OpenAI compatible API · Attested · Public status

DeepSeek: DeepSeek V3.2

Compare every TrustedRouter route for DeepSeek V3.2, including token pricing, context limits, privacy policy, regional availability, measured uptime, and API support.

Verify gateway

Onebase URL to migrate

100sof models and routes

0prompt or output logs. Always.

`deepseek/deepseek-v3.2`

open weights US providers EU-focused DeepSeek

All models

Publisher	DeepSeekdeepseek
AI IQ	IQ 102 #103 on AI IQ
Context	163,840 tokens
Providers	ChutesConfidential ZDR DeepInfra FriendliAI Venice SambaNova DigitalOcean Gradient AI Atlas Cloud IO Intelligence
Credits routes	8 provider routes
Modes	chat open weights US providers EU-focused
Billing	Credits

Current route evidence

Live leaderboard

$0.26375/1MLowest Credits input price

$0.4009/1MLowest Credits output price

not enough dataFastest measured p50 TTFT

not enough dataHighest measured throughput

Recent provider-route uptime spans not enough data across 8 routes and 8 providers. Price comes from the current Credits catalog. Speed and uptime come from routed probes rather than vendor claims.

All route prices All providers

Providers serving this model

Sorted by lowest combined prompt and completion price. Use "provider": {"sort": "throughput"} in the request body (or append :nitro to the model id) to route to the fastest provider instead.

Trust boundary: TR router attestation verifies the TrustedRouter gateway only. Provider policy separately describes the upstream model host's retention, confidential compute, and E2EE posture.

Provider	Input	Cached input	Output	Weight format	TR router attested	Provider policy
Atlas Cloudatlas-cloud	$0.2743/1M	$0.13715/1M	$0.4009/1M	Unknown	yes	privacy unknown
DeepInfradeepinfra	$0.2743/1M	$0.13715/1M	$0.4009/1M	Unknown	yes	no verified privacy claim
Venicevenice	$0.34815/1M	$0.1688/1M	$0.5064/1M	Unknown	yes	no verified privacy claim
DigitalOcean Gradient AIdigitalocean	$0.26375/1M	$0.079125/1M	$0.844/1M	Unknown	yes	privacy unknown
Chuteschutes	$1.055/1M	$0.1055/1M	$1.055/1M	FP8 Published serving configuration, reviewed 2026-09-27. Per-request precision is not verified. Pinned weight configuration declares FP8 quantization; excluded modules can retain higher precision. KV cache: unspecified. Published chute serving code (mutable; hash recorded) Pinned weight configuration	yes	Confidential ZDR
FriendliAIfriendli	$0.5275/1M	$0.26375/1M	$1.5825/1M	Unknown	yes	privacy unknown
IO Intelligenceio-net	$1.49388/1M	$0.74694/1M	$2.50668/1M	Unknown	yes	privacy unknown
SambaNovasambanova	$3.165/1M	Not published	$4.7475/1M	Unknown	yes	privacy unknown

Compare DeepSeek: DeepSeek V3.2

All comparisons

DeepSeek: DeepSeek V3.2 vs Z.ai: GLM 5.239 combined provider routes
DeepSeek: DeepSeek V3.2 vs Z.ai: GLM 5.339 combined provider routes
DeepSeek: DeepSeek V3.2 vs Z.ai: GLM 5.3 Flash39 combined provider routes
DeepSeek: DeepSeek V3.2 vs MoonshotAI: Kimi K335 combined provider routes
DeepSeek: DeepSeek V3.2 vs DeepSeek: DeepSeek V4 Flash 073134 combined provider routes
DeepSeek: DeepSeek V3.2 vs OpenAI: gpt-oss-120b31 combined provider routes

Questions

What model ID should I use for DeepSeek: DeepSeek V3.2?

Use deepseek/deepseek-v3.2 as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.

Which providers serve DeepSeek: DeepSeek V3.2?

TrustedRouter currently lists Chutes, DeepInfra, FriendliAI, Venice, SambaNova, DigitalOcean Gradient AI, Atlas Cloud, and IO Intelligence for DeepSeek: DeepSeek V3.2. Provider availability and routing eligibility can change as catalog and health data update.

How much does DeepSeek: DeepSeek V3.2 cost through TrustedRouter?

The current lowest Credits input price is $0.26375/1M and the lowest Credits output price is $0.4009/1M. Prices are per one million tokens and come from the current route catalog.

How do I require zero data retention for DeepSeek: DeepSeek V3.2?

Set provider.min_privacy to zdr on the request. TrustedRouter considers only routes with a recorded zero-data-retention posture and fails closed if no eligible route remains.