DoublewordDoubleword
Get started

Models & Pricing

Doubleword Batch API is priced per model based on token usage. Costs are calculated separately for input tokens (the content you send) and output tokens (the content generated by the model).

Upcoming Model Shutdowns: 30 October 2026

A number of older models are scheduled for shutdown on 30 October 2026. From that date they will no longer accept API requests, so update the model ID in your requests to the recommended replacement before then. View models scheduled for shutdown.

If you would like to retain access to a specific model, evaluate an alternative, or discuss a dedicated deployment, contact support@doubleword.ai.

The table below outlines the models we have available and their pricing per 1M tokens. Prices are shown as input / cache read / output. If you are interested in understanding pricing for a model not listed below or if you'd like to request a new model - please reach out to support@doubleword.ai.

Prompt caching

Prompt-caching availability and rates are model-specific. Prices are shown as input / cache read / output for each priority. See the prompt caching guide for setup, TTLs, and write pricing.

Model Catalog

Input / cache read / output per 1M tokens

ModelRealtimeAsyncBatch (24h)
DeepSeek V4.1 Flash 1017$0.15 / $0.01 / $0.60$0.12 / $0.01 / $0.48$0.08 / $0.01 / $0.30
Muse Spark Open$1.25 / $0.15 / $4.25$1.25 / $0.15 / $4.25$1.25 / $0.15 / $4.25
DeepSeek V4.1 Flash$0.15 / $0.01 / $0.60$0.12 / $0.01 / $0.48$0.08 / $0.01 / $0.30
GLM 5.3 Flash$0.15 / $0.03 / $0.50$0.11 / $0.02 / $0.38$0.08 / $0.02 / $0.25
GLM 5.3$1.40 / $0.28 / $4.40$1.05 / $0.21 / $3.30$0.70 / $0.14 / $2.20
Qwen3.8 27B$0.45 / $0.04 / $3.00$0.35 / $0.04 / $2.25$0.25 / $0.02 / $1.50
DeepSeek V4 Pro 0813$1.32 / $0.13 / $3.96$0.99 / $0.10 / $2.97$0.66 / $0.07 / $1.98
Muse Glimmer 30B$0.11 / $0.01 / $0.32$0.07 / $0.01 / $0.24$0.05 / $0.01 / $0.15
DeepSeek V4 Flash 0731$0.09 / $0.02 / $0.18$0.07 / $0.01 / $0.14$0.05 / $0.01 / $0.09
Kimi K3$3.00 / $0.30 / $15.00$2.15 / $0.22 / $11.25$1.50 / $0.15 / $7.50
GLM 5.2$0.93 / $0.19 / $3.00$0.70 / $0.14 / $2.25$0.47 / $0.09 / $1.50
Nemotron 3 Ultra 550B A55B$0.50 / $0.13 / $2.20$0.38 / $0.10 / $1.65$0.25 / $0.06 / $1.10
Qwen3.6 35B A3B$0.14 / $0.14 / $1.00$0.11 / $0.11 / $0.75$0.07 / $0.07 / $0.50
Gemma 4 31B IT$0.12 / $0.12 / $0.35$0.09 / $0.09 / $0.26$0.06 / $0.06 / $0.18
Qwen3.5 35B A3B dottxt$0.35 / $0.20 / $1.20$0.14 / $0.08 / $0.60$0.10 / $0.06 / $0.40
LightOnOCR 2 1B bbox soup—$0.08 / $0.08 / $0.08$0.05 / $0.05 / $0.05
Qwen3 VL 235B A22B Instruct$0.21 / $0.12 / $1.90$0.16 / $0.09 / $1.43$0.11 / $0.06 / $0.95
Qwen3 Embedding 8B$0.04 / $0.04 / $0.00$0.03 / $0.03 / $0.00$0.02 / $0.02 / $0.00

Retrieve model prices through the API

Use a Platform key with GET https://app.doubleword.ai/admin/api/v1/models?include=pricing to retrieve customer-facing prices in tariffs. The OpenAI-compatible GET /v1/models endpoint uses an Inference key to list available model IDs and does not return prices.

See Inference keys and platform keys for the key comparison and a request example, or the Models API reference for model discovery.

Models & Pricing | Doubleword Inference API | Doubleword Docs