Provider
Alibaba (China)
| Model | Input /M | Output /M | Cache read /M | Cache write /M | Context | Status | Updated |
|---|---|---|---|---|---|---|---|
| DeepSeek R1 Distill Llama 8Bdeepseek-r1-distill-llama-8b | $0 | $0 | — | — | 33K | Jan 1, 2025 | |
| DeepSeek R1 Distill Qwen 1.5Bdeepseek-r1-distill-qwen-1-5b | $0 | $0 | — | — | 33K | Jan 1, 2025 | |
| Qwen Flashqwen-flash | $0.022 | $0.216 | — | — | 1M | Jul 28, 2025 | |
| Qwen3.7 Flashqwen3.7-flash | $0.03 | $0.118 | $0.0030 | $0.037 | 1M | Jul 15, 2026 | |
| Qwen3-ASR Flashqwen3-asr-flash | $0.032 | $0.032 | — | — | 53K | Sep 8, 2025 | |
| Qwen Turboqwen-turbo | $0.044 | $0.087 | — | — | 1M | Jul 15, 2025 | |
| Qwen-Omni Turboqwen-omni-turbo | $0.058 | $0.23 | — | — | 33K | Mar 26, 2025 | |
| Qwen3-Omni Flashqwen3-omni-flash | $0.058 | $0.23 | — | — | 66K | Sep 15, 2025 | |
| Tongyi Intent Detect V3tongyi-intent-detect-v3 | $0.058 | $0.144 | — | — | 8K | Jan 1, 2024 | |
| DeepSeek R1 Distill Qwen 7Bdeepseek-r1-distill-qwen-7b | $0.072 | $0.144 | — | — | 33K | Jan 1, 2025 | |
| Qwen Longqwen-long | $0.072 | $0.287 | — | — | 10M | Jan 25, 2025 | |
| Qwen2.5 7B Instructqwen2-5-7b-instruct | $0.072 | $0.144 | — | — | 131K | Sep 1, 2024 | |
| Qwen3 8Bqwen3-8b | $0.072 | $0.287 | — | — | 131K | Apr 1, 2025 | |
| Qwen Doc Turboqwen-doc-turbo | $0.087 | $0.144 | — | — | 131K | Jan 1, 2024 | |
| Qwen2.5-Omni 7Bqwen2-5-omni-7b | $0.087 | $0.345 | — | — | 33K | Dec 1, 2024 | |
| Qwen-MT Turboqwen-mt-turbo | $0.101 | $0.28 | — | — | 16K | Jan 1, 2025 | |
| Qwen3-VL 30B-A3Bqwen3-vl-30b-a3b | $0.108 | $0.431 | — | — | 131K | Apr 1, 2025 | |
| Qwen Plusqwen-plus | $0.115 | $0.287 | — | — | 1M | Sep 11, 2025 | |
| Qwen Plus Characterqwen-plus-character | $0.115 | $0.287 | — | — | 33K | Jan 1, 2024 | |
| Qwen-VL Plusqwen-vl-plus | $0.115 | $0.287 | — | — | 131K | Aug 15, 2025 | |
| DeepSeek V4 Flashdeepseek-v4-flash | $0.14 | $0.28 | $0.0028 | — | 1M | Apr 24, 2026 | |
| Qwen3-VL Plusqwen3-vl-plus | $0.143 | $1.43 | — | — | 262K | Sep 23, 2025 | |
| DeepSeek R1 Distill Qwen 14Bdeepseek-r1-distill-qwen-14b | $0.144 | $0.431 | — | — | 33K | Jan 1, 2025 | |
| Qwen2.5 14B Instructqwen2-5-14b-instruct | $0.144 | $0.431 | — | — | 131K | Sep 1, 2024 | |
| Qwen2.5-Coder 7B Instructqwen2-5-coder-7b-instruct | $0.144 | $0.287 | — | — | 131K | Nov 1, 2024 | |
| Qwen2.5-Math 7B Instructqwen2-5-math-7b-instruct | $0.144 | $0.287 | — | — | 4K | Sep 1, 2024 | |
| Qwen3 14Bqwen3-14b | $0.144 | $0.574 | — | — | 131K | Apr 1, 2025 | |
| Qwen3 Coder Flashqwen3-coder-flash | $0.144 | $0.574 | — | — | 1M | Jul 28, 2025 | |
