AkashML API pricing
Updated
AkashML lists standard prices for 7 models. The cheapest is GPT OSS 20B at USD 0.018 input and USD 0.09 output per 1M tokens; the dearest is Kimi K3.1 Pro at USD 1.75 / USD 10. It publishes cached-input prices for 5 of them, and lists no per-model batch, flex or priority prices on the pages we read.
- Models with a standard price
- 7
- Median input / output
- USD 0.19 / USD 0.90
- Cached-input prices
- 5 of 7
- Cheapest host for
- 1 of 7 shared models
Which models is AkashML the cheapest provider for?
Of the 7 models that AkashML and at least one other provider both price at the standard tier, AkashML has the lowest price for 1, ranked on a blend of 3 input tokens to 1 output token.
| Model | AkashML input / output | Next cheapest | Saving on 3:1 blend | Providers |
|---|---|---|---|---|
| GPT OSS 20B (promo) | USD 0.018 / USD 0.09 | CoreWeave Forge USD 0.03 / USD 0.13 | 35% | 10 |
How does AkashML price the most widely hosted models?
The 6 models AkashML sells that the most other providers also sell, with AkashML's rank among them on the 3:1 blend.
| Model | AkashML | Rank | Cheapest |
|---|---|---|---|
| GLM 5.3 | USD 0.19 / USD 4.40 | 3 of 24 | DeepInfra USD 0.5625 / USD 2.50 |
| OpenAI GPT OSS 120B | USD 0.037 / USD 0.187 | 3 of 21 | CoreWeave Forge USD 0.03 / USD 0.17 |
| Qwen3.8 27B | USD 0.225 / USD 1.98 | 4 of 15 | Chutes USD 0.039 / USD 1.25 |
| Llama 3.3 70B | USD 0.20 / USD 0.52 | 3 of 14 | DeepInfra USD 0.10 / USD 0.32 |
| Kimi K3.1 Pro | USD 1.75 / USD 10 | 2 of 13 | DeepInfra USD 1.90 / USD 9.50 |
| GPT OSS 20B | USD 0.018 / USD 0.09 | 1 of 10 | AkashML (this page) |
Which model makers does AkashML sell?
AkashML prices models from 5 makers. OpenAI leads with 2 models. Standard prices, USD per 1M input / output tokens.
| Maker | Models | Cheapest model | Median input / output |
|---|---|---|---|
| OpenAI | 2 | GPT OSS 20B USD 0.018 / USD 0.09 | USD 0.0275 / USD 0.1385 |
| Qwen | 2 | Qwen3.6 35B A3B USD 0.10 / USD 0.90 | USD 0.1625 / USD 1.44 |
| Meta | 1 | Llama 3.3 70B USD 0.20 / USD 0.52 | — |
| Moonshot AI | 1 | Kimi K3.1 Pro USD 1.75 / USD 10 | — |
| Z.ai | 1 | GLM 5.3 USD 0.19 / USD 4.40 | — |
AkashML price list
USD per 1M tokens: 7 prices for 7 models, one row per model with any other service tiers stacked under the standard price. Sources checked 2026-11-15 unless a row says otherwise. "vs maker" compares a standard price with the model maker's own API on the 3:1 blend; a minus means AkashML is cheaper. Of 4 hosted model prices with a maker price to compare, 4 are below the maker's and 0 above.
