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
3564 个模型| 模型 | 提供商 | 输入 / 1M | 输出 / 1M | 上下文 | 最大输出 |
|---|---|---|---|---|---|
| google/gemini-2.0-flash-001openrouter/google/gemini-2.0-flash-001 | openrouter | $0.10 | $0.40 | 1M | 8.2K |
| mistralai/ministral-3b-2512openrouter/mistralai/ministral-3b-2512 | openrouter | $0.10 | $0.10 | 131.1K | 104.9K |
| bytedance/ui-tars-1.5-7bopenrouter/bytedance/ui-tars-1.5-7b | openrouter | $0.10 | $0.20 | 128K | 2K |
| openai/gpt-4.1-nanoopenrouter/openai/gpt-4.1-nano | openrouter | $0.10 | $0.40 | 1M | 32.8K |
| meta-llama/Llama-3.3-70B-Instruct-Turbodeepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo | DeepInfra | $0.10 | $0.32 | 131.1K | 131.1K |
| nvidia/Llama-3.3-Nemotron-Super-49B-v1.5deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5 | DeepInfra | $0.10 | $0.40 | 131.1K | 131.1K |
| google/gemini-2.0-flash-001deepinfra/google/gemini-2.0-flash-001 | DeepInfra | $0.10 | $0.40 | 1M | 1M |
| meta-llama/Llama-4-Scout-17B-16E-Instructdeepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct | DeepInfra | $0.10 | $0.30 | 327.7K | 327.7K |
| meta/llama-2-13b-chatreplicate/meta/llama-2-13b-chat | Replicate | $0.10 | $0.50 | 4.1K | 4.1K |
| openai/gpt-4.1-nanoreplicate/openai/gpt-4.1-nano | Replicate | $0.10 | $0.40 | — | — |
| meta/llama-2-13breplicate/meta/llama-2-13b | Replicate | $0.10 | $0.50 | 4.1K | 4.1K |
| gpt-4.1-nano-2025-04-14gpt-4.1-nano-2025-04-14 | OpenAI | $0.10 | $0.40 | 1M | 32.8K |
| gpt-4.1-nanogpt-4.1-nano | OpenAI | $0.10 | $0.40 | 1M | 32.8K |
| mistralai/Mistral-Small-24B-Instruct-2501together_ai/mistralai/Mistral-Small-24B-Instruct-2501 | together_ai | $0.10 | $0.30 | 32.8K | — |
| together-ai-up-to-4btogether-ai-up-to-4b | together_ai | $0.10 | $0.10 | — | — |
| gemini-2.5-flash-lite-preview-06-17gemini-2.5-flash-lite-preview-06-17 | $0.10 | $0.40 | 1M | 65.5K | |
| gemini-2.5-flash-lite-preview-09-2025gemini-2.5-flash-lite-preview-09-2025 | $0.10 | $0.40 | 1M | 65.5K | |
| gemini-2.5-flash-litegemini-2.5-flash-lite | $0.10 | $0.40 | 1M | 65.5K | |
| gpt-4.1-nano-2025-04-14azure/gpt-4.1-nano-2025-04-14 | Azure | $0.10 | $0.40 | 1M | 32.8K |
| gpt-4.1-nanoazure/gpt-4.1-nano | Azure | $0.10 | $0.40 | 1M | 32.8K |
| Meta-Llama-3.1-8B-Instructsambanova/Meta-Llama-3.1-8B-Instruct | sambanova | $0.10 | $0.20 | 16.4K | 16.4K |
| mistral-small-2503@001vertex_ai/mistral-small-2503@001 | $0.10 | $0.30 | 32K | 8.2K | |
| mistral-small-2503vertex_ai/mistral-small-2503 | $0.10 | $0.30 | 128K | 128K | |
| nvidia/Llama-3.3-Nemotron-Super-49B-v1nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1 | nebius | $0.10 | $0.40 | 131.1K | 131.1K |
| Qwen/Qwen3-32Bnebius/Qwen/Qwen3-32B | nebius | $0.10 | $0.30 | 41K | 41K |
| Qwen/Qwen3-30B-A3Bnebius/Qwen/Qwen3-30B-A3B | nebius | $0.10 | $0.30 | 32.8K | 32.8K |
| google/gemma-3-27b-itnebius/google/gemma-3-27b-it | nebius | $0.10 | $0.30 | 110K | 110K |
| gemini-2.5-flash-litegemini/gemini-2.5-flash-lite | $0.10 | $0.40 | 1M | 65.5K | |
| gemini-2.0-flash-001gemini/gemini-2.0-flash-001 | $0.10 | $0.40 | 1M | 8.2K | |
| gemini-2.5-flash-lite-preview-09-2025gemini/gemini-2.5-flash-lite-preview-09-2025 | $0.10 | $0.40 | 1M | 65.5K | |
| gemini-2.0-flashgemini/gemini-2.0-flash | $0.10 | $0.40 | 1M | 8.2K | |
| gemini-2.5-flash-lite-preview-06-17gemini/gemini-2.5-flash-lite-preview-06-17 | $0.10 | $0.40 | 1M | 65.5K | |
