你可以先按供应商筛选，再看具体模型的输入、缓存、输出价格和上下文长度。由于用到了缓存，这里的模型列表可能滞后于用户面板。
页面只展示当前可用的模型，点击模型行里的“详情”可以查看完整参数。
模型
| 供应商 | 模型 | 输入 | 缓存 | 输出 | 上下文 | 能力 | 详情 |
|---|---|---|---|---|---|---|---|
OpenAI
|
GPT-5.4 Nano
gpt-5.4-nano
GPT-5.4 nano is OpenAI's smallest and fastest model, optimized for edge and low-latency use cases.
|
$0.2 | $0.02 | $1.25 | 128,000 |
tools
structured_output
vision
reasoning
|
|
|
OpenAI
|
GPT-5.4 Mini
gpt-5.4-mini
GPT-5.4 mini is a smaller, faster, and more cost-efficient version of GPT-5.4 for lightweight tasks.
|
$0.75 | $0.075 | $4.5 | 128,000 |
tools
structured_output
vision
reasoning
|
|
|
OpenAI
|
GPT-5.4
gpt-5.4
GPT-5.4 is OpenAI's flagship model with strong coding, reasoning, and multimodal capabilities.
|
$2.5 | $0.25 | $15 | 1,000,000 |
tools
structured_output
vision
reasoning
|
|
|
OpenAI
|
GPT-5.5
gpt-5.5
GPT-5.5 is OpenAI's flagship model with strong coding, reasoning, and multimodal capabilities.
|
$5 | $0 | $30 | 1,000,000 |
tools
structured_output
vision
reasoning
|
|
|
OpenAI
|
GPT-5.4 Pro
gpt-5.4-pro
GPT-5.4 pro uses OpenAI's Responses API with built-in tools, improved reasoning, and stateful context management.
|
$30 | $0 | $180 | — |
tools
structured_output
vision
reasoning
|
|
Anthropic
|
Claude Sonnet 4.6
claude-sonnet-4.6
Claude Sonnet 4.6 is Anthropic's latest balanced model offering strong coding, reasoning, and agentic capabilities with improved instruction following.
|
$3 | $0.3 | $15 | 200,000 |
tools
vision
reasoning
|
|
|
Anthropic
|
Claude Opus 4.6
claude-opus-4.6
Claude Opus 4.6 is Anthropic's flagship language model built for complex, multi-step work in coding, financial analysis, and legal reasoning. It uses extended thinking to work through complex problems carefully and features a one million token context window.
|
$5 | $0.5 | $25 | 1,000,000 |
tools
vision
reasoning
|
|
|
Anthropic
|
Claude Opus 4.7
claude-opus-4.7
Claude Opus 4.7 is Anthropic's most capable generally available model, with a step-change improvement in agentic coding over Claude Opus 4.6. It uses adaptive thinking to calibrate reasoning per task and supports a one million token context window at standard pricing.
|
$5 | $0.5 | $25 | 1,000,000 |
tools
vision
|
|
|
Anthropic
|
Claude Opus 4.8
claude-opus-4.8
Claude Opus 4.8 is Anthropic's most capable generally available model, with a step-change improvement in agentic coding over Claude Opus 4.7. It uses adaptive thinking to calibrate reasoning per task and supports a one million token context window at standard pricing.
|
$5 | $0.5 | $25 | 1,000,000 |
tools
vision
reasoning
|
|
|
Anthropic
|
Claude Fable 5
claude-fable-5
Claude Fable 5 is Anthropic's most capable widely released model, built for the most demanding reasoning and long-horizon agentic work. Adaptive thinking is always on, and the model supports a 1M token context window with up to 128k output tokens per request.
|
$10 | $1 | $50 | 1,000,000 |
tools
vision
reasoning
|
|
Google
|
Gemini 3.1 Flash-Lite Preview
gemini-3.1-flash-lite-preview
Gemini 3.1 Flash-Lite Preview is a text generation model for reasoning, coding, and conversation.
|
$0.125 | $0 | $0.75 | 1,000,000 |
—
|
|
|
Google
|
Gemini 3.1 Flash Lite
gemini-3.1-flash-lite
Google's lightest and most cost-efficient Gemini model for high-throughput tasks.
|
$0.25 | $0.03 | $1.5 | 1,000,000 |
tools
vision
|
|
|
Google
|
Gemini 3 Flash
gemini-3-flash
Gemini 3 Flash is Google's fast multimodal model with frontier intelligence, superior search, and grounding capabilities.
|
$0.5 | $0.05 | $3 | 1,000,000 |
tools
reasoning
vision
|
|
|
Google
|
Gemini 3 Flash Preview
gemini-3-flash-preview
Gemini 3 Flash Preview is a text generation model for reasoning, coding, and conversation.
|
$0.5 | $0 | $3 | 1,000,000 |
—
|
|
|
Google
|
Gemini 3.1 Pro
gemini-3.1-pro
Google's most intelligent Gemini model with improved reasoning, a medium thinking level, and a 1M token context window.
