Relace API pricing
Updated
Relace lists standard per-token prices for 8 models. The cheapest is DeepSeek V4 Flash at USD 0.07 input and USD 0.14 output per 1M tokens; the dearest is Kimi K3 at USD 2 / USD 14. It publishes cached-input prices for all of them, and lists no per-model batch, flex or priority prices on the pages we read. Checked 2026-11-16.
- Models with a standard price
- 8
- Median input / output
- USD 0.625 / USD 2.20
- Cached-input prices
- 8 of 8
- Cheapest host for
- 3 of 8 shared models
Which models is Relace the cheapest provider for?
Of the 8 models that Relace and at least one other provider both price at the standard tier, Relace has the lowest price for 3, ranked on a blend of 3 input tokens to 1 output token.
| Model | Relace input / output | Next cheapest | Saving on 3:1 blend | Providers |
|---|---|---|---|---|
| DeepSeek V4.1 Flash | USD 0.07 / USD 0.50 | River USD 0.12 / USD 0.48 | 15% | 23 |
| DeepSeek V4 Pro | USD 0.50 / USD 2 | GMI Cloud USD 0.957 / USD 1.914 | 27% | 12 |
| DeepSeek V4 Flash | USD 0.07 / USD 0.14 | DeepInfra USD 0.09 / USD 0.18 | 22% | 10 |
How does Relace price the most widely hosted models?
The 6 models Relace sells that the most other providers also sell, with Relace's rank among them on the 3:1 blend.
| Model | Relace | Rank | Cheapest |
|---|---|---|---|
| GLM 5.3 | USD 0.75 / USD 2.40 | 3 of 31 | DeepInfra USD 0.5625 / USD 2.50 |
| GLM 5.3 Flash | USD 0.075 / USD 0.50 | 3 of 29 | GMI Cloud USD 0.075 / USD 0.25 |
| DeepSeek V4.1 Flash | USD 0.07 / USD 0.50 | 1 of 23 | Relace (this page) |
| Kimi K3 | USD 2 / USD 14 | 3 of 23 | Chutes USD 1.85 / USD 9.50 |
| GLM 5.2 | USD 0.75 / USD 2.40 | 3 of 21 | DeepInfra USD 0.5625 / USD 1.80 |
| Kimi K3.1 Pro | USD 1.60 / USD 11.20 | 4 of 20 | Sail Research USD 1.50 / USD 10 |
Which model makers does Relace sell?
Relace prices models from 3 makers. DeepSeek leads with 3 models. Standard prices, USD per 1M input / output tokens.
| Maker | Models | Cheapest model | Median input / output |
|---|---|---|---|
| DeepSeek | 3 | DeepSeek V4 Flash USD 0.07 / USD 0.14 | USD 0.07 / USD 0.50 |
| Z.ai | 3 | GLM 5.3 Flash USD 0.075 / USD 0.50 | USD 0.75 / USD 2.40 |
| Moonshot AI | 2 | Kimi K3.1 Pro USD 1.60 / USD 11.20 | USD 1.80 / USD 12.60 |
Relace price list
USD per 1M tokens: 8 prices for 8 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 Relace is cheaper. Of 7 hosted model prices with a maker price to compare, 6 are below the maker's and 0 above.
| Model | Tier | Input | Cached | Output | Context | vs maker | Source |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash | standard | USD 0.07 | USD 0.014 | USD 0.14 | not stated | — | source |
| DeepSeek V4 Pro | standard | USD 0.50 | USD 0.05 | USD 2 | not stated | −56% | source |
| DeepSeek V4.1 Flash | standard | USD 0.07 | USD 0.008 | USD 0.50 | not stated | −66% | source |
| GLM 5.2 | standard | USD 0.75 | USD 0.075 | USD 2.40 | not stated | −46% | source |
| GLM 5.3 | standard | USD 0.75 | USD 0.075 | USD 2.40 | not stated | −46% | source |
| GLM 5.3 Flash | standard | USD 0.075 | USD 0.0075 | USD 0.50 | not stated | −24% | source |
| Kimi K3 | standard | USD 2 | USD 0.30 | USD 14 | not stated | −17% | source |
| Kimi K3.1 Pro | standard | USD 1.60 | USD 0.24 | USD 11.20 | not stated | same | source |
- Cached "—" means Relace's page shows no cache price for that row; budget cached tokens at the input price.
- Context "not stated": Relace's pricing page does not give context windows.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What service tiers does Relace publish?
Standard prices only: Relace publishes no per-model batch, flex, priority or fast price on the pages we read.
Cached input: 8 of 8 standard prices include a cache-read price, a median 11% of the input price. What cached input means.
What we recorded about Relace's pricing page: Prices from the table on relace.ai/pricing ("Prices are in US dollars per million tokens"; columns Input, Cached input, Output). The page states "Prices as of November 4, 2026" and "We reprice often; the price returned by the API at the time of your request is the one you pay." No model IDs, context or precision are shown.
Is Relace cheaper than the model makers' own APIs?
Mostly yes. Of 7 standard prices for models whose maker sells its own API, 6 are below the maker's price, 0 above and 1 the same, on the 3:1 blend. The median difference is 46% below the maker. The biggest saving is DeepSeek V4.1 Flash, 66% below DeepSeek.
BroadNet Inference and Relace
BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference also serves 2 models that Relace prices: DeepSeek V4.1 Flash at USD 0.175 / USD 0.52 against Relace's USD 0.07 / USD 0.50 (Relace is cheaper on the 3:1 blend); GLM 5.3 at USD 0.78 / USD 3.46 against Relace's USD 0.75 / USD 2.40 (Relace is cheaper on the 3:1 blend). BroadNet prices are from its rate card, synced 2026-11-14. BroadNet Inference pricing.
More on Relace
- Relace'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 Relace API cost per token?
Relace's standard prices run from USD 0.07 input and USD 0.14 output per 1M tokens (DeepSeek V4 Flash) to USD 2 / USD 14 (Kimi K3). The median across 8 standard prices is USD 0.625 input and USD 2.20 output per 1M, which is USD 0.000000625 per input token. Input, cached input and output are billed separately.
What is the cheapest model on Relace?
DeepSeek V4 Flash, at USD 0.07 input and USD 0.14 output per 1M tokens (USD 0.0875 on a 3:1 input-to-output blend). The cheapest from other makers: GLM 5.3 Flash (Z.ai) at USD 0.075 / USD 0.50; Kimi K3.1 Pro (Moonshot AI) at USD 1.60 / USD 11.20.
Is Relace cheaper than other providers?
It depends on the model. Of 8 models that other providers also price, Relace is the cheapest standard price for 3, for example DeepSeek V4.1 Flash, DeepSeek V4 Pro and DeepSeek V4 Flash; another provider is cheaper for 5; and it is the dearest for none. Its median rank is 3 of a median 22 providers, on a 3:1 input-to-output blend.
Does Relace have batch, cached or priority pricing?
Cached input: yes, for 8 of 8 standard prices, at a median 11% 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 Relace?
For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 5.80 on DeepSeek V4 Flash, USD 56.70 on DeepSeek V4 Pro (the middle of Relace's list) and USD 340.20 on Kimi K3. Try your own numbers.