NEAR AI Cloud API pricing
Updated
NEAR AI Cloud lists standard prices for 6 models. The cheapest is GLM 5.3 Flash at USD 0.08 input and USD 0.50 output per 1M tokens; the dearest is DeepSeek V4.1 Flash 1017 Abliterated at USD 0.30 / USD 1.20. It publishes cached-input prices for all of them, and lists no per-model batch, flex or priority prices on the pages we read.
- Models with a standard price
- 6
- Median input / output
- USD 0.16 / USD 1.15
- Cached-input prices
- 6 of 6
- Cheapest host for
- 1 of 6 shared models
Which models is NEAR AI Cloud the cheapest provider for?
Of the 6 models that NEAR AI Cloud and at least one other provider both price at the standard tier, NEAR AI Cloud has the lowest price for 1, ranked on a blend of 3 input tokens to 1 output token. It is the dearest for 1.
| Model | NEAR AI Cloud input / output | Next cheapest | Saving on 3:1 blend | Providers |
|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 Abliterated | USD 0.30 / USD 1.20 | Venice USD 0.375 / USD 1.50 | 20% | 2 |
How does NEAR AI Cloud price the most widely hosted models?
The 6 models NEAR AI Cloud sells that the most other providers also sell, with NEAR AI Cloud's rank among them on the 3:1 blend.
| Model | NEAR AI Cloud | Rank | Cheapest |
|---|---|---|---|
| GLM 5.3 Flash | USD 0.08 / USD 0.50 | 4 of 29 | GMI Cloud USD 0.075 / USD 0.25 |
| DeepSeek V4.1 Flash 1017 | USD 0.30 / USD 1.20 | 12 of 23 | Sail Research USD 0.09 / USD 0.30 |
| Qwen3.8 27B | USD 0.04 / USD 1.35 | 2 of 19 | Chutes USD 0.039 / USD 1.25 |
| Qwen3.6 35B A3B | USD 0.17 / USD 1.10 | 7 of 12 | CoreWeave Forge USD 0.10 / USD 0.89 |
| Qwen3 VL 30B A3B Instruct | USD 0.15 / USD 0.55 | 2 of 5 | Featherless USD 0.15 / USD 0.50 |
| DeepSeek V4.1 Flash 1017 Abliterated | USD 0.30 / USD 1.20 | 1 of 2 | NEAR AI Cloud (this page) |
Which model makers does NEAR AI Cloud sell?
NEAR AI Cloud prices models from 3 makers. Qwen leads with 3 models. Standard prices, USD per 1M input / output tokens.
| Maker | Models | Cheapest model | Median input / output |
|---|---|---|---|
| Qwen | 3 | Qwen3 VL 30B A3B Instruct USD 0.15 / USD 0.55 | USD 0.15 / USD 1.10 |
| DeepSeek | 2 | DeepSeek V4.1 Flash 1017 USD 0.30 / USD 1.20 | USD 0.30 / USD 1.20 |
| Z.ai | 1 | GLM 5.3 Flash USD 0.08 / USD 0.50 | — |
NEAR AI Cloud price list
USD per 1M tokens: 6 prices for 6 models, one row per model with any other service tiers stacked under the standard price. Sources checked 2026-11-16 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 NEAR AI Cloud is cheaper. Of 4 hosted model prices with a maker price to compare, 3 are below the maker's and 0 above.
| Model | Tier | Input | Cached | Output | Context | vs maker | Source |
|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | standard | USD 0.30 | USD 0.006 | USD 1.20 | 1,048,576 | same | source |
| DeepSeek V4.1 Flash 1017 Abliterated | standard | USD 0.30 | USD 0.006 | USD 1.20 | 1,048,576 | — | source |
| GLM 5.3 Flash | standard | USD 0.08 | USD 0.012 | USD 0.50 | 1,048,576 | −22% | source |
| Qwen3 VL 30B A3B Instruct | standard | USD 0.15 | USD 0.03 | USD 0.55 | 16,384 | — | source |
| Qwen3.6 35B A3B | standard | USD 0.17 | USD 0.056 | USD 1.10 | 262,144 | −52% | source |
| Qwen3.8 27B | standard | USD 0.04 | USD 0.018 | USD 1.35 | 262,144 | −67% | source |
- Cached "—" means NEAR AI Cloud's page shows no cache price for that row; budget cached tokens at the input price.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What service tiers does NEAR AI Cloud publish?
