The Known Good Updated 29 Jul 2026
Providers· First-party endpoint· 46 tracked models

Azure — pricing & performance

Compare models All providers Data sources
Models served
46
of 947 tracked models
Mean output speed
52
tokens per second, averaged over
35 measured endpoints
Mean latency
4.7s
time to first token, averaged over
35 measured endpoints
Cheapest blended
$0.14
per 1M tokens at a 3:1
input:output blend
Output speed on Azure

Median output tokens per second for the 35 of 46 models on Azure with published throughput telemetry from OpenRouter. The full table below lists all 46, measured or not. Higher is better. We do not run these measurements ourselves.

⇩
122
108
84
76
66
66
66
64
64
60
60
59
The Known Good
46 models on Azure
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
Anthropic: Claude Fable 5 Anthropic $10.00 $50.00 $20.00 45 5.7s 1.00M
Anthropic: Claude Haiku 4.5 Anthropic $1.00 $5.00 $2.00 66 0.7s 200k
Anthropic: Claude Opus 4.1 Anthropic $15.00 $75.00 $30.00 — — 200k
Anthropic: Claude Opus 4.5 Anthropic $5.00 $25.00 $10.00 — — 200k
Anthropic: Claude Opus 4.6 Anthropic $5.00 $25.00 $10.00 28 14.0s 1.00M
Anthropic: Claude Opus 4.7 Anthropic $5.00 $25.00 $10.00 — — 1.00M
Anthropic: Claude Opus 4.8 Anthropic $5.00 $25.00 $10.00 39 1.7s 1.00M
Anthropic: Claude Sonnet 4.5 Anthropic $3.00 $15.00 $6.00 — — 200k
Anthropic: Claude Sonnet 4.6 Anthropic $3.00 $15.00 $6.00 38 13.3s 1.00M
Anthropic: Claude Sonnet 5 Anthropic $2.00 $10.00 $4.00 50 1.8s 1.00M
Claude Opus 5 Anthropic $5.00 $25.00 $10.00 60 1.2s 1.00M
DeepSeek: R1 DeepSeek $1.49 $5.94 $2.60 64 1.2s 164k
OpenAI: GPT-3.5 Turbo (older v0613) OpenAI $1.00 $2.00 $1.25 — — 4k
OpenAI: GPT-3.5 Turbo 16k OpenAI $3.00 $4.00 $3.25 — — 16k
OpenAI: GPT-4 OpenAI $30.00 $60.00 $37.50 50 0.8s 8k
OpenAI: GPT-4.1 OpenAI $2.00 $8.00 $3.50 50 1.0s 1.05M
OpenAI: GPT-4.1 Mini OpenAI $0.40 $1.60 $0.70 64 1.1s 1.05M
OpenAI: GPT-4.1 Nano OpenAI $0.10 $0.40 $0.17 32 1.7s 1.05M
OpenAI: GPT-4o OpenAI $2.50 $10.00 $4.38 28 0.9s 128k
OpenAI: GPT-4o (2024-05-13) OpenAI $5.00 $15.00 $7.50 19 1.2s 128k
OpenAI: GPT-4o (2024-08-06) OpenAI $2.50 $10.00 $4.38 48 1.0s 128k
OpenAI: GPT-4o-mini OpenAI $0.15 $0.60 $0.26 25 1.2s 128k
OpenAI: GPT-5 OpenAI $1.25 $10.00 $3.44 46 0.6s 400k
OpenAI: GPT-5 Mini OpenAI $0.25 $2.00 $0.69 76 5.2s 400k
OpenAI: GPT-5 Nano OpenAI $0.050 $0.40 $0.14 58 2.0s 400k
OpenAI: GPT-5.1 OpenAI $1.25 $10.00 $3.44 66 2.0s 400k
OpenAI: GPT-5.1 Chat OpenAI $1.25 $10.00 $3.44 — — 128k
OpenAI: GPT-5.1-Codex OpenAI $1.25 $10.00 $3.44 28 2.5s 400k
OpenAI: GPT-5.1-Codex-Max OpenAI $1.25 $10.00 $3.44 54 2.8s 400k
OpenAI: GPT-5.1-Codex-Mini OpenAI $0.25 $2.00 $0.69 48 2.5s 400k
OpenAI: GPT-5.2 OpenAI $1.75 $14.00 $4.81 40 3.2s 400k
OpenAI: GPT-5.2 Chat OpenAI $1.75 $14.00 $4.81 — — 128k
OpenAI: GPT-5.2-Codex OpenAI $1.75 $14.00 $4.81 32 2.2s 400k
OpenAI: GPT-5.3 Chat OpenAI $1.75 $14.00 $4.81 — — 128k
OpenAI: GPT-5.3-Codex OpenAI $1.75 $14.00 $4.81 60 4.2s 400k
OpenAI: GPT-5.4 OpenAI $2.50 $15.00 $5.62 59 3.5s 1.05M
OpenAI: GPT-5.4 Mini OpenAI $0.75 $4.50 $1.69 122 1.1s 400k
OpenAI: GPT-5.4 Nano OpenAI $0.20 $1.25 $0.46 45 1.1s 400k
OpenAI: GPT-5.4 Pro OpenAI $30.00 $180.00 $67.50 — — 1.05M
OpenAI: GPT-5.5 OpenAI $5.00 $30.00 $11.25 51 8.4s 1.05M
OpenAI: GPT-5.6 Luna OpenAI $1.00 $6.00 $2.25 66 2.4s 1.05M
OpenAI: GPT-5.6 Luna Pro OpenAI $1.00 $6.00 $2.25 108 8.5s 1.05M
OpenAI: GPT-5.6 Sol OpenAI $5.00 $30.00 $11.25 43 3.7s 1.05M
OpenAI: GPT-5.6 Sol Pro OpenAI $5.00 $30.00 $11.25 84 57.7s 1.05M
OpenAI: GPT-5.6 Terra OpenAI $2.50 $15.00 $5.62 42 3.9s 1.05M
OpenAI: GPT-5.6 Terra Pro OpenAI $2.50 $15.00 $5.62 — — 1.05M
The Known Good
Source. Prices, endpoint availability and throughput for Azure are ingested from OpenRouter; model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint — it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this site; see methodology. Quality scores are not provider-specific: a model scores the same wherever it is hosted, so quality lives on the model pages.