Choose a model to open its comparison page.
Llama 3.3 API pricing covers 30 API providers, from $0.0027/M to $75.00/M. The page also shows measured API speed and first-token latency.
Meta Llama 3.3 is an updated Llama 3 open model with improved instruction following, multilingual support, and efficient inference.
Compare Llama 3.3 API pricing across 30 providers. Prices range from $0.0027/M to $75.00/M. 云AI offers the lowest rate at $0.0027/M.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | llama-3.3-70b | default | $0.0068/M | $0.020/M | — | — | — | |
L1 100% | llama-3.3-70b | default | $0.013/M | $0.038/M | — | — | — | |
L1 100% | llama-3.3-70b | default | $0.014/M | $0.041/M | — | — | — | |
L1 100% | llama-3.3-70b | default | $0.011/M | $0.032/M | — | — | — | |
L1 100% | llama-3.3-70b | default | $75.00/M | $75.00/M | — | — | — | |
L1 100% | llama-3.3-70b | default | $0.0068/M | $0.020/M | — | — | — | |
L1 100% | llama-3.3-70b | default | $0.013/M | $0.038/M | — | — | — | |
L1 100% | llama-3.3-70b | default | $0.0068/M | $0.020/M | — | — | — | |
L1 1% | llama-3.3-70b | mix | $0.0027/M | $0.0081/M | — | — | — |
gemini-2-5-pro
Google Gemini 2.5 Pro is Google advanced multimodal model with a 1M-token context window, strong STEM reasoning, and native support for images, audio, and video understanding.
gemini-2-5-flash
Google Gemini 2.5 Flash is a fast multimodal model balancing speed and intelligence for chat, tool use, and large-context workloads at lower cost than Pro tiers.
deepseek-v3
DeepSeek V3 is DeepSeek flagship MoE language model with 671B total parameters, delivering strong performance in reasoning, coding, and multilingual tasks at competitive inference cost.
qwen3
Alibaba Qwen3 is the Qwen family's flagship LLM series with dense and MoE variants, seamless thinking/non-thinking modes, and leading open-source performance in math, code, and agent tasks.
gpt-5-4
OpenAI GPT-5.4 extends the GPT-5 family with stronger instruction following, deeper tool use, and improved performance on coding, math, and long-document analysis.
gpt-5-3-codex
OpenAI GPT-5.3 Codex is a code-specialized variant in the GPT-5 series, optimized for code generation, debugging, and software development tasks.
