# DeepSeek V4.1 Flash API

DeepSeek V4.1 Flash (version DeepSeek-V4.1-Flash-1017) is DeepSeek's Flash-tier model with image input, thinking and non-thinking modes, a 1M-token context window and up to 384K output tokens; list price $0.30 in / $1.20 out per 1M tokens, provider list as at 1 November 2026.

- Provider: DeepSeek
- Model ID: deepseek-flash
- Type: Chat
- Region: Global (provider global routing)
- Context window: 1,000,000 tokens
- Max output: 384,000 tokens
- Modalities: text, vision, tools, reasoning
- Endpoints: OpenAI Chat Completions https://api.seedrise.ai/v1
- Prices checked: 1 November 2026

## Provider list price

Provider list price as at 1 November 2026, per 1M tokens. AUD at a reference rate of 1 USD = 1.53 AUD; invoices use the rate on the day.

| Token type | USD | AUD |
|---|---:|---:|
| Input | 0.30 | 0.46 |
| Output | 1.20 | 1.84 |
| Cached input | 0.006 | 0.009 |

Your Seedrise rate is quoted per account against this list price. Request a rate card: https://seedrise.ai/contact?model=deepseek-flash

The ID deepseek-flash points to DeepSeek-V4.1-Flash-1017 as at 1 November 2026, and the list price shown is DeepSeek's peak-hour rate (off-peak $0.15 in / $0.60 out). Global: runs on the provider's global routing, with no Australian-region option.

## Strengths

- Image input, unlike DeepSeek V4 Pro
- Cache-hit input lists at $0.006 per 1M tokens
- Up to 384K output tokens, with thinking on by default
- JSON output, tool calls and chat prefix completion (beta)

## Typical use cases

- High-volume chat and extraction where cost per call matters
- Reading screenshots, receipts and documents
- Coding assistants and agents on a tight budget
- Batch summarisation of long inputs

## Quickstart

A first request with curl. Replace sk-... with your Seedrise key.

```bash
curl https://api.seedrise.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-flash","messages":[{"role":"user","content":"Hello"}]}'
```

OpenAI SDK, Python:

```python
from openai import OpenAI

client = OpenAI(base_url="https://api.seedrise.ai/v1", api_key="sk-...")

r = client.chat.completions.create(
    model="deepseek-flash",
    messages=[{"role": "user", "content": "Summarise this contract in three bullets."}],
)
print(r.choices[0].message.content)
```

## Where it runs

Global: Served on the provider's global routing.

## Related models

- [DeepSeek V4 Pro](https://seedrise.ai/models/deepseek-v4-pro): US$1.32 input · US$3.96 output per 1M tokens, Global
- [DeepSeek V3.2](https://seedrise.ai/models/deepseek-v3.2): US$0.64 input · US$1.91 output per 1M tokens, AU
- [Qwen3 235B](https://seedrise.ai/models/qwen3-235b): US$0.23 input · US$0.91 output per 1M tokens, AU
- [Qwen3.7 Plus](https://seedrise.ai/models/qwen3.7-plus): US$0.40 input · US$1.60 output per 1M tokens, SG
- [Qwen3.8 Flash](https://seedrise.ai/models/qwen3.8-flash): US$0.15 input · US$0.47 output per 1M tokens, SG

## FAQ

### What is the model ID for DeepSeek V4.1 Flash?

Use deepseek-flash as the model field, with no vendor prefix, on the OpenAI-compatible endpoint at https://api.seedrise.ai/v1. GET /v1/models returns the IDs your key can call.

### How does the Seedrise rate for DeepSeek V4.1 Flash compare to the list price?

DeepSeek's list price as at 1 November 2026 is US$0.30 per 1M input tokens and US$1.20 per 1M output tokens. Seedrise quotes rates per account against the provider's published list price for the same routing. Volume and committed tiers sit below list.

### What is the context window and max output of DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash has a context window of 1,000,000 tokens and a maximum output of 384,000 tokens, per the provider documentation checked on 1 November 2026.

### Can DeepSeek V4.1 Flash run in Australia?

Not at present. DeepSeek V4.1 Flash is served on the provider's global routing. Models marked AU in the model library can be pinned to Sydney or Melbourne on request.

### Which version does deepseek-flash call?

DeepSeek-V4.1-Flash-1017 as at 1 November 2026. DeepSeek moves this name to new Flash versions, so if you need a fixed version, ask for a pinned ID with your rate card where the provider offers one.

### Can DeepSeek V4.1 Flash read images?

Yes. DeepSeek lists vision support for V4.1 Flash, while V4 Pro is text only.

Model names are trademarks of their respective providers.

Source: https://seedrise.ai/models/deepseek-flash