Reka API pricing
Updated
Reka lists standard per-token prices for 7 models. The cheapest is Reka Edge 2603 at USD 0.10 input and USD 0.10 output per 1M tokens; the dearest is Qwen3.8 27B at USD 0.20 / USD 2.50. It publishes cached-input prices for 5 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
- 7
- Median input / output
- USD 0.15 / USD 0.66
- Cached-input prices
- 5 of 7
- Cheapest host for
- 0 of 5 shared models
Which models is Reka the cheapest provider for?
None. Every one of the 5 models that Reka shares with other providers is cheaper elsewhere at the standard tier. The closest is Qwen3.6 27B, where Reka ranks 2 of 8. It is the dearest provider for 1.
How does Reka price the most widely hosted models?
The 5 models Reka sells that the most other providers also sell, with Reka's rank among them on the 3:1 blend.
| Model | Reka | Rank | Cheapest |
|---|---|---|---|
| GLM 5.3 Flash | USD 0.15 / USD 0.50 | 8 of 29 | GMI Cloud USD 0.075 / USD 0.25 |
| DeepSeek V4.1 Flash | USD 0.30 / USD 1.20 | 10 of 23 | Relace USD 0.07 / USD 0.50 |
| Qwen3.8 27B | USD 0.20 / USD 2.50 | 8 of 19 | Chutes USD 0.039 / USD 1.25 |
| DeepSeek V4 Flash | USD 0.11 / USD 0.66 | 9 of 10 | Relace USD 0.07 / USD 0.14 |
| Qwen3.6 27B | USD 0.29 / USD 1.95 | 2 of 8 | Chutes USD 0.25 / USD 2 |
Which model makers does Reka sell?
Reka prices models from 4 makers. DeepSeek leads with 2 models. Standard prices, USD per 1M input / output tokens.
| Maker | Models | Cheapest model | Median input / output |
|---|---|---|---|
| DeepSeek | 2 | DeepSeek V4 Flash USD 0.11 / USD 0.66 | USD 0.205 / USD 0.93 |
| Qwen | 2 | Qwen3.6 27B USD 0.29 / USD 1.95 | USD 0.245 / USD 2.225 |
| Reka | 2 | Reka Edge 2603 USD 0.10 / USD 0.10 | USD 0.10 / USD 0.15 |
| Z.ai | 1 | GLM 5.3 Flash USD 0.15 / USD 0.50 | — |
Reka 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 2026-11-16 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 Reka is cheaper. Of 4 hosted model prices with a maker price to compare, 2 are below the maker's and 0 above.
| Model | Tier | Input | Cached | Output | Context | vs maker | Source |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash | standard | USD 0.11 | USD 0.007 | USD 0.66 | 262,144 | — | source |
| DeepSeek V4.1 Flash | standard | USD 0.30 | USD 0.006 | USD 1.20 | 1,048,576 | same | source |
| GLM 5.3 Flash | standard | USD 0.15 | USD 0.015 | USD 0.50 | 1,048,576 | same | source |
| Qwen3.6 27B | standard | USD 0.29 | USD 0.029 | USD 1.95 | 262,144 | −48% | source |
| Qwen3.8 27B | standard | USD 0.20 | USD 0.05 | USD 2.50 | 262,144 | −31% | source |
| Reka Edge 2603 | standard | USD 0.10 | — | USD 0.10 | 16,384 | own model | source |
| Reka Flash 3 | standard | USD 0.10 | — | USD 0.20 | 65,536 | own model | source |
- Cached "—" means Reka'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 Reka publish?
Standard prices only: Reka 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 10% of the input price. What cached input means.
What we recorded about Reka's pricing page: Prices from the model cards on developer.reka.ai/models, linked from Reka's API pricing page (docs.reka.ai/pricing: "The model catalog on developer.reka.ai lists the current input, output and cached-input price for every model"). Reka's own models (Reka Flash 3, Reka Edge 2603) are maker rows; the open-weight models from other makers are described on their cards as "hosted by Reka" and are host rows. Context from each card ("262k" read as 262,144, "1M" as 1,048,576, "64k" as 65,536, "16k" as 16,384). Reka Vision (video and image search APIs) has separate pricing and is excluded.
Is Reka cheaper than the model makers' own APIs?
Mostly yes. Of 4 standard prices for models whose maker sells its own API, 2 are below the maker's price, 0 above and 2 the same, on the 3:1 blend. The median difference is 16% below the maker. The biggest saving is Qwen3.6 27B, 48% below Alibaba Cloud.
BroadNet Inference and Reka
BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference also serves 2 models that Reka prices: DeepSeek V4.1 Flash at USD 0.175 / USD 0.52 against Reka's USD 0.30 / USD 1.20 (BroadNet is cheaper on the 3:1 blend); Qwen3.8 27B at USD 0.175 / USD 2.17 against Reka's USD 0.20 / USD 2.50 (BroadNet is cheaper on the 3:1 blend). BroadNet prices are from its rate card, synced 2026-11-14. BroadNet Inference pricing.
More on Reka
- Reka'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 Reka API cost per token?
Reka's standard prices run from USD 0.10 input and USD 0.10 output per 1M tokens (Reka Edge 2603) to USD 0.20 / USD 2.50 (Qwen3.8 27B). The median across 7 standard prices is USD 0.15 input and USD 0.66 output per 1M, which is USD 0.00000015 per input token. Input, cached input and output are billed separately.
What is the cheapest model on Reka?
Reka Edge 2603, at USD 0.10 input and USD 0.10 output per 1M tokens (USD 0.10 on a 3:1 input-to-output blend). The cheapest from other makers: DeepSeek V4 Flash (DeepSeek) at USD 0.11 / USD 0.66; Qwen3.6 27B (Qwen) at USD 0.29 / USD 1.95; GLM 5.3 Flash (Z.ai) at USD 0.15 / USD 0.50.
Is Reka cheaper than other providers?
It depends on the model. Of 5 models that other providers also price, Reka is the cheapest standard price for none; another provider is cheaper for 5; and it is the dearest for 1. Its median rank is 8 of a median 19 providers, on a 3:1 input-to-output blend.
Does Reka have batch, cached or priority pricing?
Cached input: yes, for 5 of 7 standard prices, at a median 10% 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 Reka?
For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 10.80 on Reka Edge 2603, USD 16.22 on DeepSeek V4 Flash (the middle of Reka's list) and USD 54.90 on Qwen3.8 27B. Try your own numbers.