Ionstream — pricing & performance
Models served
5
of 947 tracked models
Mean output speed
39
tokens per second, averaged over
5 measured endpoints
5 measured endpoints
Mean latency
1.4s
time to first token, averaged over
5 measured endpoints
5 measured endpoints
Cheapest blended
$0.17
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on Ionstream
Median output tokens per second for all 5 models on Ionstream with published throughput telemetry from OpenRouter. Higher is better. We do not run these measurements ourselves.
All 5 of 5 models⇩
The Known Good
5 models on Ionstream
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
DeepSeek: DeepSeek V4 Flash
|
DeepSeek | $0.14 | $0.28 | $0.17 | 19 | 2.7s | 1.05M |
|
DeepSeek: DeepSeek V4 Pro
|
DeepSeek | $1.13 | $2.26 | $1.41 | 5 | 2.1s | 1.05M |
Google: Gemma 4 26B A4B
|
$0.13 | $0.40 | $0.20 | 8 | 1.2s | 262k | |
Qwen: Qwen3 Coder Next
|
Alibaba | $0.11 | $0.80 | $0.28 | 80 | 0.4s | 262k |
Z.ai: GLM 5.2
|
Z.ai | $1.40 | $4.40 | $2.15 | 83 | 0.5s | 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.