Doubleword Models
London-based inference provider (TYTN Ltd). Offers flex models at reduced pricing in exchange for slower response times. Account data is stored in an AWS Europe region, but inference runs across a range of GPU providers and some processing may occur outside Europe. Retains API content for operations but does not train on it by default. Requesty routes to 8 Doubleword models starting at $0.10 per 1M input tokens with context windows up to 1.0M tokens. One API key, OpenAI-compatible SDK, no markup.
Flagship model
deepseek-v4-flash:flexIntelligence Index
40.3
Coding Index
56.2
GPQA Diamond
89.4%
Terminal-Bench Hard
35.6%
All Doubleword models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | Coding |
|---|---|---|---|---|---|---|
deepseek-v4-flash:flex | 1.0M | 131K | $0.10 | $0.20 | 🧠 | 56 |
deepseek-v4-flash | 1.0M | 131K | $0.14 | $0.28 | 🧠 | 56 |
deepseek-v4-pro:flex | 1.0M | 131K | $1.31 | $2.75 | 🧠 | 59 |
deepseek-v4-pro | 1.0M | 131K | $1.74 | $3.48 | 🧠 | 59 |
nvidia-nemotron-3-ultra:flex | 262K | 131K | $0.37 | $1.87 | 🧠 | N/A |
glm-5.2:flex | 1.0M | 131K | $1.05 | $3.30 | 🧠 | 69 |
nvidia-nemotron-3-ultra | 262K | 131K | $0.50 | $2.50 | 🧠 | N/A |
glm-5.2 | 1.0M | 131K | $0.70 | $0.70 | 🧠 | 69 |
About Doubleword on Requesty
How many Doubleword models are available through Requesty?
Requesty routes to 8 Doubleword models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest Doubleword model?
The cheapest Doubleword model starts at $0.10 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on Doubleword pricing?
No. Requesty passes through exactly what Doubleword charges. You pay the same per-token rates as going direct, plus you get smart routing, caching, analytics, and one unified API for 400+ models.
Is my data used to train Doubleword models?
Doubleword's terms state that API data is not used for training. See their privacy policy for the authoritative statement.
Where are Doubleword models hosted?
Doubleword models are hosted in 🇬🇧 UK, 🌍 Global inference. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI: filter by region on the Doubleword rows in the models explorer.