The Known Good Updated 9 Sep 2026 Subscribe
Providers· First-party endpoint· 51 tracked models

Azure — pricing & performance

Compare models All providers Data sources
Models served
51
of 1,111 tracked models
Mean output speed
46
tokens per second, averaged over
45 measured endpoints
Mean latency
5.1s
time to first token, averaged over
45 measured endpoints
Cheapest blended
$0.14
per 1M tokens at a 3:1
input:output blend
Output speed on Azure

Output tokens per second for the 45 of 51 models on Azure with published throughput telemetry, the most recent figure OpenRouter publishes for each host. The full table below lists all 51, measured or not. Higher is better. We do not run these measurements ourselves.

⇩
129
84
80
77
75
73
72
68
67
66
65
65
The Known Good
51 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 37 6.1s 1.00M
Anthropic: Claude Fable 5.1 Anthropic $10.00 $50.00 $20.00 34 5.0s 1.00M
Anthropic: Claude Haiku 4.5 Anthropic $1.00 $5.00 $2.00 67 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 73 1.3s 200k
Anthropic: Claude Opus 4.6 Anthropic $5.00 $25.00 $10.00 23 1.9s 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 49 4.3s 1.00M
Anthropic: Claude Sonnet 4.5 Anthropic $3.00 $15.00 $6.00 42 1.8s 200k
Anthropic: Claude Sonnet 4.6 Anthropic $3.00 $15.00 $6.00 32 2.1s 1.00M
Anthropic: Claude Sonnet 5 Anthropic $2.00 $10.00 $4.00 65 0.9s 1.00M
Claude Opus 5 Anthropic $5.00 $25.00 $10.00 80 4.7s 1.00M
DeepSeek: DeepSeek V4 Flash 0423 DeepSeek $0.21 $0.56 $0.30 37 1.2s 1.05M
DeepSeek: DeepSeek V4 Pro 0423 DeepSeek $1.91 $3.83 $2.39 50 2.6s 1.05M
DeepSeek: R1 DeepSeek $1.49 $5.94 $2.60 — — 164k
OpenAI: GPT-3.5 Turbo (older v0613) OpenAI $1.00 $2.00 $1.25 30 0.8s 4k
OpenAI: GPT-3.5 Turbo 16k OpenAI $3.00 $4.00 $3.25 6 0.5s 16k
OpenAI: GPT-4 OpenAI $30.00 $60.00 $37.50 30 0.5s 8k
OpenAI: GPT-4.1 OpenAI $2.00 $8.00 $3.50 22 1.4s 1.05M
OpenAI: GPT-4.1 Mini OpenAI $0.40 $1.60 $0.70 52 1.3s 1.05M
OpenAI: GPT-4.1 Nano OpenAI $0.10 $0.40 $0.17 30 1.7s 1.05M
OpenAI: GPT-4o OpenAI $2.50 $10.00 $4.38 38 0.9s 128k
OpenAI: GPT-4o (2024-05-13) OpenAI $5.00 $15.00 $7.50 2 1.5s 128k
OpenAI: GPT-4o (2024-08-06) OpenAI $2.50 $10.00 $4.38 3 0.6s 128k
OpenAI: GPT-4o-mini OpenAI $0.15 $0.60 $0.26 64 1.2s 128k
OpenAI: GPT-5 OpenAI $1.25 $10.00 $3.44 59 11.6s 400k
OpenAI: GPT-5 Mini OpenAI $0.25 $2.00 $0.69 72 3.9s 400k
OpenAI: GPT-5 Nano OpenAI $0.050 $0.40 $0.14 65 3.4s 400k
OpenAI: GPT-5.1 OpenAI $1.25 $10.00 $3.44 42 1.1s 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 56 4.1s 400k
OpenAI: GPT-5.1-Codex-Max OpenAI $1.25 $10.00 $3.44 49 4.9s 400k
OpenAI: GPT-5.1-Codex-Mini OpenAI $0.25 $2.00 $0.69 32 3.2s 400k
OpenAI: GPT-5.2 OpenAI $1.75 $14.00 $4.81 43 4.4s 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 27 4.6s 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 42 5.7s 400k
OpenAI: GPT-5.4 OpenAI $2.50 $15.00 $5.62 45 1.9s 1.05M
OpenAI: GPT-5.4 Mini OpenAI $0.75 $4.50 $1.69 66 1.6s 400k
OpenAI: GPT-5.4 Nano OpenAI $0.20 $1.25 $0.46 54 1.6s 400k
OpenAI: GPT-5.4 Pro OpenAI $30.00 $180.00 $67.50 2 9.8s 1.05M
OpenAI: GPT-5.5 OpenAI $5.00 $30.00 $11.25 68 47.6s 1.05M
OpenAI: GPT-5.6 Luna OpenAI $0.20 $1.20 $0.45 75 2.8s 1.05M
OpenAI: GPT-5.6 Luna Pro OpenAI $0.20 $1.20 $0.45 129 8.6s 1.05M
OpenAI: GPT-5.6 Sol OpenAI $5.00 $30.00 $11.25 46 4.3s 1.05M
OpenAI: GPT-5.6 Sol Pro OpenAI $5.00 $30.00 $11.25 77 19.7s 1.05M
OpenAI: GPT-5.6 Terra OpenAI $2.00 $12.00 $4.50 48 2.1s 1.05M
OpenAI: GPT-5.6 Terra Pro OpenAI $2.00 $12.00 $4.50 84 11.5s 1.05M
OpenAI: GPT-6 Astra OpenAI $10.00 $50.00 $20.00 19 8.3s 1.05M
OpenAI: GPT-6 Astra Pro OpenAI $10.00 $50.00 $20.00 24 21.3s 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.