# Azure
HQ US · serves 19 tracked open-weights models, 1 confirmed by its own catalog. status page · privacy policy
- models
- 19
- verified
- 1
- of overall top 10
- 1
- cheapest on
- 3 models
- vs best $
- 2.50×
- ctx (median)
- 253k
- uptime
- 100.0%
# models
| model | rank | $/M in | $/M out | ✓ |
|---|---|---|---|---|
| deepseek-v4-pro | #1 | $1.91 | $3.83 | — |
| deepseek-r1 | — | $1.35 | $5.40 | — |
| deepseek-v3 | — | $1.14 | $4.56 | — |
| deepseek-v3.1 | — | $1.23 | $4.94 | — |
| deepseek-v3.2 | — | $0.58 | $1.68 | — |
| deepseek-v4-flash | — | $0.21 | $0.56 | — |
| deepseek-v4-flash-0731 | — | $0.44 | $1.32 | — |
| deepseek-v4.1-flash | — | $0.30 | $1.20 | — |
| gpt-oss-120b | — | $0.15 | $0.60 | ✓ |
| kimi-k2-thinking | — | $0.60 | $2.50 | — |
| kimi-k2.5 | — | $0.60 | $3.00 | — |
| kimi-k2.6 | — | $0.95 | $4.00 | — |
| kimi-k2.7-code | — | $0.95 | $4.00 | — |
| llama-3.3-70b-instruct | — | $0.71 | $0.71 | — |
| mistral-large-3 | — | $0.50 | $1.50 | — |
| phi-3.5-mini-instruct | — | $0.13 | $0.52 | — |
| phi-4 | — | $0.12 | $0.50 | — |
| phi-4-multimodal-instruct | — | $0.08 | $0.32 | — |
| phi-4-reasoning-plus | — | $0.12 | $0.50 | — |
all providers · machine-readable: providers.json