|
$2 | $0.2 | $12 | 1,000,000 |
tools
reasoning
vision
|
|
|
Google
|
Gemini 3.1 Pro Preview
gemini-3.1-pro-preview
Gemini 3.1 Pro Preview is a text generation model for reasoning, coding, and conversation.
|
$2 | $0 | $12 | 1,000,000 |
—
|
|
DeepSeek
|
deepseek-v4-flash
deepseek-v4-flash
deepseek-v4-flash is a text generation model for reasoning, coding, and conversation.
|
$0.14 | $0.0028 | $0.28 | 1,024,000 |
tools
reasoning
|
|
|
DeepSeek
|
DeepSeek V4 Pro
deepseek-v4-pro
DeepSeek V4 Pro is a high-capability reasoning model from DeepSeek, served via Fireworks infrastructure for production-grade inference.
|
$1.74 | $0.145 | $3.48 | 131,072 |
tools
reasoning
|
|
Community
|
GLM 4.7 Flash
@cf/zai-org/glm-4.7-flash
GLM 4.7 Flash is a text generation model for reasoning, coding, and conversation.
|
$0.3 | $0 | $0.6 | 8,192 |
tools
vision
reasoning
|
|
|
Community
|
GLM 4.7 Flash
glm-4.7-flash
GLM 4.7 Flash is a text generation model for reasoning, coding, and conversation.
|
$0.3 | $0 | $0.6 | 131,072 |
tools
vision
reasoning
|
|
|
Community
|
Llama 3 8B
@cf/meta/llama-3-8b-instruct
Llama 3 8B is a text generation model for reasoning, coding, and conversation.
|
$0.3 | $0 | $0.6 | 8,192 |
tools
vision
reasoning
|
|
|
Community
|
Llama 3 8B
llama-3-8b
Llama 3 8B is a text generation model for reasoning, coding, and conversation.
|
$0.3 | $0 | $0.6 | 8,192 |
tools
vision
reasoning
|
|
|
Community
|
Llama 3.1 70B
@cf/meta/llama-3.1-70b-instruct
Llama 3.1 70B is a text generation model for reasoning, coding, and conversation.
|
$0.3 | $0 | $0.6 | 8,192 |
tools
vision
reasoning
|
|
|
Community
|
Llama 3.1 70B
llama-3.1-70b
Llama 3.1 70B is a text generation model for reasoning, coding, and conversation.
|
$0.3 | $0 | $0.6 | 131,072 |
tools
vision
reasoning
|
|
|
Community
|
Llama 3.1 8B
@cf/meta/llama-3.1-8b-instruct
Llama 3.1 8B is a text generation model for reasoning, coding, and conversation.
|
$0.3 | $0 | $0.6 | 8,192 |
tools
vision
reasoning
|
|
|
Community
|
Llama 3.1 8B
llama-3.1-8b
Llama 3.1 8B is a text generation model for reasoning, coding, and conversation.
|
$0.3 | $0 | $0.6 | 16,384 |
tools
vision
reasoning
|
|
|
Community
|
Llama 3.2 1B
@cf/meta/llama-3.2-1b-instruct
Llama 3.2 1B is a text generation model for reasoning, coding, and conversation.
|
$0.3 | $0 | $0.6 | 8,192 |
tools
vision
reasoning
|
|
|
Community
|
Llama 3.2 1B
llama-3.2-1b
Llama 3.2 1B is a text generation model for reasoning, coding, and conversation.
|
$0.3 | $0 | $0.6 | 8,192 |
tools
vision
reasoning
|
|
|
Community
|
Llama 3.2 3B
@cf/meta/llama-3.2-3b-instruct
Llama 3.2 3B is a text generation model for reasoning, coding, and conversation.
|
$0.3 | $0 | $0.6 | 8,192 |
tools
vision
reasoning
|
|
|
Community
|
Llama 3.2 3B
llama-3.2-3b
Llama 3.2 3B is a text generation model for reasoning, coding, and conversation.
|
$0.3 | $0 | $0.6 | 8,192 |
tools
vision
reasoning
|
|
|
Community
|
Mistral 7B
@cf/mistral/mistral-7b-instruct-v0.3
Mistral 7B is a text generation model for reasoning, coding, and conversation.
|
$0.3 | $0 | $0.6 | 8,192 |
—
|
|
|
Community
|
Mistral 7B
mistral-7b
Mistral 7B is a text generation model for reasoning, coding, and conversation.
|
$0.3 | $0 | $0.6 | 8,192 |
tools
vision
reasoning
|
|
|
Community
|
Mistral 7B v0.1
@cf/mistral/mistral-7b-instruct-v0.1
Mistral 7B v0.1 is a text generation model for reasoning, coding, and conversation.
|
$0.3 | $0 | $0.6 | 8,192 |
tools
vision
reasoning
|
|
|
Community
|
Qwen 1.5 7B
@cf/qwen/qwen1.5-7b-chat
Qwen 1.5 7B is a text generation model for reasoning, coding, and conversation.
