厂商 · 2026-05-12
azure
| 模型 | 输入 / 1M | 输出 / 1M | 上下文 | 服务商 | 标签 |
|---|---|---|---|---|---|
| text-embedding-3-small | $0.020 | Unknown | 8K | 1 | — |
| Ministral 3B | $0.040 | $0.040 | 128K | 1 | tools · open-weights |
| text-embedding-ada-002 | $0.100 | Unknown | 8K | 1 | — |
| text-embedding-3-large | $0.130 | Unknown | 8K | 1 | — |
| Model Router | $0.140 | Unknown | 128K | 1 | tools · vision |
| o4-mini | $1.10 | $4.40 | 200K | 1 | tools · reasoning · vision |
| MAI-DS-R1 | $1.35 | $5.40 | 128K | 1 | reasoning |
| Codex Mini | $1.50 | $6.00 | 200K | 1 | tools · reasoning |
| o1 | $15.00 | $60.00 | 200K | 1 | tools · reasoning · vision |
| Embed v3 Multilingual衍生 | $0.100 | Unknown | 512 | 1 | open-weights |
| Embed v3 English衍生 | $0.100 | Unknown | 512 | 1 | open-weights |
| Embed v4衍生 | $0.120 | Unknown | 128K | 1 | vision · open-weights |
| Grok 4.20 (Non-Reasoning)衍生 | $2.00 | $6.00 | 262K | 1 | tools |
| Grok 4.20 (Reasoning)衍生 | $2.00 | $6.00 | 262K | 1 | tools · reasoning |
Frequently asked questions
How many AI models does azure offer?
We track 9 canonical azure models plus 5 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily from models.dev.
Which azure model is the cheapest?
text-embedding-3-small is currently the lowest-priced azure model, at $0.020 per 1M input tokens and Unknown per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.
Which azure model has the largest context window?
o4-mini leads at 200K tokens. This is the total of prompt + completion.
Which azure models support tool calling?
Multiple azure models support tool calling, with Ministral 3B being a popular pick. The capability column in the table above marks every model with azure tool-calling support.
Which azure models accept image input?
Model Router accepts image input. Other vision-capable azure models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.
What are the best alternatives to azure?
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 azure 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.
Explore more
Top azure models
- text-embedding-3-small$0.02 in / $0.00 out
- Ministral 3B$0.04 in / $0.04 out
- text-embedding-ada-002$0.10 in / $0.00 out
- text-embedding-3-large$0.13 in / $0.00 out
- Model Router$0.14 in / $0.00 out
Browse by use case
Browse by capability
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.