astra | Premium OpenAI route for workloads that prioritize continuity and request success, billed at 13% of official list pricing. Eligible requests receive 85% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 85% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 1.3 | 6.5 | 0.13 | 1.625 |
| 35 | gpt-6-astra | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. Eligible requests receive 75% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 75% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.8 | 4 | 0.08 | 1 |
| 36 | gpt-6-luna | Price-priority routing for budget-sensitive, retryable development, testing, and flexible workloads. Eligible requests receive 65% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 65% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.0075 | 0.0375 | 0.0008 | 0.0094 |
| 37 | gpt-6-luna | Enterprise-only OpenAI stability route for authorized production workloads; no platform-level group RPM limit. Actual availability and throughput are subject to the enterprise service agreement and upstream quotas. | CNY / 1M tokens | 0.125 | 0.625 | 0.0125 | 0.1563 |
| 38 | gpt-6-luna | openai-first-topup | CNY / 1M tokens | 0.25 | 1.25 | 0.025 | 0.3125 |
| 39 | gpt-6-luna | Premium OpenAI route for workloads that prioritize continuity and request success, billed at 13% of official list pricing. Eligible requests receive 85% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 85% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.0325 | 0.1625 | 0.0033 | 0.0406 |
| 40 | gpt-6-luna | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. Eligible requests receive 75% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 75% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.02 | 0.1 | 0.002 | 0.025 |
| 41 | gpt-6-sol | Price-priority routing for budget-sensitive, retryable development, testing, and flexible workloads. Eligible requests receive 65% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 65% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.06 | 0.3 | 0.006 | 0.075 |
| 42 | gpt-6-sol | Enterprise-only OpenAI stability route for authorized production workloads; no platform-level group RPM limit. Actual availability and throughput are subject to the enterprise service agreement and upstream quotas. | CNY / 1M tokens | 1 | 5 | 0.1 | 1.25 |
| 43 | gpt-6-sol | openai-first-topup | CNY / 1M tokens | 2 | 10 | 0.2 | 2.5 |
| 44 | gpt-6-sol | Premium OpenAI route for workloads that prioritize continuity and request success, billed at 13% of official list pricing. Eligible requests receive 85% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 85% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.26 | 1.3 | 0.026 | 0.325 |
| 45 | gpt-6-sol | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. Eligible requests receive 75% daily cache hit-rate protection, with shortfalls compensated. Eligible requests receive 75% daily cache hit-rate protection, with shortfalls compensated. | CNY / 1M tokens | 0.16 | 0.8 | 0.016 | 0.2 |
| 46 | gpt-image-2 | Image and video generation route. | CNY / 1M tokens | 3.77 | 22.62 | 0.9425 | - |
| 47 | gpt-image-2.5-flare | Image and video generation route. | CNY / 1M tokens | 5.33 | 31.98 | 1.3325 | - |
| 48 | gpt-image-2.5-sunburst | Image and video generation route. | CNY / 1M tokens | 5.33 | 31.98 | 1.3325 | - |
| 49 | claude-fable-5 | Price-priority routing for budget-sensitive, retryable development, testing, and flexible workloads. | CNY / 1M tokens | 2.5 | 12.5 | 0.25 | 3.125 |
| 50 | claude-fable-5 | claude-first-topup | CNY / 1M tokens | 10 | 50 | 1 | 12.5 |
