Doubleword API pricing
Updated
Doubleword lists standard per-token prices for 16 models. The cheapest is DeepSeek V4 Flash 0731 at USD 0.09 input and USD 0.18 output per 1M tokens; the dearest is Kimi K3 at USD 3 / USD 15. It publishes cached-input prices for 14 of them, plus batch and flex / spot tiers (no priority). Checked 2026-11-16.
- Models with a standard price
- 16
- Median input / output
- USD 0.33 / USD 2.05
- Cached-input prices
- 14 of 16
- Cheapest host for
- 1 of 16 shared models
Which models is Doubleword the cheapest provider for?
Of the 16 models that Doubleword and at least one other provider both price at the standard tier, Doubleword has the lowest price for 1, ranked on a blend of 3 input tokens to 1 output token. It also ties the lowest price for 1 more, where another provider is listed first.
| Model | Doubleword input / output | Next cheapest | Saving on 3:1 blend | Providers |
|---|---|---|---|---|
| Muse Glimmer 30B | USD 0.11 / USD 0.32 | Featherless USD 0.30 / USD 1.10 | 68% | 4 |
How does Doubleword price the most widely hosted models?
The 6 models Doubleword sells that the most other providers also sell, with Doubleword's rank among them on the 3:1 blend.
| Model | Doubleword | Rank | Cheapest |
|---|---|---|---|
| GLM 5.3 | USD 1.40 / USD 4.40 | 10 of 31 | DeepInfra USD 0.5625 / USD 2.50 |
| 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 1017 | USD 0.15 / USD 0.60 | 4 of 23 | Sail Research USD 0.09 / USD 0.30 |
| DeepSeek V4.1 Flash | USD 0.15 / USD 0.60 | 5 of 23 | Relace USD 0.07 / USD 0.50 |
| Kimi K3 | USD 3 / USD 15 | 6 of 23 | Chutes USD 1.85 / USD 9.50 |
| GLM 5.2 | USD 0.93 / USD 3 | 4 of 21 | DeepInfra USD 0.5625 / USD 1.80 |
Which model makers does Doubleword sell?
Doubleword prices models from 7 makers. DeepSeek leads with 4 models. Standard prices, USD per 1M input / output tokens.
| Maker | Models | Cheapest model | Median input / output |
|---|---|---|---|
| DeepSeek | 4 | DeepSeek V4 Flash 0731 USD 0.09 / USD 0.18 | USD 0.15 / USD 0.60 |
| Qwen | 3 | Qwen3.6 35B A3B USD 0.14 / USD 1 | USD 0.21 / USD 1.90 |
| Z.ai | 3 | GLM 5.3 Flash USD 0.15 / USD 0.50 | USD 0.93 / USD 3 |
| Meta | 2 | Muse Glimmer 30B USD 0.11 / USD 0.32 | USD 0.68 / USD 2.285 |
| Moonshot AI | 2 | Kimi K3.1 Pro USD 2 / USD 10 | USD 2.50 / USD 12.50 |
| 1 | Gemma 4 31B USD 0.12 / USD 0.35 | — | |
| NVIDIA | 1 | NVIDIA Nemotron 3 Ultra USD 0.50 / USD 2.20 | — |
Doubleword price list
USD per 1M tokens: 48 prices for 16 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 Doubleword is cheaper. Of 10 hosted model prices with a maker price to compare, 5 are below the maker's and 0 above.
| Model | Tier | Input | Cached | Output | Context | vs maker | Source |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | standard batch flex / spot | USD 0.09 USD 0.05 USD 0.07 | USD 0.02 USD 0.01 USD 0.01 | USD 0.18 USD 0.09 USD 0.14 | not stated | — | source |
| DeepSeek V4 Pro 0813 | standard batch flex / spot | USD 1.32 USD 0.66 USD 0.99 | USD 0.13 USD 0.07 USD 0.10 | USD 3.96 USD 1.98 USD 2.97 | not stated | same | source |
| DeepSeek V4.1 Flash | standard batch flex / spot | USD 0.15 USD 0.08 USD 0.12 | USD 0.01 USD 0.01 USD 0.01 | USD 0.60 USD 0.30 USD 0.48 | not stated | −50% | source |
| DeepSeek V4.1 Flash 1017 | standard batch flex / spot | USD 0.15 USD 0.08 USD 0.12 | USD 0.01 USD 0.01 USD 0.01 | USD 0.60 USD 0.30 USD 0.48 | not stated | −50% | source |
| Gemma 4 31B | standard batch flex / spot | USD 0.12 USD 0.06 USD 0.09 | USD 0.12 USD 0.06 USD 0.09 | USD 0.35 USD 0.18 USD 0.26 | not stated | — | source |
| GLM 5.2 | standard batch flex / spot | USD 0.93 USD 0.47 USD 0.70 | USD 0.19 USD 0.09 USD 0.14 | USD 3 USD 1.50 USD 2.25 | not stated | −33% | source |
| GLM 5.3 | standard batch flex / spot | USD 1.40 USD 0.70 USD 1.05 | USD 0.28 USD 0.14 USD 0.21 | USD 4.40 USD 2.20 USD 3.30 | not stated | same | source |
| GLM 5.3 Flash | standard batch flex / spot | USD 0.15 USD 0.08 USD 0.11 | USD 0.03 USD 0.02 USD 0.02 | USD 0.50 USD 0.25 USD 0.38 | not stated | same | source |
| Kimi K3 | standard batch flex / spot | USD 3 USD 1.50 USD 2.15 | USD 0.30 USD 0.15 USD 0.22 | USD 15 USD 7.50 USD 11.25 | not stated | same | source |
| Kimi K3.1 Pro | standard batch flex / spot | USD 2 USD 1 USD 1.40 | USD 0.20 USD 0.10 USD 0.14 | USD 10 USD 5 USD 7 | not stated | same | source |
| Muse Glimmer 30B | standard batch flex / spot | USD 0.11 USD 0.05 USD 0.07 | USD 0.01 USD 0.01 USD 0.01 | USD 0.32 USD 0.15 USD 0.24 | not stated | — | source |