|
$0.3 | $0 | $0.6 | 8,192 |
tools
vision
reasoning
|
|
|
Community
|
Gemma 3 12B
@cf/google/gemma-3-12b-it
Gemma 3 12B is a text generation model for reasoning, coding, and conversation.
|
$0.4 | $0 | $0.8 | 32,768 |
tools
vision
reasoning
|
|
|
Community
|
Gemma 4 26B (MoE)
@cf/google/gemma-4-26b-a4b-it
Gemma 4 26B (MoE) is a text generation model for reasoning, coding, and conversation.
|
$0.4 | $0 | $0.8 | 32,768 |
tools
vision
reasoning
|
|
|
Community
|
Kimi K2.5
@cf/moonshotai/kimi-k2.5
Kimi K2.5 is a text generation model for reasoning, coding, and conversation.
|
$0.5 | $0 | $1 | 131,072 |
tools
vision
reasoning
|
|
|
Community
|
Kimi K2.5
kimi-k2.5
Kimi K2.5 is a text generation model for reasoning, coding, and conversation.
|
$0.5 | $0 | $1 | 262,144 |
tools
vision
reasoning
|
|
|
Community
|
Kimi K2.6
@cf/moonshotai/kimi-k2.6
Kimi K2.6 is a text generation model for reasoning, coding, and conversation.
|
$0.5 | $0 | $1 | 131,072 |
tools
vision
reasoning
|
|
|
Community
|
Kimi K2.6
kimi-k2.6
Kimi K2.6 is a text generation model for reasoning, coding, and conversation.
|
$0.5 | $0 | $1 | 262,142 |
tools
vision
reasoning
|
|
|
Community
|
Llama 3.3 70B
@cf/meta/llama-3.3-70b-instruct-fp8-fast
Llama 3.3 70B is a text generation model for reasoning, coding, and conversation.
|
$0.5 | $0 | $1 | 8,192 |
tools
vision
reasoning
|
|
|
Community
|
Llama 3.3 70B
llama-3.3-70b
Llama 3.3 70B is a text generation model for reasoning, coding, and conversation.
|
$0.5 | $0 | $1 | 131,072 |
tools
vision
reasoning
|
|
|
Community
|
Llama 4 Scout 17B
@cf/meta/llama-4-scout-17b-16e-instruct
Llama 4 Scout 17B is a text generation model for reasoning, coding, and conversation.
|
$0.5 | $0 | $1 | 16,384 |
tools
vision
reasoning
|
|
|
Community
|
Llama 4 Scout 17B
llama-4-scout
Llama 4 Scout 17B is a text generation model for reasoning, coding, and conversation.
|
$0.5 | $0 | $1 | 327,680 |
tools
vision
reasoning
|
|
|
Community
|
Mistral Small 3.1 24B
@cf/mistralai/mistral-small-3.1-24b-instruct
Mistral Small 3.1 24B is a text generation model for reasoning, coding, and conversation.
|
$0.5 | $0 | $1 | 32,768 |
tools
vision
reasoning
|
|
|
Community
|
Mistral Small 3.1 24B
mistral-small-3.1-24b
Mistral Small 3.1 24B is a text generation model for reasoning, coding, and conversation.
|
$0.5 | $0 | $1 | 128,000 |
tools
vision
reasoning
|
|
|
Community
|
NVIDIA Nemotron 3 120B
@cf/nvidia/nemotron-3-120b-a12b
NVIDIA Nemotron 3 120B is a text generation model for reasoning, coding, and conversation.
|
$0.5 | $0 | $1 | 8,192 |
tools
vision
reasoning
|
|
|
Community
|
Qwen 2.5 Coder 32B
@cf/qwen/qwen2.5-coder-32b-instruct
Qwen 2.5 Coder 32B is a text generation model for reasoning, coding, and conversation.
|
$0.5 | $0 | $1 | 32,768 |
tools
vision
reasoning
|
|
|
Community
|
Qwen3 30B (MoE)
@cf/qwen/qwen3-30b-a3b-fp8
Qwen3 30B (MoE) is a text generation model for reasoning, coding, and conversation.
|
$0.5 | $0 | $1 | 32,768 |
tools
vision
reasoning
|
|
|
Community
|
QwQ 32B (推理)
@cf/qwen/qwq-32b
QwQ 32B (推理) is a text generation model for reasoning, coding, and conversation.
|
$0.5 | $0 | $1 | 32,768 |
tools
vision
reasoning
|
|
|
Community
|
QwQ 32B (推理)
qwq-32b
QwQ 32B (推理) is a text generation model for reasoning, coding, and conversation.
|
$0.5 | $0 | $1 | 32,768 |
tools
vision
reasoning
|
|
|
Community
|
DeepSeek R1 (CF)
@cf/deepseek-ai/deepseek-r1-distill-qwen-32b
DeepSeek R1 (CF) is a text generation model for reasoning, coding, and conversation.
|
$0.55 | $0 | $2 | 32,768 |
tools
vision
reasoning
|