| Model | Tier | Input | Cached | Output | Context | vs maker | Source |
|---|---|---|---|---|---|---|---|
| GLM 5.3promo | standard | USD 0.19 | USD 0.19 | USD 4.40 | 1,048,576 | −42% | source |
| GPT OSS 20Bpromo | standard | USD 0.018 | USD 0.009 | USD 0.09 | 131,072 | — | source |
| Kimi K3.1 Propromo | standard | USD 1.75 | USD 0.18 | USD 10 | 1,048,576 | −5% | source |
| Llama 3.3 70B | standard | USD 0.20 | USD 0.10 | USD 0.52 | 131,072 | — | source |
| OpenAI GPT OSS 120Bpromo | standard | USD 0.037 | USD 0.037 | USD 0.187 | 131,072 | — | source |
| Qwen3.6 35B A3Bpromo | standard | USD 0.10 | USD 0.05 | USD 0.90 | 262,144 | −64% | source |
| Qwen3.8 27Bpromo | standard | USD 0.225 | USD 0.05 | USD 1.98 | 262,144 | −41% | source |
- Cached "—" means AkashML's page shows no cache price for that row; budget cached tokens at the input price.
- Promo: AkashML's page describes 6 prices as promotional or discounted; they can end without notice. Each model page has the list price where the source gives one.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What service tiers does AkashML publish?
Standard prices only: AkashML publishes no per-model batch, flex, priority or fast price on the pages we read.
Cached input: 5 of 7 standard prices include a cache-read price, a median 50% of the input price. What cached input means.
What we recorded about AkashML's pricing page: Prices from the "Model Pricing" table on akashml.com and each model page (input, output, cache read per 1M tokens). Only models with a price are included; models marked "Coming Soon" have no price. Context from each model page ("1M" read as 1,048,576, "128K" as 131,072, "262K" as 262,144).
Is AkashML cheaper than the model makers' own APIs?
Mostly yes. Of 4 standard prices for models whose maker sells its own API, 4 are below the maker's price, 0 above and 0 the same, on the 3:1 blend. The median difference is 42% below the maker. The biggest saving is Qwen3.6 35B A3B, 64% below Alibaba Cloud.
BroadNet Inference and AkashML
BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference also serves 2 models that AkashML prices: Qwen3.8 27B at USD 0.175 / USD 2.17 against AkashML's USD 0.225 / USD 1.98 (AkashML is cheaper on the 3:1 blend); GLM 5.3 at USD 0.78 / USD 3.46 against AkashML's USD 0.19 / USD 4.40 (AkashML is cheaper on the 3:1 blend). BroadNet prices are from its rate card, synced 2026-11-14. BroadNet Inference pricing.
More on AkashML
- AkashML's own pricing page (the source; checked 2026-11-15)
- All 41 providers compared · Cheapest LLM APIs right now · Download every price (CSV, JSON)
Questions
How much does the AkashML API cost per token?
AkashML's standard prices run from USD 0.018 input and USD 0.09 output per 1M tokens (GPT OSS 20B) to USD 1.75 / USD 10 (Kimi K3.1 Pro). The median across 7 standard prices is USD 0.19 input and USD 0.90 output per 1M, which is USD 0.00000019 per input token. Input, cached input and output are billed separately.
What is the cheapest model on AkashML?
GPT OSS 20B, at USD 0.018 input and USD 0.09 output per 1M tokens (USD 0.036 on a 3:1 input-to-output blend), a promotional price. The cheapest from other makers: Qwen3.6 35B A3B (Qwen) at USD 0.10 / USD 0.90; Llama 3.3 70B (Meta) at USD 0.20 / USD 0.52; Kimi K3.1 Pro (Moonshot AI) at USD 1.75 / USD 10.
Is AkashML cheaper than other providers?
It depends on the model. Of 7 models that other providers also price, AkashML is the cheapest standard price for 1, for example GPT OSS 20B; another provider is cheaper for 6; and it is the dearest for none. Its median rank is 3 of a median 14 providers, on a 3:1 input-to-output blend.
Does AkashML have batch, cached or priority pricing?
Cached input: yes, for 5 of 7 standard prices, at a median 50% of the input price. No batch, flex or priority prices are listed per model on the pages we read.
How much does a chatbot cost per month on AkashML?
For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 2.75 on GPT OSS 20B, USD 22.50 on Qwen3.6 35B A3B (the middle of AkashML's list) and USD 252.72 on Kimi K3.1 Pro. Try your own numbers.