Choose a model to open its comparison page.
DeepSeek OCR API pricing covers 26 API providers, from $0.0049/M to $28.57/M. DeepSeek OCR free API options are available from 1 provider.
DeepSeek OCR is an OCR model, specialized in extracting and understanding text from images and documents.
Compare DeepSeek OCR API pricing across 25 providers. Prices range from $0.0049/M to $28.57/M. ModelPool offers the lowest rate at $0.0049/M. 1 provider offers free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | deepseek-ocr | default | $0.100/request | - | — | — | — | |
L1 100% | deepseek-ai/DeepSeek-OCR | default | $0.147/M | $0.490/M | — | — | — | |
L1 100% | deepseek-ocr | default | $0.137/M | $0.685/M | — | — | — | |
L1 100% | deepseek-ocr | default | $0.548/M | $1.64/M | — | — | — | |
L1 100% | deepseek-ocr | default | $0.387/M | $1.85/M | — | — | — | |
L1 100% | deepseek-ocr | default | $10.27/M | $20.55/M | — | — | — | |
L1 99% | deepseek-ocr | deepseek | $0.022/M | $0.099/M | — | — | — | |
L1 99% | deepseek-ai/DeepSeek-OCR | default | $28.57/M | $28.57/M | — | — | — | |
L1 97% | deepseek-ocr | default | $0.010/request | - | — | — | — | |
初叶🍂Furry API Free | L1 87% | deepseek-ai/DeepSeek-OCR | free | Free | Free | — | — | — |
L1 79% | deepseek-ocr | 国内模型-deepseek | $0.0049/M | $0.020/M | — | — | — | |
L1 78% | DeepSeek-OCR | default | $0.020/M | $0.020/M | — | — | — | |
L1 100% | deepseek-ocr | default | $0.050/request | - | — | — | — | |
L1 98% | deepseek-ocr | default | $0.450/M | $1.80/M | — | — | — | |
L1 0% | deepseek-ocr | default | $0.016/request | - | — | — | — |
deepseek-v3-2
DeepSeek V3.2 is an upgraded V3-series MoE model with stronger reasoning, coding, and math performance, widely available through OpenAI-compatible API relays.
deepseek-v3
DeepSeek V3 is DeepSeek flagship MoE language model with 671B total parameters, delivering strong performance in reasoning, coding, and multilingual tasks at competitive inference cost.
kimi-k2-5
Moonshot Kimi K2.5 is an open-weight multimodal agent model with native vision and text input, strong coding performance, and a 256K context window.
minimax-m2-5
MiniMax M2.5 is MiniMax's flagship text model for coding and agents, with SOTA-level programming and agentic performance, improved token efficiency, and fast high-TPS API deployment.
deepseek-r1
DeepSeek R1 is a reasoning-focused language model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.
deepseek-v4-flash
DeepSeek V4 Flash is a fast, cost-efficient language model in the DeepSeek V4 family, optimized for low-latency chat, coding assistance, and high-throughput API workloads while retaining strong reasoning quality.
