AI 模型情报

厂商 · 2026-05-12

poe

1 个标准模型45 条记录(含衍生 / 微调)
模型输入 / 1M输出 / 1M上下文服务商标签
Tako未公开未公开2K1tools
Llama-3.1-8B-CS衍生$0.100$0.100128K1tools
DeepSeek-V4-Flash-EL衍生$0.140$0.2801M1tools · reasoning · open-weights
GPT-4o-mini-Search衍生$0.140$0.540128K1tools
GPT-OSS-120B-CS衍生$0.350$0.750128K1tools · reasoning
Claude-Haiku-3衍生$0.210$1.10189K1tools · vision
GPT-3.5-Turbo-Raw衍生$0.450$1.405K1tools · vision
Nano-Banana衍生$0.210$1.8066K1tools · vision
Claude-Haiku-3.5衍生$0.680$3.40189K1tools · vision
DeepSeek-V4-Pro-EL衍生$1.67$3.331M1tools · reasoning · open-weights
GPT-5.1-Instant衍生$1.10$9.00128K1tools · reasoning · vision
GPT-4o-Aug衍生$2.20$9.00128K1tools · vision
GPT-4o-Search衍生$2.20$9.00128K1tools
gemini-deep-research衍生$1.60$9.601.05M1tools · reasoning · vision
Gemini-3-Pro衍生$1.60$9.601.05M1tools · reasoning · vision
Gemini-3.1-Pro衍生$2.00$12.001.05M1tools · reasoning · vision
GPT-5.2-Instant衍生$1.60$13.00128K1tools · vision
GPT-5.3-Instant衍生$1.60$13.00128K1tools · vision
Claude-Sonnet-3.5衍生$2.60$13.00189K1tools · vision
Claude-Sonnet-3.7衍生$2.60$13.00197K1tools · reasoning · vision
Claude-Sonnet-3.5-June衍生$2.60$13.00189K1tools · vision
GPT-4-Classic-0314衍生$27.00$54.008K1tools · vision
GPT-4-Classic衍生$27.00$54.008K1tools · vision
claude-code衍生未公开未公开Unknown1tools · reasoning
DALL-E-3衍生未公开未公开8001tools
Gemma-4-31B衍生未公开未公开262K1tools · vision
GPT-Image-2衍生$5.05$32.32Unknown1vision
Imagen-3衍生未公开未公开4801tools
Imagen-3-Fast衍生未公开未公开4801tools
Imagen-4衍生未公开未公开4801tools
Imagen-4-Fast衍生未公开未公开4801tools
Imagen-4-Ultra衍生未公开未公开4801tools
Kimi-K2.5-FW衍生未公开未公开262K1tools · vision
llama-3.3-70b-cs衍生未公开未公开Unknown1
Lyria衍生未公开未公开Unknown1tools
Nano-Banana-Pro衍生$2.00$12.0066K1tools · vision
qwen3-235b-2507-cs衍生未公开未公开Unknown1tools · reasoning
qwen3-32b-cs衍生未公开未公开Unknown1tools · reasoning
Sora-2衍生未公开未公开Unknown1tools · vision
Sora-2-Pro衍生未公开未公开Unknown1tools · vision
Veo-2衍生未公开未公开4801tools
Veo-3衍生未公开未公开4801tools
Veo-3-Fast衍生未公开未公开4801tools
Veo-3.1衍生未公开未公开4801tools
Veo-3.1-Fast衍生未公开未公开4801tools · vision

Frequently asked questions

How many AI models does poe offer?

We track 1 canonical poe models plus 44 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily from models.dev.

Which poe model has the largest context window?

Tako leads at 2K tokens. This is the total of prompt + completion.

Which poe models support tool calling?

Multiple poe models support tool calling, with Tako being a popular pick. The capability column in the table above marks every model with poe tool-calling support.

What are the best alternatives to poe?

Depends on the use case. For raw cost savings, look at /pricing/cheapest-llm-api. For agent-oriented workloads, /best/best-ai-model-for-agents. For long-document workflows, /best/best-long-context-llm.

How fresh is this poe pricing data?

Daily. Our pipeline pulls models.dev each morning and rebuilds these pages on data change, so list-price moves and new model releases land within roughly 24 hours.

最近更新:

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.