AkashML
Explore AkashML models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
AkashMLakashml
No provider claim
| Provider | AkashML |
|---|---|
| Routing status | Active |
| Provider website | https://akashml.com/ |
| Models | 6 public models |
| Prepaid routes | 6 |
| BYOK routes | 0 |
| Zero data retention | not claimed |
| Confidential compute | not claimed |
| Provider E2EE | not claimed |
| Policy note | No contractual zero-retention, confidential-compute, or E2EE claim is tracked for TrustedRouter's AkashML account. This route is Standard. Policy source |
Measured performance
29 samplesContinuously sampled across AkashML's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 1552 ms |
|---|---|
| Effective throughput | 43 tok/s n=4 |
| Uptime | 100.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| qwen/qwen3.6-35b-a3b | 1171 ms | — | 100.00% | — | 9 |
| deepseek/deepseek-v4-flash-0731 | 1188 ms | 39 tok/s n=2 | 100.00% | — | 5 |
| openai/gpt-oss-20b | 1552 ms | — | 100.00% | — | 5 |
| meta-llama/llama-3.3-70b-instruct | 1853 ms | — | 100.00% | — | 4 |
| openai/gpt-oss-120b | 2317 ms | 47 tok/s n=2 | 100.00% | — | 6 |
AkashML performance history · Full provider & model leaderboard.
Models served by AkashML.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Endpoints | Prompt | Completion | Routes |
|---|---|---|---|---|---|---|
deepseek/deepseek-v4-flash-0731DeepSeek: DeepSeek V4 Flash 0731 |
— | 1,310,720 | 1 | $0.1477/1M | $0.2954/1M | prepaid |
meta-llama/llama-3.3-70b-instructMeta: Llama 3.3 70B Instruct |
— | 131,072 | 1 | $0.211/1M | $0.5486/1M | prepaid |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 105#63 | 131,072 | 1 | $0.039035/1M | $0.51695/1M | prepaid |
openai/gpt-oss-20bOpenAI: gpt-oss-20b |
IQ 100#79 | 131,072 | 1 | $0.03165/1M | $0.13715/1M | prepaid |
qwen/qwen3.6-35b-a3bQwen: Qwen3.6 35B A3B |
IQ 100#80 | 262,144 | 1 | $0.1477/1M | $1.055/1M | prepaid |
qwen/qwen3.8-27bQwen: Qwen3.8 27B |
IQ 112#46 | 1,000,000 | 1 | $0.47475/1M | $3.376/1M | prepaid |
Questions
Does AkashML have zero data retention?
TrustedRouter does not currently mark AkashML as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is AkashML end-to-end encrypted?
TrustedRouter does not currently mark AkashML as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which AkashML models are available through TrustedRouter?
This page currently lists 6 public AkashML models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.