| 51 | claude-fable-5 | Premium Claude route for workloads that prioritize continuity and request success, billed at 50% of official list pricing. | CNY / 1M tokens | 5 | 25 | 0.5 | 6.25 |
| 52 | claude-fable-5 | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. | CNY / 1M tokens | 3.15 | 15.75 | 0.315 | 3.9375 |
| 53 | claude-fable-5-1 | Price-priority routing for budget-sensitive, retryable development, testing, and flexible workloads. | CNY / 1M tokens | 2.5 | 12.5 | 0.0625 | 3.125 |
| 54 | claude-fable-5-1 | claude-first-topup | CNY / 1M tokens | 10 | 50 | 0.25 | 12.5 |
| 55 | claude-fable-5-1 | Premium Claude route for workloads that prioritize continuity and request success, billed at 50% of official list pricing. | CNY / 1M tokens | 5 | 25 | 0.125 | 6.25 |
| 56 | claude-fable-5-1 | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. | CNY / 1M tokens | 3.15 | 15.75 | 0.0788 | 3.9375 |
| 57 | claude-haiku-4-5 | Price-priority routing for budget-sensitive, retryable development, testing, and flexible workloads. | CNY / 1M tokens | 0.25 | 1.25 | 0.025 | 0.3125 |
| 58 | claude-haiku-4-5 | claude-first-topup | CNY / 1M tokens | 1 | 5 | 0.1 | 1.25 |
| 59 | claude-haiku-4-5 | Premium Claude route for workloads that prioritize continuity and request success, billed at 50% of official list pricing. | CNY / 1M tokens | 0.5 | 2.5 | 0.05 | 0.625 |
| 60 | claude-haiku-4-5 | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. | CNY / 1M tokens | 0.315 | 1.575 | 0.0315 | 0.3938 |
| 61 | claude-haiku-5-5 | Price-priority routing for budget-sensitive, retryable development, testing, and flexible workloads. | CNY / 1M tokens | 0.025 | 0.125 | 0.0025 | 0.0313 |
| 62 | claude-haiku-5-5 | Premium Claude route for workloads that prioritize continuity and request success, billed at 50% of official list pricing. | CNY / 1M tokens | 0.05 | 0.25 | 0.005 | 0.0625 |
| 63 | claude-haiku-5-5 | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. | CNY / 1M tokens | 0.0315 | 0.1575 | 0.0032 | 0.0394 |
| 64 | claude-opus-4-8 | Price-priority routing for budget-sensitive, retryable development, testing, and flexible workloads. | CNY / 1M tokens | 1.25 | 6.25 | 0.125 | 1.5625 |
| 65 | claude-opus-4-8 | claude-first-topup | CNY / 1M tokens | 5 | 25 | 0.5 | 6.25 |
| 66 | claude-opus-4-8 | Premium Claude route for workloads that prioritize continuity and request success, billed at 50% of official list pricing. | CNY / 1M tokens | 2.5 | 12.5 | 0.25 | 3.125 |
| 67 | claude-opus-4-8 | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. | CNY / 1M tokens | 1.575 | 7.875 | 0.1575 | 1.9688 |
| 68 | claude-opus-5 | Price-priority routing for budget-sensitive, retryable development, testing, and flexible workloads. | CNY / 1M tokens | 1.25 | 6.25 | 0.125 | 1.5625 |
| 69 | claude-opus-5 | claude-first-topup | CNY / 1M tokens | 5 | 25 | 0.5 | 6.25 |
| 70 | claude-opus-5 | Premium Claude route for workloads that prioritize continuity and request success, billed at 50% of official list pricing. | CNY / 1M tokens | 2.5 | 12.5 | 0.25 | 3.125 |
| 71 | claude-opus-5 | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. | CNY / 1M tokens | 1.575 | 7.875 | 0.1575 | 1.9688 |
| 72 | claude-opus-5-5 | Price-priority routing for budget-sensitive, retryable development, testing, and flexible workloads. | CNY / 1M tokens | 1 | 5 | 0.05 | 1.25 |
| 73 | claude-opus-5-5 | claude-first-topup | CNY / 1M tokens | 4 | 20 | 0.2 | 5 |
| 74 | claude-opus-5-5 | Premium Claude route for workloads that prioritize continuity and request success, billed at 50% of official list pricing. | CNY / 1M tokens | 2 | 10 | 0.1 | 2.5 |