Standard prices only: NEAR AI Cloud publishes no per-model batch, flex, priority or fast price on the pages we read.
Cached input: 6 of 6 standard prices include a cache-read price, a median 18% of the input price. What cached input means.
What we recorded about NEAR AI Cloud's pricing page: Prices from the model table on near.ai/models ("Prices in USD per million tokens"; columns Input, Output, Cache read, Context). Included: models whose Provider is "NEAR AI" (Privacy tier "Private TEE": "Runs in a secure enclave on NEAR AI's infrastructure"). Excluded: "Incognito" models (the model "runs at the provider", i.e. resold Anthropic, OpenAI, Google, xAI, Moonshot, DeepSeek and Qwen APIs), "Attested 3P" models (run by a third party), image, embedding, rerank and transcription models, and Qwen 3.8 27B Abliterated (no matching model page). Context as shown ("1.05M" read as 1,048,576, "262K" as 262,144, "16K" as 16,384). No model IDs are shown.
Is NEAR AI Cloud cheaper than the model makers' own APIs?
Mostly yes. Of 4 standard prices for models whose maker sells its own API, 3 are below the maker's price, 0 above and 1 the same, on the 3:1 blend. The median difference is 37% below the maker. The biggest saving is Qwen3.8 27B, 67% below Alibaba Cloud.
BroadNet Inference and NEAR AI Cloud
BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference also serves 1 model that NEAR AI Cloud prices: Qwen3.8 27B at USD 0.175 / USD 2.17 against NEAR AI Cloud's USD 0.04 / USD 1.35 (NEAR AI Cloud is cheaper on the 3:1 blend). BroadNet prices are from its rate card, synced 2026-11-14. BroadNet Inference pricing.
More on NEAR AI Cloud
- NEAR AI Cloud's own pricing page (the source; checked 2026-11-16)
- All 50 providers compared · Cheapest LLM APIs right now · Download every price (CSV, JSON)
Questions
How much does the NEAR AI Cloud API cost per token?
NEAR AI Cloud's standard prices run from USD 0.08 input and USD 0.50 output per 1M tokens (GLM 5.3 Flash) to USD 0.30 / USD 1.20 (DeepSeek V4.1 Flash 1017 Abliterated). The median across 6 standard prices is USD 0.16 input and USD 1.15 output per 1M, which is USD 0.00000016 per input token. Input, cached input and output are billed separately.
What is the cheapest model on NEAR AI Cloud?
GLM 5.3 Flash, at USD 0.08 input and USD 0.50 output per 1M tokens (USD 0.185 on a 3:1 input-to-output blend). The cheapest from other makers: Qwen3 VL 30B A3B Instruct (Qwen) at USD 0.15 / USD 0.55; DeepSeek V4.1 Flash 1017 (DeepSeek) at USD 0.30 / USD 1.20.
Is NEAR AI Cloud cheaper than other providers?
It depends on the model. Of 6 models that other providers also price, NEAR AI Cloud is the cheapest standard price for 1, for example DeepSeek V4.1 Flash 1017 Abliterated; another provider is cheaper for 5; and it is the dearest for 1. Its median rank is 3 of a median 15.5 providers, on a 3:1 input-to-output blend.
Does NEAR AI Cloud have batch, cached or priority pricing?
Cached input: yes, for 6 of 6 standard prices, at a median 18% 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 NEAR AI Cloud?
For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 12.53 on GLM 5.3 Flash, USD 26.71 on Qwen3.8 27B (the middle of NEAR AI Cloud's list) and USD 32.72 on DeepSeek V4.1 Flash 1017 Abliterated. Try your own numbers.