| Muse Spark Open | standard batch flex / spot | USD 1.25 USD 1.25 USD 1.25 | USD 0.15 USD 0.15 USD 0.15 | USD 4.25 USD 4.25 USD 4.25 | not stated | — | source |
| NVIDIA Nemotron 3 Ultra | standard batch flex / spot | USD 0.50 USD 0.25 USD 0.38 | USD 0.13 USD 0.06 USD 0.10 | USD 2.20 USD 1.10 USD 1.65 | not stated | — | source |
| Qwen3 VL 235B A22B Instruct | standard batch flex / spot | USD 0.21 USD 0.11 USD 0.16 | USD 0.12 USD 0.06 USD 0.09 | USD 1.90 USD 0.95 USD 1.43 | not stated | — | source |
| Qwen3.6 35B A3B | standard batch flex / spot | USD 0.14 USD 0.07 USD 0.11 | USD 0.14 USD 0.07 USD 0.11 | USD 1 USD 0.50 USD 0.75 | not stated | −58% | source |
| Qwen3.8 27B | standard batch flex / spot | USD 0.45 USD 0.25 USD 0.35 | USD 0.04 USD 0.02 USD 0.04 | USD 3 USD 1.50 USD 2.25 | not stated | −3% | source |
- Cached "—" means Doubleword's page shows no cache price for that row; budget cached tokens at the input price.
- Context "not stated": Doubleword'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 Doubleword publish?
- batch (16 rows). Across 16 models with both prices, the median batch price is 50% below standard (range 55% below standard to the same as standard). Doubleword row note: “Batch (24h) priority.”
- flex / spot (16 rows). Across 16 models with both prices, the median flex / spot price is 24% below standard (range 36% below standard to the same as standard). Doubleword row note: “Async priority.”
Cached input: 14 of 16 standard prices include a cache-read price, a median 11% of the input price. What cached input means.
What we recorded about Doubleword's pricing page: Prices from the "Active Models" table on Doubleword's Models & Pricing page (per 1M tokens, "input / cache read / output" for each priority: Realtime, Async, Batch (24h)). Realtime rows are standard. Excluded: Qwen3.5 35B A3B dottxt (a fine-tune), LightOnOCR 2 1B bbox soup (OCR), Qwen3 Embedding 8B (embeddings) and the models listed under "Shut Down". No context length is shown in the table.
Is Doubleword cheaper than the model makers' own APIs?
Mostly yes. Of 10 standard prices for models whose maker sells its own API, 5 are below the maker's price, 0 above and 5 the same, on the 3:1 blend. The median difference is 2% below the maker. The biggest saving is Qwen3.6 35B A3B, 58% below Alibaba Cloud.
BroadNet Inference and Doubleword
BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference also serves 3 models that Doubleword prices: DeepSeek V4.1 Flash at USD 0.175 / USD 0.52 against Doubleword's USD 0.15 / USD 0.60 (BroadNet is cheaper on the 3:1 blend); Qwen3.8 27B at USD 0.175 / USD 2.17 against Doubleword's USD 0.45 / USD 3 (BroadNet is cheaper on the 3:1 blend); GLM 5.3 at USD 0.78 / USD 3.46 against Doubleword's USD 1.40 / USD 4.40 (BroadNet is cheaper on the 3:1 blend). BroadNet prices are from its rate card, synced 2026-11-14. BroadNet Inference pricing.
More on Doubleword
- Doubleword'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 Doubleword API cost per token?
Doubleword's standard prices run from USD 0.09 input and USD 0.18 output per 1M tokens (DeepSeek V4 Flash 0731) to USD 3 / USD 15 (Kimi K3). The median across 16 standard prices is USD 0.33 input and USD 2.05 output per 1M, which is USD 0.00000033 per input token. Input, cached input and output are billed separately.
What is the cheapest model on Doubleword?
DeepSeek V4 Flash 0731, at USD 0.09 input and USD 0.18 output per 1M tokens (USD 0.1125 on a 3:1 input-to-output blend). The cheapest from other makers: Qwen3.6 35B A3B (Qwen) at USD 0.14 / USD 1; GLM 5.3 Flash (Z.ai) at USD 0.15 / USD 0.50; Muse Glimmer 30B (Meta) at USD 0.11 / USD 0.32.
Is Doubleword cheaper than other providers?
It depends on the model. Of 16 models that other providers also price, Doubleword is the cheapest standard price for 1, for example Muse Glimmer 30B; it ties the lowest price, without beating it, for 1 more; another provider is cheaper for 14; and it is the dearest for none. Its median rank is 4 of a median 18 providers, on a 3:1 input-to-output blend.
Does Doubleword have batch, cached or priority pricing?
Cached input: yes, for 14 of 16 standard prices, at a median 11% of the input price. Other tiers: batch on 16 rows (median input 50% below standard); flex / spot on 16 rows (median input 24% below standard).
How much does a chatbot cost per month on Doubleword?
For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 7.56 on DeepSeek V4 Flash 0731, USD 48.24 on Qwen3 VL 235B A22B Instruct (the middle of Doubleword's list) and USD 394.20 on Kimi K3. Try your own numbers.