全球 AI 模型价格与规格对比
比较模型公开价格、上下文窗口与能力，按任务和提供商筛选。
模型列表
3566 个模型| 模型 | 提供商 | 输入 / 1M | 输出 / 1M | 上下文 | 最大输出 |
|---|---|---|---|---|---|
| pixtral-12b-2409mistral/pixtral-12b-2409 | Mistral | $0.15 | $0.15 | 128K | 128K |
| ministral-3-8b-2512mistral/ministral-3-8b-2512 | Mistral | $0.15 | $0.15 | 262.1K | 262.1K |
| deepseek/deepseek-r1-distill-qwen-14bnovita/deepseek/deepseek-r1-distill-qwen-14b | novita | $0.15 | $0.15 | 32.8K | 16.4K |
| qwen/qwen3-next-80b-a3b-instructnovita/qwen/qwen3-next-80b-a3b-instruct | novita | $0.15 | $1.50 | 131.1K | 32.8K |
| qwen/qwen3-next-80b-a3b-thinkingnovita/qwen/qwen3-next-80b-a3b-thinking | novita | $0.15 | $1.50 | 131.1K | 32.8K |
| Phi-3-small-8k-instructazure_ai/Phi-3-small-8k-instruct | Azure | $0.15 | $0.60 | 8.2K | 4.1K |
| Phi-3-small-128k-instructazure_ai/Phi-3-small-128k-instruct | Azure | $0.15 | $0.60 | 128K | 4.1K |
| gpt-oss-120bazure_ai/gpt-oss-120b | Azure | $0.15 | $0.60 | 131.1K | 131.1K |
| mistral-nemoazure_ai/mistral-nemo | Azure | $0.15 | $0.15 | 131.1K | 4.1K |
| accounts/fireworks/models/llama4-scout-instruct-basicfireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic | Fireworks AI | $0.15 | $0.60 | 131.1K | 131.1K |
| accounts/fireworks/models/qwen3-coder-30b-a3b-instructfireworks_ai/accounts/fireworks/models/qwen3-coder-30b-a3b-instruct | Fireworks AI | $0.15 | $0.60 | 262.1K | 262.1K |
| accounts/fireworks/models/qwen3-vl-30b-a3b-instructfireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct | Fireworks AI | $0.15 | $0.60 | 262.1K | 262.1K |
| accounts/fireworks/models/qwen3-30b-a3bfireworks_ai/accounts/fireworks/models/qwen3-30b-a3b | Fireworks AI | $0.15 | $0.60 | 131.1K | 131.1K |
| accounts/fireworks/models/gpt-oss-120bfireworks_ai/accounts/fireworks/models/gpt-oss-120b | Fireworks AI | $0.15 | $0.60 | 131.1K | 32.8K |
| accounts/fireworks/models/qwen3-vl-30b-a3b-thinkingfireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-thinking | Fireworks AI | $0.15 | $0.60 | 262.1K | 262.1K |
| qwen3-next-80b-a3b-thinkingdashscope/qwen3-next-80b-a3b-thinking | dashscope | $0.15 | $1.20 | 262.1K | 65.5K |
| qwen3-next-80b-a3b-instructdashscope/qwen3-next-80b-a3b-instruct | dashscope | $0.15 | $1.20 | 262.1K | 65.5K |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-32Bnscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | nscale | $0.15 | $0.15 | — | — |
| nvidia.nemotron-super-3-120bnvidia.nemotron-super-3-120b | bedrock_converse | $0.15 | $0.65 | 256K | 32K |
| google.gemini-2.5-flashoci/google.gemini-2.5-flash | oci | $0.15 | $0.60 | 1M | 65.5K |
| cohere.command-r-08-2024oci/cohere.command-r-08-2024 | oci | $0.15 | $0.15 | 128K | 4K |
| ministral-8b-2512mistral/ministral-8b-2512 | Mistral | $0.15 | $0.15 | 262.1K | 262.1K |
| google/gemma-4-26b-a4b-it-maasvertex_ai/google/gemma-4-26b-a4b-it-maas | $0.15 | $0.60 | 262.1K | 128K | |
| ministral-8b-latestmistral/ministral-8b-latest | Mistral | $0.15 | $0.15 | 262.1K | 262.1K |
| openai-gpt-5-nanosnowflake/openai-gpt-5-nano | snowflake | $0.15 | $0.60 | 5M | 16.4K |
| openai/gpt-oss-120btensormesh/openai/gpt-oss-120b | tensormesh | $0.15 | $0.60 | 131.1K | 131.1K |
| gpt-oss-120bfireworks_ai/gpt-oss-120b | Fireworks AI | $0.15 | $0.60 | 131.1K | 32.8K |
| qwen3.6-35b-a3blibertai/qwen3.6-35b-a3b | libertai | $0.15 | $0.50 | 262.1K | 262.1K |
| qwen3.6-27b-thinkinglibertai/qwen3.6-27b-thinking | libertai | $0.15 | $0.50 | 262.1K | 262.1K |
| qwen3.6-35b-a3b-thinkinglibertai/qwen3.6-35b-a3b-thinking | libertai | $0.15 | $0.50 | 262.1K | 262.1K |
| hermes-3-8b-teelibertai/hermes-3-8b-tee | libertai | $0.15 | $0.60 | 16K | 16K |
| gemma-4-31b-it-thinkinglibertai/gemma-4-31b-it-thinking | libertai | $0.15 | $0.40 | 262.1K | 262.1K |
