The Known Good Updated 23 Oct 2026 Subscribe
Providers· Inference host· 10 tracked models

Ionstream — pricing & performance

Compare models All providers Data sources
Models served
10
of 1,299 tracked models
Mean output speed
58
tokens per second, averaged over
10 measured endpoints
Mean latency
0.9s
time to first token, averaged over
10 measured endpoints
Cheapest blended
$0.17
per 1M tokens at a 3:1
input:output blend
Output speed on Ionstream

Output tokens per second for all 10 models on Ionstream with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.

All 10 of 10 models⇩
127
122
75
54
52
51
35
30
24
7
The Known Good
10 models on Ionstream
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
DeepSeek: DeepSeek V4 Flash 0423 DeepSeek $0.14 $0.28 $0.17 24 1.2s 1.05M
DeepSeek: DeepSeek V4 Flash 0731 DeepSeek $0.21 $0.42 $0.26 51 0.8s 1.05M
DeepSeek: DeepSeek V4 Pro 0423 DeepSeek $1.13 $2.26 $1.41 35 0.8s 1.05M
DeepSeek: DeepSeek V4 Pro 0813 DeepSeek $0.37 $2.93 $1.01 52 0.6s 1.05M
DeepSeek: DeepSeek V4.1 Flash DeepSeek $0.22 $0.60 $0.32 122 0.8s 1.05M
DeepSeek: DeepSeek V4.1 Flash 1017 DeepSeek $0.22 $0.60 $0.32 127 0.8s 1.05M
Google: Gemma 4 26B A4B Google $0.13 $0.40 $0.20 7 1.7s 262k
Qwen: Qwen3 Coder Next Alibaba $0.16 $0.80 $0.32 75 0.6s 262k
Qwen: Qwen3.8 27B Alibaba $0.040 $1.95 $0.52 54 0.8s 262k
Z.ai: GLM 5.2 Z.ai $1.40 $4.40 $2.15 30 1.2s 1.05M
The Known Good
Source. Prices, endpoint availability and throughput for Ionstream 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.