| Qwen3-Next 80B-A3B Instructqwen3-next-80b-a3b-instruct | $0.144 | $0.574 | — | — | 131K | Sep 1, 2025 | |
| Qwen3-Next 80B-A3B (Thinking)qwen3-next-80b-a3b-thinking | $0.144 | $1.43 | — | — | 131K | Sep 1, 2025 | |
| Qwen3.5 Flashqwen3.5-flash | $0.172 | $1.72 | — | — | 1M | Feb 23, 2026 | |
| Qwen3.6 Flashqwen3.6-flash | $0.188 | $1.13 | — | $0.234 | 1M | Apr 27, 2026 | |
| Qwen3-Coder 30B-A3B Instructqwen3-coder-30b-a3b-instruct | $0.216 | $0.861 | — | — | 262K | Apr 1, 2025 | |
| Qwen-Omni Turbo Realtimeqwen-omni-turbo-realtime | $0.23 | $0.918 | — | — | 33K | May 8, 2025 | |
| Qwen-VL Maxqwen-vl-max | $0.23 | $0.574 | — | — | 131K | Aug 13, 2025 | |
| Qwen3-Omni Flash Realtimeqwen3-omni-flash-realtime | $0.23 | $0.918 | — | — | 66K | Sep 15, 2025 | |
| QwQ Plusqwq-plus | $0.23 | $0.574 | — | — | 131K | Mar 5, 2025 | |
| siliconflow/deepseek-v3-0324siliconflow/deepseek-v3-0324 | $0.25 | $1 | — | — | 164K | Nov 25, 2025 | |
| Qwen-MT Plusqwen-mt-plus | $0.259 | $0.775 | — | — | 16K | Jan 1, 2025 | |
| siliconflow/deepseek-v3.1-terminussiliconflow/deepseek-v3.1-terminus | $0.27 | $1 | — | — | 164K | Nov 25, 2025 | |
| siliconflow/deepseek-v3.2siliconflow/deepseek-v3.2 | $0.27 | $0.42 | — | — | 164K | Dec 3, 2025 | |
| Qwen3-VL 235B-A22Bqwen3-vl-235b-a22b | $0.287 | $1.15 | — | — | 131K | Apr 1, 2025 | |
| DeepSeek R1 Distill Llama 70Bdeepseek-r1-distill-llama-70b | $0.287 | $0.861 | — | — | 33K | Jan 1, 2025 | |
| DeepSeek R1 Distill Qwen 32Bdeepseek-r1-distill-qwen-32b | $0.287 | $0.861 | — | — | 33K | Jan 1, 2025 | |
| DeepSeek V3deepseek-v3 | $0.287 | $1.15 | — | — | 66K | Dec 1, 2024 | |
| DeepSeek V3.2 Expdeepseek-v3-2-exp | $0.287 | $0.431 | — | — | 131K | Jan 1, 2025 | |
| Qwen Math Turboqwen-math-turbo | $0.287 | $0.861 | — | — | 4K | Sep 19, 2024 | |
| Qwen2.5 32B Instructqwen2-5-32b-instruct | $0.287 | $0.861 | — | — | 131K | Sep 1, 2024 | |
| Qwen2.5-Coder 32B Instructqwen2-5-coder-32b-instruct | $0.287 | $0.861 | — | — | 131K | Nov 1, 2024 | |
| Qwen2.5-VL 7B Instructqwen2-5-vl-7b-instruct | $0.287 | $0.717 | — | — | 131K | Sep 1, 2024 | |
| Qwen3 235B-A22Bqwen3-235b-a22b | $0.287 | $1.15 | — | — | 131K | Apr 1, 2025 | |
| Qwen3 32Bqwen3-32b | $0.287 | $1.15 | — | — | 131K | Apr 1, 2025 | |
| QwQ 32Bqwq-32b | $0.287 | $0.861 | — | — | 131K | Dec 1, 2024 | |
| MiniMax-M2.5MiniMax-M2.5 | $0.3 | $1.20 | — | — | 205K | Feb 12, 2026 | |
| MiniMax-M2.7MiniMax/MiniMax-M2.7 | $0.3 | $1.20 | $0.06 | $0.375 | 205K | Mar 18, 2026 | |
| Qwen Maxqwen-max | $0.345 | $1.38 | — | — | 131K | Jan 25, 2025 | |
