Models

DeepSeek-OCR vs DeepSeek-V3-Fast

Output tokens cost $0.02 per million on DeepSeek-OCR and $2.24 per million on DeepSeek-V3-Fast. Input tokens cost $0.02 per million on DeepSeek-OCR and $0.56 per million on DeepSeek-V3-Fast. Cached input tokens are billed at $0.02 per million on DeepSeek-OCR and $0.56 per million on DeepSeek-V3-Fast. Context lengths are 8,000 tokens on DeepSeek-OCR and 32,000 tokens on DeepSeek-V3-Fast. Time to first token (TTFT) measured on AIHubMix is 1.7s on DeepSeek-OCR and 1.5s on DeepSeek-V3-Fast. Measured output throughput is 105.2 tok/s on DeepSeek-OCR and 150.0 tok/s on DeepSeek-V3-Fast.

DeepSeekDeepSeek-OCRDeepSeekDeepSeek-V3-Fast
DeepSeek logo
DeepSeek-OCR
DeepSeek · text, image → text

DeepSeek-OCR is a vision-language model launched by DeepSeek AI, focusing on optical character recognition (OCR) and “contextual optical compression.” The model is designed to explore the limits of compressing contextual information from images, efficiently processing documents and converting them into structured text formats such as Markdown. The model requires an image as input.

Input$0.02 /M
Output$0.02 /M
DeepSeek logo
DeepSeek-V3-Fast
DeepSeek · text → text

V3 Ultra-Fast Version,The current price is a limited-time 50% discount and will return to the original price on July 31st. The original price is: input: $0.55/M, output: $2.2/M. The model provider is the Sophnet platform. DeepSeek V3 Fast is a high-TPS, ultra-fast version of DeepSeek V3 0324, featuring full-precision (non-quantized) performance, enhanced code and math capabilities, and faster responses! DeepSeek V3 0324 is a powerful Mixture-of-Experts (MoE) model with a total parameter count of 671B, activating 37B parameters per token. It adopts Multi-Head Latent Attention (MLA) and the DeepSeekMoE architecture to achieve efficient inference and economical training costs. It innovatively implements a load balancing strategy without auxiliary loss and sets multi-token prediction training targets to enhance performance. The model is pre-trained on 14.8 trillion diverse, high-quality tokens and further optimized through supervised fine-tuning and reinforcement learning stages to fully realize its capabilities. Comprehensive evaluations show that DeepSeek V3 outperforms other open-source models and rivals leading closed-source models in performance. The entire training process only requires 2.788M H800 GPU hours and remains highly stable, with no irrecoverable loss spikes or rollbacks.

Input$0.56 /M
Output$2.24 /M

Pricing & Specifications

Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.

DeepSeek-OCR
DeepSeek-V3-Fast
Input /M
$0.02
$0.56
Output /M
$0.02
$2.24
Cache read /M
$0.02
$0.56
Context length
8,000
32,000
Max output
0
32,000
Time to First Token
1.7 s
1.5 s
Throughput
105.2 tok/s
150.0 tok/s
Modalities
textimage
text
Supported Parameters
toolsfunction callingstructured outputs
API Formats

Promotional prices show the discounted rate; see each model page for promotion windows.

Activity Past 30 Days

Daily traffic served through AIHubMix — how demand for each model is trending.

DeepSeek-OCRDeepSeek-V3-Fast

Tokens / day

-

Requests / day

-

Performance Past 3 Days

Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.

DeepSeek-OCRDeepSeek-V3-Fast

Throughput (tok/s)

-

TTFT (s)

-

Uptime (%)

-

Cost calculator

Estimate your monthly bill for the same workload on each model.

DeepSeek-OCR
$1.50 /mo
DeepSeek-V3-Fast
$67.20 /mo

Monthly = daily × 30. Discounted rates applied where a promotion is active.

FAQ

Which is cheaper: DeepSeek-OCR, DeepSeek-V3-Fast?

DeepSeek-OCR: $0.02/M output tokens; DeepSeek-V3-Fast: $2.24/M. Use the cost calculator above to estimate your own workload.

Which responds faster?

DeepSeek-V3-Fast: 1.5s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.

How large is each context window?

DeepSeek-OCR accepts 8,000 and DeepSeek-V3-Fast accepts 32,000 input tokens.

Which one generates tokens faster?

DeepSeek-V3-Fast at 150.0 tok/s and DeepSeek-OCR at 105.2 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.

What inputs and capabilities does each model support?

DeepSeek-OCR accepts text and image input; DeepSeek-V3-Fast accepts text input and supports tool calling, function calling and structured outputs.

Can I call DeepSeek-OCR and DeepSeek-V3-Fast with the same API key?

Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.

Popular comparisons

Related model match-ups readers also look at.