All promotions
GuidesMCP

AkashML

Inference providerGlobalprices checked Oct 23, 06:00 UTC

Pricing page ↗

AkashML serves 8 models at a verified price. On the 8 it shares with other hosts, it is the cheapest on 2 and charges a median 28% above the cheapest.

Models served88 with open weights
Cheapest input, per M$0.02gpt-oss-20b
Uptime, last 24 h99.9%average of its 7 OpenRouter endpoints
Sign-upno free credits stated
Newest first
ModelPrecisionContextToolsInputOutputCache
GLM-5.3fp81M✓$0.19$4.40$0.19
Qwen3.8 27Bfp8256K✓$0.23$1.98$0.05
DeepSeek V4 Flash 0731not stated by the host1M—$0.065$0.18$0.016
Kimi K3fp41M✓$1.20$14.00$1.20
Qwen3.6 35B A3Bcheapestfp8256K✓$0.10$0.90$0.05
gpt-oss-120bbf16128K✓$0.03$0.19$0.03
gpt-oss-20bcheapestfp4128K✓$0.02$0.10—
Llama 3.3 70Bfp8128K✓$0.20$0.52$0.10

8 of 8 models · prices per million tokens · precision and context: read at AkashML's own catalogue or docs where its terms allow, otherwise as declared to OpenRouter (hover a cell for its source) · tools as AkashML declares them to OpenRouter

ConditionWhat it saysSource
Sign-upCard requiredakashml.com
Free creditsNone stated—
Headquarters regionGlobal—
Price listWhere its per-token prices are publishedakashml.com
API documentationIts own docsakashml.com
Terms of serviceIts termsakashml.com

Links checked Oct 8.