| Qwen3.5 397B-A17Bqwen3.5-397b-a17b | $0.43 | $2.58 | — | — | 262K | Feb 16, 2026 | |
| DeepSeek V4 Prodeepseek-v4-pro | $0.435 | $0.87 | $0.0036 | — | 1M | Apr 24, 2026 | |
| Qwen3.6 Plusqwen3.6-plus | $0.5 | $3 | $0.05 | $0.625 | 1M | Apr 2, 2026 | |
| Qwen3.7 Plusqwen3.7-plus | $0.5 | $3 | $0.05 | $0.625 | 1M | Jun 2, 2026 | |
| siliconflow/deepseek-r1-0528siliconflow/deepseek-r1-0528 | $0.5 | $2.18 | — | — | 164K | Nov 25, 2025 | |
| Qwen3.5 Plusqwen3.5-plus | $0.573 | $3.44 | — | — | 1M | Feb 16, 2026 | |
| DeepSeek R1deepseek-r1 | $0.574 | $2.29 | — | — | 131K | Jan 1, 2025 | |
| DeepSeek R1 0528deepseek-r1-0528 | $0.574 | $2.29 | — | — | 131K | May 28, 2025 | |
| DeepSeek V3.1deepseek-v3-1 | $0.574 | $1.72 | — | — | 131K | Jan 1, 2025 | |
| Moonshot Kimi K2 Thinkingkimi-k2-thinking | $0.574 | $2.29 | — | — | 262K | Nov 6, 2025 | |
| Moonshot Kimi K2.5kimi-k2.5 | $0.574 | $2.41 | — | — | 262K | Jan 27, 2026 | |
| Moonshot Kimi K2 Instructmoonshot-kimi-k2-instruct | $0.574 | $2.29 | — | — | 131K | Jan 1, 2025 | |
| Qwen Math Plusqwen-math-plus | $0.574 | $1.72 | — | — | 4K | Sep 19, 2024 | |
| Qwen2.5 72B Instructqwen2-5-72b-instruct | $0.574 | $1.72 | — | — | 131K | Sep 1, 2024 | |
| Qwen2.5-Math 72B Instructqwen2-5-math-72b-instruct | $0.574 | $1.72 | — | — | 4K | Sep 1, 2024 | |
| kimi/kimi-k2.5kimi/kimi-k2.5 | $0.6 | $3 | $0.1 | — | 262K | Jan 27, 2026 | |
| Qwen-VL OCRqwen-vl-ocr | $0.717 | $0.717 | — | — | 34K | Apr 13, 2025 | |
| GLM-5glm-5 | $0.86 | $3.15 | — | — | 203K | Feb 11, 2026 | |
| Qwen3-Coder 480B-A35B Instructqwen3-coder-480b-a35b-instruct | $0.861 | $3.44 | — | — | 262K | Apr 1, 2025 | |
| Qwen3 Maxqwen3-max | $0.861 | $3.44 | — | — | 262K | Sep 23, 2025 | |
| GLM-5.1glm-5.1 | $0.87 | $3.48 | $0.17 | — | 203K | Apr 14, 2026 | |
| Moonshot Kimi K2.6kimi-k2.6 | $0.929 | $3.86 | — | — | 262K | Apr 21, 2026 | |
| Qwen3 Coder Plusqwen3-coder-plus | $1 | $5 | — | — | 1.05M | Jul 23, 2025 | |
| GLM-5.2glm-5.2 | $1.10 | $3.85 | $0.275 | $0 | 1M | Jun 13, 2026 | |
| QVQ Maxqvq-max | $1.15 | $4.59 | — | — | 131K | Mar 25, 2025 | |
| Qwen3.6 Max Previewqwen3.6-max-preview | $1.32 | $7.90 | $0.132 | — | 246K | Apr 21, 2026 | |
| Qwen3.8 Maxqwen3.8-max | $1.78 | $5.33 | $0.222 | $2.22 | 1M | Aug 3, 2026 | |
| Qwen2.5-VL 72B Instructqwen2-5-vl-72b-instruct | $2.29 | $6.88 | — | — | 131K | Sep 1, 2024 | |
| Qwen3.7 Maxqwen3.7-max | $2.50 | $7.50 | $0.5 | $3.13 | 1M | May 21, 2026 | |
| Qwen Deep Researchqwen-deep-research | $7.74 | $23.37 | — | — | 1M | Jan 1, 2024 |