| qwen3.6-27blibertai/qwen3.6-27b | libertai | $0.15 | $0.50 | 262.1K | 262.1K |
| gemma-4-31b-itlibertai/gemma-4-31b-it | libertai | $0.15 | $0.40 | 262.1K | 262.1K |
| mistralai/voxtral-small-24b-2507scaleway/mistralai/voxtral-small-24b-2507 | scaleway | $0.15 | $0.35 | 32K | 16.4K |
| mistralai/mistral-small-3.2-24b-instruct-2506scaleway/mistralai/mistral-small-3.2-24b-instruct-2506 | scaleway | $0.15 | $0.35 | 128K | 32.8K |
| openai/gpt-oss-120bscaleway/openai/gpt-oss-120b | scaleway | $0.15 | $0.60 | 128K | 32.8K |
| mistral-small-2603mistral/mistral-small-2603 | Mistral | $0.15 | $0.60 | 262.1K | 262.1K |
| cohere/command-rvercel_ai_gateway/cohere/command-r | vercel_ai_gateway | $0.15 | $0.60 | 128K | 4.1K |
| openai/gpt-4o-minivercel_ai_gateway/openai/gpt-4o-mini | vercel_ai_gateway | $0.15 | $0.60 | 128K | 16.4K |
| google/gemini-2.0-flashvercel_ai_gateway/google/gemini-2.0-flash | vercel_ai_gateway | $0.15 | $0.60 | 1M | 8.2K |
| mistral/codestral-embedvercel_ai_gateway/mistral/codestral-embed | vercel_ai_gateway | $0.15 | $0.00 | — | — |
| mistral/pixtral-12bvercel_ai_gateway/mistral/pixtral-12b | vercel_ai_gateway | $0.15 | $0.15 | 128K | 4K |
| meta/llama-3.2-3bvercel_ai_gateway/meta/llama-3.2-3b | vercel_ai_gateway | $0.15 | $0.15 | 128K | 8.2K |
| mistralai/ministral-8b-2512openrouter/mistralai/ministral-8b-2512 | openrouter | $0.15 | $0.15 | 262.1K | 209.7K |
| Qwen/QwQ-32Bdeepinfra/Qwen/QwQ-32B | DeepInfra | $0.15 | $0.40 | 131.1K | 131.1K |
| qwen/qwen3-next-80b-a3b-thinking-maasvertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas | $0.15 | $1.20 | 262.1K | 262.1K | |
| qwen/qwen3-next-80b-a3b-instruct-maasvertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas | $0.15 | $1.20 | 262.1K | 262.1K | |
| openai/gpt-4o-minireplicate/openai/gpt-4o-mini | Replicate | $0.15 | $0.60 | — | — |
| gpt-4o-mini-2024-07-18gpt-4o-mini-2024-07-18 | OpenAI | $0.15 | $0.60 | 128K | 16.4K |
估算调用费用
按公开单价估算。阶梯价、缓存、批量折扣和税费可能改变实际账单。
| 模型 | 提供商 | 预计费用 |
|---|---|---|
| pixtral-12b-2409 | Mistral | $0.0450 |
| ministral-3-8b-2512 | Mistral | $0.0450 |
| deepseek/deepseek-r1-distill-qwen-14b | novita | $0.0450 |
| qwen/qwen3-next-80b-a3b-instruct | novita | $0.1800 |
| qwen/qwen3-next-80b-a3b-thinking | novita | $0.1800 |
| Phi-3-small-8k-instruct | Azure | $0.0900 |
| Phi-3-small-128k-instruct | Azure | $0.0900 |
| gpt-oss-120b | Azure | $0.0900 |
| mistral-nemo | Azure | $0.0450 |
| accounts/fireworks/models/llama4-scout-instruct-basic | Fireworks AI | $0.0900 |
| accounts/fireworks/models/qwen3-coder-30b-a3b-instruct | Fireworks AI | $0.0900 |
| accounts/fireworks/models/qwen3-vl-30b-a3b-instruct | Fireworks AI | $0.0900 |
| accounts/fireworks/models/qwen3-30b-a3b | Fireworks AI | $0.0900 |
| accounts/fireworks/models/gpt-oss-120b | Fireworks AI | $0.0900 |
| accounts/fireworks/models/qwen3-vl-30b-a3b-thinking | Fireworks AI | $0.0900 |
| qwen3-next-80b-a3b-thinking | dashscope | $0.1500 |
| qwen3-next-80b-a3b-instruct | dashscope | $0.1500 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | nscale | $0.0450 |
| nvidia.nemotron-super-3-120b | bedrock_converse | $0.0950 |
| google.gemini-2.5-flash | oci | $0.0900 |
| cohere.command-r-08-2024 | oci | $0.0450 |
| ministral-8b-2512 | Mistral | $0.0450 |
| google/gemma-4-26b-a4b-it-maas | $0.0900 | |
| ministral-8b-latest | Mistral | $0.0450 |
| openai-gpt-5-nano | snowflake | $0.0900 |
| openai/gpt-oss-120b | tensormesh | $0.0900 |
| gpt-oss-120b | Fireworks AI | $0.0900 |
| qwen3.6-35b-a3b | libertai | $0.0800 |
| qwen3.6-27b-thinking | libertai | $0.0800 |
| qwen3.6-35b-a3b-thinking | libertai | $0.0800 |