DeepSeek V3.2
vertex The API that serves this model and sets the prices shown here. deepseek-v3.2-maas The model identifier to send in API requests. LLM Generates text from a prompt, so it can be compared with other LLMs on price and capability. Large The most capable general-purpose tier of a model family. Retired Aug 13, 2026 This model has been retired and can no longer be relied on.Provider: deepseek · served via Vertex
Listed as deprecated on models.dev as of 2026-08-13.
Sticker prices & cost-per-token
List rates as published by Vertex, before any volume or enterprise discounts.
$0.56
$1.68
163,840 tokens
65,536
tokens per response (includes reasoning tokens)
Open weights (permissive license)
MIT
$0.056
Get this data free
Want to stay updated on price changes on this model? Pull this data free (no API key required) here:
curl "https://coolhandlabs.com/api/v2/inference_apis?q%5Bmodel_eq%5D=deepseek-v3.2-maas&q%5Bsource_api_eq%5D=vertex"Pricing History
| Effective | Price |
|---|---|
| Aug 16, 2026 – present | Input cost: $0.56 / 1M, Output cost: $1.68 / 1M, Cached input cost: $0.056 / 1M, Cache creation cost: $0.00 / 1M, 5-minute cache write cost: $0.00 / 1M, 1-hour cache write cost: $0.00 / 1M, Reasoning output cost: $0.00 / 1M, Cache storage cost: $0.00 / 1M/hr |
History
No automated scan changes recorded yet.
| Date | Changed by | What changed |
|---|---|---|
| Aug 16, 2026 | Unknown | Initial record created |
Source
https://models.dev/api.json (models.dev provider 'google-vertex', bulk import 2026-08-13)Comparable models
No comparable models identified yet.
Reliability
No reliability incidents recorded in the last 90 days.
Frequently asked questions
DeepSeek V3.2 (deepseek via Vertex) costs $0.56 per 1M input tokens and $1.68 per 1M output tokens, as last published by Vertex.
DeepSeek V3.2 has a context window of 163,840 tokens (the maximum combined input and output it can handle in a single request).
DeepSeek V3.2 sits in the large size tier. Size tiers run from micro (small enough to run on a device) through small, medium and large to extra large (frontier flagships), and are assigned from the model's family, naming and limits rather than its price.
DeepSeek V3.2 can generate up to 65,536 tokens in a single response. Reasoning (thinking) tokens count toward this limit.
DeepSeek V3.2 accepts pdf and text as input and produces text as output, as recorded in the Coolhand catalog.
Yes — the weights of DeepSeek V3.2 can be downloaded under the MIT license. Check the license terms for any limits on commercial use.
Yes — deepseek deprecated DeepSeek V3.2 on August 13, 2026. Listed as deprecated on models.dev as of 2026-08-13.
deepseek retired DeepSeek V3.2 on August 13, 2026.
Since DeepSeek V3.2 is deprecated, deepseek customers are moving to DeepSeek-R1, DeepSeek-V3.2, and DeepSeek-V3.1.
Call GET https://coolhandlabs.com/api/v2/inference_apis?q[source_api_eq]=vertex&q[model_eq]=deepseek-v3.2-maas — free, no API key required, and scoped to just this model since source_api and model together are unique. See https://coolhandlabs.com/docs for the full REST API reference.
Coolhand also tracks DeepSeek-R1, DeepSeek-R1, DeepSeek-V3.2, DeepSeek-V3.1, DeepSeek V4 Flash, and DeepSeek V4 Flash Free from deepseek. Some may already be deprecated, so check each model's status alongside its current pricing.
| Model | Input cost | Output cost | Context window | Max output tokens | Status |
|---|---|---|---|---|---|
| DeepSeek-R1 via Azure | $1.35/1M $0.0000013500 | $5.40/1M $0.0000054000 | 163,840 | 163,840 |
Deprecated Aug 13, 2026
|
| DeepSeek-R1 via Bedrock | $1.35/1M $0.0000013500 | $5.40/1M $0.0000054000 | 128,000 | 32,768 | Active |
| DeepSeek-V3.2 via Bedrock | $0.62/1M $0.0000006200 | $1.85/1M $0.0000018500 | 163,840 | 81,920 | Active |
| DeepSeek-V3.1 via Bedrock | $0.58/1M $0.0000005800 | $1.68/1M $0.0000016800 | 163,840 | 81,920 | Active |
| DeepSeek V4 Flash via OpenCode | $0.14/1M $0.0000001400 | $0.28/1M $0.0000002800 | 1,000,000 | 384,000 | Active |
| DeepSeek V4 Flash Free via OpenCode | $0.00/1M $0.0000000000 | $0.00/1M $0.0000000000 | 200,000 | 128,000 | Active |
Track LLM pricing and deprecations automatically.
Start free