CtrlAltDebrief

DeepSeek V3 2 Speciale

DeepSeek
Tool useReasoningPrompt caching
Compare DeepSeek V3 2 SpecialeCount tokens for DeepSeek V3 2 Speciale
Context
164K
Max output
164K
Serving providers
1
Cheapest input
$0.58 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Headline indices
Intelligence Index
22.2
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt7%default—
EvalComputeProxy91.3default—
GPQA Diamond87%default—
Humanity's Last Exam26%default—
IFBench64%default—
LiveCodeBench90%default—
Long-Context Reasoning59%default—
MMLU-Pro86%default—
Omniscience-16.5default—
SciCode44%default—
TerminalBench Hard35%default—
τ²-bench0%default—

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
AzureCheapest$0.58$1.681
ComponentUnitStandardBatchCached
Text input/1M tok$0.5800——
Text output/1M tok$1.68——

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.500$1.00$1.50$2.00Dec 16Jun 22$1.68$0.580

Cost calculator

estimate your monthly spend on this model
$250
estimated / month

Model IDs

copy the exact identifier for your platform
azure_ai/deepseek-v3.2-speciale

Frequently asked questions

DeepSeek V3 2 Speciale pricing, context and availability

How much does DeepSeek V3 2 Speciale cost?

DeepSeek V3 2 Speciale costs $0.58 per 1M input tokens and $1.68 per 1M output tokens at its cheapest provider via Azure.

What is the context window of DeepSeek V3 2 Speciale?

DeepSeek V3 2 Speciale accepts up to 164K tokens of context and can return up to 164K output tokens.

What can DeepSeek V3 2 Speciale do?

DeepSeek V3 2 Speciale supports tool use, reasoning and prompt caching.

Other DeepSeek models

compare pricing across the DeepSeek lineup
R1$0.40/1M · 12 providersDeepSeek V3 0324$0.20/1M · 11 providersDeepSeek$0.20/1M · 9 providersR1 Distill Llama 70B$0.20/1M · 9 providersR1 0528$0.20/1M · 8 providersDeepSeek V3 1$0.27/1M · 7 providersDeepSeek V3.2$0.27/1M · 6 providersDeepSeek R1 Distill Qwen 32B$0.15/1M · 5 providers
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI