The Known Good Updated 8 Sep 2026 Subscribe
Providers· Inference host· 28 tracked models

StreamLake — pricing & performance

Compare models All providers Data sources
Models served
28
of 1,109 tracked models
Mean output speed
45
tokens per second, averaged over
28 measured endpoints
Mean latency
1.7s
time to first token, averaged over
28 measured endpoints
Cheapest blended
$0.084
per 1M tokens at a 3:1
input:output blend
Output speed on StreamLake

Output tokens per second for all 28 models on StreamLake with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.

⇩
150
145
75
74
62
58
52
52
51
51
43
36
The Known Good
28 models on StreamLake
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
DeepSeek: DeepSeek V3 DeepSeek $0.26 $1.03 $0.45 24 1.3s 128k
DeepSeek: DeepSeek V3.1 Terminus DeepSeek $0.34 $1.03 $0.51 43 1.5s 128k
DeepSeek: DeepSeek V3.2 DeepSeek $0.21 $0.32 $0.24 22 1.5s 128k
DeepSeek: DeepSeek V4 Flash 0423 DeepSeek $0.089 $0.18 $0.11 29 1.8s 1.02M
DeepSeek: DeepSeek V4 Flash 0731 DeepSeek $0.13 $0.40 $0.20 75 1.3s 1.02M
DeepSeek: DeepSeek V4 Pro 0423 DeepSeek $0.96 $1.91 $1.19 34 2.0s 1.02M
DeepSeek: DeepSeek V4 Pro 0813 DeepSeek $1.05 $3.15 $1.57 52 2.8s 1.02M
DeepSeek: R1 0528 DeepSeek $0.57 $2.29 $1.00 51 3.3s 128k
Kwaipilot: KAT-Coder-Air V2.5 Kuaishou $0.15 $0.60 $0.26 150 1.6s 256k
Kwaipilot: KAT-Coder-Pro V2 Kuaishou $0.30 $1.20 $0.53 15 0.6s 256k
Kwaipilot: KAT-Coder-Pro V2.5 Kuaishou $0.74 $2.96 $1.29 21 0.7s 256k
MiniMax: MiniMax M2.5 MiniMax $0.27 $1.08 $0.47 58 0.9s 200k
MiniMax: MiniMax M3 MiniMax $0.30 $1.20 $0.53 62 1.6s 1.00M
MoonshotAI: Kimi K2.5 Moonshot AI $0.54 $2.70 $1.08 51 1.2s 256k
MoonshotAI: Kimi K2.6 Moonshot AI $0.60 $2.52 $1.08 33 1.7s 256k
MoonshotAI: Kimi K2.7 Code Moonshot AI $0.71 $3.00 $1.28 30 1.0s 256k
Qwen: Qwen3 235B A22B Instruct 2507 Alibaba $0.21 $0.84 $0.37 22 1.4s 128k
Qwen: Qwen3 30B A3B Instruct 2507 Alibaba $0.048 $0.19 $0.084 16 1.6s 128k
Qwen: Qwen3 Coder Next Alibaba $0.18 $0.90 $0.36 145 0.9s 256k
Qwen: Qwen3.5 397B A17B Alibaba $0.60 $3.60 $1.35 74 0.7s 256k
Xiaomi: MiMo-V2.5 Xiaomi $0.17 $0.34 $0.21 25 1.4s 1.00M
Xiaomi: MiMo-V2.5-Pro Xiaomi $0.52 $1.04 $0.65 22 2.6s 1.00M
Z.ai: GLM 4.7 Z.ai $0.48 $1.76 $0.80 34 1.9s 200k
Z.ai: GLM 5 Z.ai $0.60 $1.92 $0.93 36 2.9s 198k
Z.ai: GLM 5.1 Z.ai $0.97 $3.04 $1.48 24 2.2s 200k
Z.ai: GLM 5.2 Z.ai $0.68 $2.13 $1.04 52 1.5s 1.02M
Z.ai: GLM 5.3 Z.ai $1.11 $3.50 $1.71 28 3.1s 1.02M
Z.ai: GLM 5.3 Flash Z.ai $0.14 $0.45 $0.21 30 3.6s 1.02M
The Known Good
Source. Prices, endpoint availability and throughput for StreamLake 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.