| 75 | claude-opus-5-5 | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. | CNY / 1M tokens | 1.26 | 6.3 | 0.063 | 1.575 |
| 76 | claude-sonnet-5 | Price-priority routing for budget-sensitive, retryable development, testing, and flexible workloads. | CNY / 1M tokens | 0.5 | 2.5 | 0.05 | 0.625 |
| 77 | claude-sonnet-5 | claude-first-topup | CNY / 1M tokens | 2 | 10 | 0.2 | 2.5 |
| 78 | claude-sonnet-5 | Premium Claude route for workloads that prioritize continuity and request success, billed at 50% of official list pricing. | CNY / 1M tokens | 1 | 5 | 0.1 | 1.25 |
| 79 | claude-sonnet-5 | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. | CNY / 1M tokens | 0.63 | 3.15 | 0.063 | 0.7875 |
| 80 | claude-sonnet-5-5 | Price-priority routing for budget-sensitive, retryable development, testing, and flexible workloads. | CNY / 1M tokens | 0.5 | 2.5 | 0.05 | 0.625 |
| 81 | claude-sonnet-5-5 | claude-first-topup | CNY / 1M tokens | 2 | 10 | 0.2 | 2.5 |
| 82 | claude-sonnet-5-5 | Premium Claude route for workloads that prioritize continuity and request success, billed at 50% of official list pricing. | CNY / 1M tokens | 1 | 5 | 0.1 | 1.25 |
| 83 | claude-sonnet-5-5 | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. | CNY / 1M tokens | 0.63 | 3.15 | 0.063 | 0.7875 |
| 84 | gemini-2.5-flash-image | Image and video generation route. | CNY / 次 | 0.033 | - | - | - |
| 85 | gemini-3.1-flash-image | Image and video generation route. | CNY / 1M tokens | 0.4225 | 50.7 | - | - |
| 86 | gemini-3.1-flash-lite | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. | CNY / 1M tokens | 0.0375 | 0.225 | 0.0038 | 0.15 |
| 87 | gemini-3.1-flash-lite-image | Image and video generation route. | CNY / 1M tokens | 0.2113 | 25.35 | - | - |
| 88 | gemini-3.1-pro-preview | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. | CNY / 1M tokens | 0.3 | 1.8 | 0.03 | 0.675 |
| 89 | gemini-3.5-flash | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. | CNY / 1M tokens | 0.225 | 1.35 | 0.0225 | 0.15 |
| 90 | gemini-3.5-flash-lite | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. | CNY / 1M tokens | 0.045 | 0.375 | 0.0045 | 0.15 |
| 91 | gemini-3.6-flash | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. | CNY / 1M tokens | 0.225 | 1.125 | 0.0225 | 0.15 |
| 92 | gemini-3.7-flash | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. | CNY / 1M tokens | 0.225 | 1.125 | 0.0225 | 0.15 |
| 93 | gemini-3.8-flash | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. | CNY / 1M tokens | 0.225 | 1.125 | 0.0225 | 0.15 |
| 94 | gemini-3.8-flash-high | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. | CNY / 1M tokens | 0.225 | 1.125 | 0.0225 | 0.15 |
| 95 | gemini-3-pro-image | Image and video generation route. | CNY / 1M tokens | 1.69 | 101.4 | - | - |
| 96 | gemini-4-argon | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. | CNY / 1M tokens | 0.6 | 3 | 0.03 | - |
| 97 | qwen3.8-max | Official Qwen access on a high-stability channel, suited to everyday development, long-term projects, and production. | CNY / 1M tokens | 1.4458 | 4.3373 | 0.1807 | 1.8072 |
| 98 | grok-4.5 | Price-priority routing for budget-sensitive, retryable development, testing, and flexible workloads. | CNY / 1M tokens | 0.02 | 0.06 | 0.005 | - |
| 99 | grok-4.5 | The go-to choice for individual developers who prioritize stability, ideal for everyday development, long-term projects, and production applications. | CNY / 1M tokens | 0.22 | 0.66 | 0.055 | - |
| 100 | grok-4.6 | Price-priority routing for budget-sensitive, retryable development, testing, and flexible workloads. | CNY / 1M tokens | 0.02 | 0.06 | 0.005 | - |