The Known Good Updated 8 Oct 2026 Subscribe
Providers· Inference host· 11 tracked models

AkashML — pricing & performance

Compare models All providers Data sources
Models served
11
of 1,191 tracked models
Mean output speed
44
tokens per second, averaged over
11 measured endpoints
Mean latency
1.4s
time to first token, averaged over
11 measured endpoints
Cheapest blended
$0.040
per 1M tokens at a 3:1
input:output blend
Output speed on AkashML

Output tokens per second for all 11 models on AkashML with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.

⇩
106
75
61
41
36
35
34
33
28
27
8
The Known Good
11 models on AkashML
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
DeepSeek: DeepSeek V4 Flash 0423 DeepSeek $0.098 $0.20 $0.12 8 1.7s 131k
DeepSeek: DeepSeek V4 Flash 0731 DeepSeek $0.065 $0.18 $0.094 33 1.3s 1.05M
Meta: Llama 3.3 70B Instruct Meta $0.20 $0.52 $0.28 35 1.1s 131k
MoonshotAI: Kimi K3 Moonshot AI $1.20 $14.00 $4.40 41 1.0s 1.05M
OpenAI: gpt-oss-120b OpenAI $0.037 $0.19 $0.074 61 5.0s 131k
OpenAI: gpt-oss-20b OpenAI $0.020 $0.10 $0.040 28 1.1s 131k
Qwen: Qwen3.5-35B-A3B Alibaba $0.14 $1.00 $0.35 106 1.4s 262k
Qwen: Qwen3.6 35B A3B Alibaba $0.10 $0.90 $0.30 36 0.6s 262k
Qwen: Qwen3.8 27B Alibaba $0.23 $1.98 $0.66 34 0.9s 262k
Z.ai: GLM 5.2 Z.ai $0.77 $2.42 $1.18 27 0.6s 1.05M
Z.ai: GLM 5.3 Z.ai $0.19 $4.40 $1.24 75 1.2s 1.05M
The Known Good
Source. Prices, endpoint availability and throughput for AkashML 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.