AI 模型情报

厂商 · 2026-05-12

helicone

6 个标准模型15 条记录(含衍生 / 微调)
模型输入 / 1M输出 / 1M上下文服务商标签
Baidu Ernie 4.5 21B A3B Thinking$0.070$0.280128K1reasoning
OpenAI o4 Mini$1.10$4.40200K1tools · vision
OpenAI o3 Mini$1.10$4.40200K1tools
OpenAI o3$2.00$8.00200K1tools · vision
OpenAI: o1$15.00$60.00200K1
OpenAI o3 Pro$20.00$80.00200K1tools · vision
Google Gemma 2衍生$0.010$0.0308K1
Qwen2.5 Coder 7B fast衍生$0.030$0.09032K1
DeepSeek TNG R1T2 Chimera衍生$0.300$1.20130K1tools
OpenAI GPT-4.1 Mini衍生$0.400$1.601.05M1tools · vision
Kimi K2 (07/11)衍生$0.570$2.30131K1tools
Qwen3 235B A22B Thinking衍生$0.300$2.90262K1reasoning · vision
Perplexity Sonar Reasoning衍生$1.00$5.00127K1reasoning
Anthropic: Claude 3.5 Sonnet v2衍生$3.00$15.00200K1tools · vision
Mistral Small衍生$75.00$200.00128K1vision

Frequently asked questions

How many AI models does helicone offer?

We track 6 canonical helicone models plus 9 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily from models.dev.

Which helicone model is the cheapest?

Baidu Ernie 4.5 21B A3B Thinking is currently the lowest-priced helicone model, at $0.070 per 1M input tokens and $0.280 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.

Which helicone model has the largest context window?

OpenAI o4 Mini leads at 200K tokens. This is the total of prompt + completion.

Which helicone models support tool calling?

Multiple helicone models support tool calling, with OpenAI o4 Mini being a popular pick. The capability column in the table above marks every model with helicone tool-calling support.

Which helicone models accept image input?

OpenAI o4 Mini accepts image input. Other vision-capable helicone models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.

What are the best alternatives to helicone?

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 helicone 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.