| mistral.voxtral-small-24b-2507mistral.voxtral-small-24b-2507 | bedrock_converse | $0.10 | $0.30 | 32.8K | 8.2K |
| mistral.ministral-3-3b-instructmistral.ministral-3-3b-instruct | bedrock_converse | $0.10 | $0.10 | 128K | 8K |
| deepseek-r1-8bllamagate/deepseek-r1-8b | llamagate | $0.10 | $0.20 | 65.5K | 16.4K |
| mistral-7b-v0.3llamagate/mistral-7b-v0.3 | llamagate | $0.10 | $0.15 | 32.8K | 8.2K |
| llava-7bllamagate/llava-7b | llamagate | $0.10 | $0.20 | 4.1K | 2K |
| llama3.1-8bcerebras/llama3.1-8b | Cerebras | $0.10 | $0.10 | 128K | 128K |
| meta-llama-3.1-8b-instructfriendliai/meta-llama-3.1-8b-instruct | FriendliAI | $0.10 | $0.10 | 8.2K | 8.2K |
| arize-ai/qwen-2-1.5b-instructtogether_ai/arize-ai/qwen-2-1.5b-instruct | together_ai | $0.10 | $0.10 | 32.8K | 32.8K |
| Qwen/Qwen3.6-35B-A3Bdeepinfra/Qwen/Qwen3.6-35B-A3B | DeepInfra | $0.10 | $0.95 | 262.1K | — |
| Qwen/Qwen3.5-9Bdeepinfra/Qwen/Qwen3.5-9B | DeepInfra | $0.10 | $0.15 | 262.1K | — |
| ByteDance/Seed-2.0-minideepinfra/ByteDance/Seed-2.0-mini | DeepInfra | $0.10 | $0.40 | 256K | — |
| voxtral-small-latestmistral/voxtral-small-latest | Mistral | $0.10 | $0.40 | 32.8K | 32.8K |
| voxtral-small-2507mistral/voxtral-small-2507 | Mistral | $0.10 | $0.40 | 32.8K | 32.8K |
| ministral-3b-2512mistral/ministral-3b-2512 | Mistral | $0.10 | $0.10 | 131.1K | 131.1K |
| ministral-3b-latestmistral/ministral-3b-latest | Mistral | $0.10 | $0.10 | 131.1K | 131.1K |
| muse-spark-1.3-contributormeta/muse-spark-1.3-contributor | meta | $0.10 | $0.20 | 1M | 131.1K |
| qwen/qwen3.5-9bopenrouter/qwen/qwen3.5-9b | openrouter | $0.10 | $0.15 | 262.1K | 32.8K |
| qwen/qwen-2.5-7b-instructopenrouter/qwen/qwen-2.5-7b-instruct | openrouter | $0.10 | $0.20 | 32.8K | 29.5K |
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 |
|---|---|---|
| google/gemini-2.0-flash-001 | openrouter | $0.0600 |
| mistralai/ministral-3b-2512 | openrouter | $0.0300 |
| bytedance/ui-tars-1.5-7b | openrouter | $0.0400 |
| openai/gpt-4.1-nano | openrouter | $0.0600 |
| meta-llama/Llama-3.3-70B-Instruct-Turbo | DeepInfra | $0.0520 |
| nvidia/Llama-3.3-Nemotron-Super-49B-v1.5 | DeepInfra | $0.0600 |
| google/gemini-2.0-flash-001 | DeepInfra | $0.0600 |
| meta-llama/Llama-4-Scout-17B-16E-Instruct | DeepInfra | $0.0500 |
| meta/llama-2-13b-chat | Replicate | $0.0700 |
| openai/gpt-4.1-nano | Replicate | $0.0600 |
| meta/llama-2-13b | Replicate | $0.0700 |
| gpt-4.1-nano-2025-04-14 | OpenAI | $0.0600 |
| gpt-4.1-nano | OpenAI | $0.0600 |
| mistralai/Mistral-Small-24B-Instruct-2501 | together_ai | $0.0500 |
| together-ai-up-to-4b | together_ai | $0.0300 |
| gemini-2.5-flash-lite-preview-06-17 | $0.0600 | |
| gemini-2.5-flash-lite-preview-09-2025 | $0.0600 | |
| gemini-2.5-flash-lite | $0.0600 | |
| gpt-4.1-nano-2025-04-14 | Azure | $0.0600 |
| gpt-4.1-nano | Azure | $0.0600 |
| Meta-Llama-3.1-8B-Instruct | sambanova | $0.0400 |
| mistral-small-2503@001 | $0.0500 | |
| mistral-small-2503 | $0.0500 | |
| nvidia/Llama-3.3-Nemotron-Super-49B-v1 | nebius | $0.0600 |
| Qwen/Qwen3-32B | nebius | $0.0500 |
| Qwen/Qwen3-30B-A3B | nebius | $0.0500 |
| google/gemma-3-27b-it | nebius | $0.0500 |
| gemini-2.5-flash-lite | $0.0600 | |
| gemini-2.0-flash-001 | $0.0600 | |
| gemini-2.5-flash-lite-preview-09-2025 | $0.0600 |