DeepSeek logo

DeepSeek V3 324

Deprecated
Pricing & Specs API
Free REST API for prices, specs and benchmarks
DeepSeek V3 324 is DeepSeek's language model with a 164K context window and up to 66K output tokens, available from 9 providers, starting at $0.2 / 1M input and $0.4 / 1M output. The March 2024 update of DeepSeek V3 (V3-0324), a 671B MoE LLM representing an improved iteration over the original V3 release.
Specifications
Canonical IDdeepseek-v3-324
TypeLanguage
StatusDeprecated
CreatorDeepSeekDeepSeek
Providers
Context Window164K tokens
Max Output66K tokens
Input ModalitiesText
Output ModalitiesText
Reasoning Effortsdefault
Parameters685B
HuggingFace Likes3,101
HuggingFace Downloads (30d)617,973
HuggingFace Downloads (all-time)4,563,386
Deprecation Date
Benchmarks
Intelligence Index
#322
Coding Index
#150
Math Index
#180
MMLU-Pro
#87
GPQA
#313
HLE
#416
LiveCodeBench
#187
AIME
#62
IFBench
#254
Time to First Token
#391
SciCode
#194
MATH-500
#56
AIME 2025
#180
LCR
#281
TerminalBench Hard
#187
TAU2
#196
Output TPS
#160

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities5/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
Azure AI Foundry logo
Azure AI Foundry
azure_ai/deepseek-v3-0324
$1.14$4.56N/A
Baseten
baseten/deepseek-ai/DeepSeek-V3-0324
$0.77$0.77N/A
Crusoe
crusoe/deepseek-ai/DeepSeek-V3-0324
$1.50$1.50N/A
DeepInfra logo
DeepInfra
deepinfra/deepseek-ai/DeepSeek-V3-0324
$0.24$0.9$0.135
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/deepseek-v3-0324
$0.9$0.9N/A
GMI Cloud logo
GMI Cloud
gmi/deepseek-ai/DeepSeek-V3-0324
$0.28$0.88N/A
Hyperbolic logo
Hyperbolic
hyperbolic/deepseek-ai/DeepSeek-V3-0324
$0.4$0.4N/A
Lambda logo
Lambda
lambda_ai/deepseek-v3-0324
$0.2$0.6N/A
Novita logo
Novita
novita/deepseek/deepseek-v3-0324
$0.27$1.12$0.135

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host DeepSeek V3 324, ranked by cheapest on-demand price. The model needs about 1643 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
p6-b300.48xlargeAWS8× B3002149 GB$142.42/hr

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
DeepSeek V3.2164K$0.259$0.380Deprecated
DeepSeek V3.2 Speciale164K$0.580$1.68Available
DeepSeek V3.2 Thinking128K$0.620$1.85Available
DeepSeek V3.2 Exp164K$0.270$0.410Deprecated
DeepSeek V3.2 Exp Reasoning————Available
DeepSeek V3.2 Exp————Available
DeepSeek V3.1 Terminus164K$0.270$1.00Deprecated
DeepSeek V3.1164K$0.250$0.950Deprecated
DeepSeek V3.1 671B—164K——Available
DeepSeek V3164K$0.200$0.200Deprecated
DeepSeek V3 324—164K$0.200$0.400Current

Model IDs

accounts/fireworks/models/deepseek-v3-0324
azure_ai/deepseek-v3-0324
baseten/deepseek-ai/DeepSeek-V3-0324
crusoe/deepseek-ai/DeepSeek-V3-0324
deepinfra/deepseek-ai/DeepSeek-V3-0324
deepseek-ai/DeepSeek-V3-0324
deepseek-v3-0324
deepseek-v3-324
deepseek/deepseek-v3-0324
fireworks_ai/accounts/fireworks/models/deepseek-v3-0324
gmi/deepseek-ai/DeepSeek-V3-0324
hyperbolic/deepseek-ai/DeepSeek-V3-0324
lambda_ai/deepseek-v3-0324
nebius/deepseek-ai/DeepSeek-V3-0324
novita/deepseek/deepseek-v3-0324
sambanova/DeepSeek-V3-0324
wandb/deepseek-ai/DeepSeek-V3-0324