Deepseek Token API Pricing, Top-up, Deals & Updates | Article

Deepseek Token API pricing. DeepSeek-V4-Flash, DeepSeek-V4-Pro and 1 more models. OpenAI-compatible API, Anthropic-compatible API, Claude Code and 3 more tools integrations. Includes cache tiers and rate limits. API key setup, usage quotas, and official entry—is it worth it?

41
Platforms
395+
Models
140+
IDE Tools
3
Deepseek Token API models
¥1.5–3 / ¥4.5–9
Deepseek Token API entry price
View
Vendor details

DeepSeek API Latest Updates

DeepSeek V4-Flash-Vision Exp Launches: Image-Recognizing Multimodal Model Priced Like V4-Flash

Published Updated
ModelDeepSeekV4-Flash-VisionMultimodalModel ReleaseImage RecognitionAPI
Summary

DeepSeek's experimental multimodal model deepseek-v4-flash-vision-exp went live on the API platform on 2026-08-21, adding image understanding on top of V4-Flash text capability. It handles JPEG/PNG/GIF/WebP, reads screenshot text, and analyzes charts, with vision-agent benchmarks leaping to near Opus-4.8. Billing is identical to V4-Flash: images are tokenized by size, capped at 384 tokens each, at ¥1.5 off-peak/¥3 peak input and ¥4.5/¥9 output per 1M tokens, concurrency 2500. This covers how to pass images, how billing works, official benchmarks, and the limits to watch.

DeepSeek opened its eyes today. On 2026-08-21, the experimental multimodal model DeepSeek-V4-Flash-Vision-Exp went live on the DeepSeek API platform — set model='deepseek-v4-flash-vision-exp' and it works (source). The headline is the price: identical to V4-Flash, not a cent more.

What This Model Does

In short: a vision module layered onto V4-Flash's text capability, at the same price. DeepSeek says pure-text capability (agents, reasoning, world knowledge) matches the V4-Flash GA release, while vision-agent benchmarks jump sharply, bringing multimodal agent performance close to Opus-4.8 (source). For developers, DeepSeek's biggest pain point was "can't see images" — especially inside DeepSeek Harness, where uploading a screenshot returned MODEL_DOES_NOT_SUPPORT_IMAGES. That gap is now filled.

It handles JPEG, PNG, GIF, and WebP — formats are detected by actual file content, not the filename or declared MIME type — and can describe images, read text in screenshots, and analyze charts (source).

How to Pass Images

Three ways to send images: base64 inline, external URL, or Files API, all in the standard OpenAI-compatible format. Base64 is simplest for local files, an external URL lets the model fetch a publicly accessible link itself, and the Files API lets you upload once and reference a file_id repeatedly (source). Each has its own limits:

Method Limits Best for
Base64 inline Counts toward the 48 MiB request body limit; 32 MiB per image Local files
External URL URL up to 8192 chars; 32 MiB per image; download within 60s Images with a public link
Files API Up to 64 MiB per image, exempt from the 32 MiB check Large images, reusing one image across requests

DeepSeek also launched a free Files API the same day: upload an image once, reference it by file_id in later requests, and stop re-uploading the same image to save bandwidth (source).

How Billing Works

Images are tokenized by size and billed together with text, capped at 384 tokens each, at exactly V4-Flash rates. Before entering the model, every image is auto-scaled: images smaller than roughly 384×384 total pixels are scaled up proportionally, and larger ones are scaled down to about an 800×800 equivalent — so a 2000×2000 and a 5000×5000 image consume the same tokens, and no single image ever exceeds 384 (source).

Billing (model id = deepseek-v4-flash-vision-exp, per 1M tokens):

Line item Off-peak (CNY) Peak (CNY)
Input (cache hit) ¥0.05 / MTok ¥0.10 / MTok
Input (cache miss) ¥1.5 / MTok ¥3 / MTok
Output ¥4.5 / MTok ¥9 / MTok
Per image ≤ 384 tokens (counted as input)

Peak hours are 9:00–12:00 and 14:00–18:00 Beijing time; everything else is off-peak at half the peak price (source). At peak input, one image caps out at roughly 384 × ¥3/1M ≈ ¥0.001 — effectively free to test with.

How Strong Is the Vision Capability

The official changelog lists the full vision benchmark set — Chartography at 64.3 and ZeroBench at 35.0 — a sharp leap over V4-Flash, with multimodal agent capability "close to Opus-4.8." (source):

Benchmark deepseek-v4-flash-vision-exp
Terminal Bench 2.1 83.9
NL2Repo 57.7
DeepSWE 59.3
DSBench-Hard 63.6
AutomationBench (Public) 25.7
ApexBench (Pass@1) 36.5
Agents' Last Exam 27.3
Chartography 64.3
ZeroBench (Pass@5) 35.0

Code Agent text tasks above were tested with DeepSeek Harness minimal mode, max effort, temperature=1.0, top_p=0.95.

Things to Watch

The model is still experimental. Clear some pitfalls up front (source):

  1. Only this model accepts images. Passing an image to deepseek-v4-flash or deepseek-v4-pro returns a 400 error (This model does not support image); you must use deepseek-v4-flash-vision-exp.
  2. Images may only appear in user messages — putting one in system or assistant messages returns a 400.
  3. FIM completion isn't supported yet; fall back to a text model for completion tasks.
  4. Up to 600 images per request, with 64 MiB total (200 MiB with file_id); max edge 8192px, dropping to 4096px at 15+ images.
  5. An experimental build is better for prototyping than for a core production path.

Which to Pick

Go with this for vision work; stick to V4-Flash / V4-Pro for pure-text tasks. If you're doing screenshot understanding, mixed text-image document parsing, chart analysis, or vision-capable agents, use deepseek-v4-flash-vision-exp at the same cost as Flash. If it's just coding or batch processing, you don't need the vision overhead — deepseek-v4-flash is cheaper.

For a fixed monthly spend, DeepSeek has no official monthly coding plan; consider third-party bundles like Volcengine, CtCloud, and Baidu Qianfan, which meter DeepSeek against plan quota and aren't subject to the official concurrency cap or price hike.

Sources and verification

Last verified

Deepseek Token API FAQ

What does DeepSeek's multimodal deepseek-v4-flash-vision-exp do, and how is it different from V4-Flash?

It layers image understanding on top of V4-Flash's text capability (agents, reasoning, world knowledge) and keeps that text performance unchanged. It can describe images, read screenshot text, and analyze charts across JPEG/PNG/GIF/WebP. DeepSeek confirms pure-text capability is on par with V4-Flash GA, while vision-agent benchmarks leap to near Opus-4.8 — it could only read text before, now it reads images too.

How is image recognition billed on deepseek-v4-flash-vision-exp, and how much can one image cost?

Images are tokenized and billed together with text, capped at 384 tokens each, at exactly V4-Flash rates: ¥1.5 off-peak/¥3 peak input (cache miss), ¥4.5/¥9 output per million tokens, cache-hit input ¥0.05/¥0.10. At peak input, one image caps out at roughly 384 × ¥3/1M ≈ ¥0.001 — negligible.

Which image formats and passing methods does deepseek-v4-flash-vision-exp support, and what are the limits?

JPEG/PNG/GIF/WebP (detected by actual content, not filename or MIME). Three ways to pass images: base64 inline, external URL, or Files API. Limits: up to 600 images per request, 8192px max edge (4096px at 15+ images), 32 MiB per image via base64/URL or 64 MiB via Files API. Images may only appear in user messages, only this model accepts images, and FIM completion isn't supported.

What happens if I pass an image to regular V4-Flash or V4-Pro, and how do I correctly call the vision model?

It returns a 400 error (This model does not support image), because only deepseek-v4-flash-vision-exp accepts images in the V4 family. Set model to deepseek-v4-flash-vision-exp and place the image in a user message, passed via base64, URL, or file_id.

Can this vision model integrate with Claude Code or Cursor, and what do I need to run it?

Yes. It's compatible with Chat Completions, Anthropic (Messages), and Responses formats — Anthropic uses image blocks and Responses uses input_image blocks, so it drops straight into agent frameworks. DeepSeek released Harness 0.1.1 the same day with out-of-the-box support, enabling workflows like screenshot understanding and mixed text-image document handling.
AI Token Plan

Global AI Token Comparison

AI Token Plan is not just a collection of vendor links. It places 41+ domestic and international AI platforms into one comparison framework, covering 395+ model entries plus common plan types such as Token Plans, Coding Plans, IDE Tools and LLM APIs.

When you need to compare AI subscription pricing, coding plan quota, API usage cost or official deal entry points, AI Token Plan brings official prices, plan tiers, usage rules, model capabilities and tool integrations into one place, reducing the need to check multiple vendor sites manually.

Data is continuously organized as vendor pricing pages, plan pages and product documentation change, making the homepage a pricing comparison entry point while detail pages explain whether each vendor plan fits individual developers, team purchasing or long-term API usage.

Prices come from each platform's official site and may change at any time; the official price prevails.

© 2026 AI Token Plan · All rights reserved · First published June 18, 2026 · 64 days running · Sitemap