# DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731 pins a dated checkpoint of the V4 Flash weights, the efficiency tier of DeepSeek's V4 series, with the agentic gains that landed after the April preview.

- **Model ID:** `deepseek/deepseek-v4-flash-0731`
- **Type:** chat
- **Providers:** baseten, deepinfra, novita, alibaba, wafer, runware, morph, parasail, togetherai, digitalocean, streamlake, inceptron, relace, boundless, gmicloud
- **Context window:** 1,048,576
- **Maximum output tokens:** 1,048,576
- **Pricing:** $0.0199/1M input tokens, $0.153/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/deepseek-v4-flash-0731

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { streamText } from 'ai'

const result = streamText({
  model: 'deepseek/deepseek-v4-flash-0731',
  prompt: 'Why is the sky blue?'
})
```

## About

DeepSeek V4 Flash 0731 became available on AI Gateway on July 31, 2026 as a dated checkpoint of DeepSeek V4 Flash, the efficiency tier of DeepSeek's V4 generation. The V4 series arrived in April 2026 with two variants: V4 Pro for agentic coding, formal mathematical reasoning, and long-horizon workflows, and V4 Flash for high-volume, latency-sensitive work. V4 Flash performs close to V4 Pro on reasoning and holds up on simpler agent tasks at a smaller parameter size.

This checkpoint carries the updated weights that followed the April preview, and the agentic gains are the reason to pin this checkpoint. On Terminal-Bench, a benchmark that measures how well a model completes real tasks in a terminal, DeepSeek V4 Flash 0731 scores 82.7, up 25.8 points from 56.9 in the April preview. That lands directly on coding-agent work such as fixing failing tests in a repository and opening a pull request.

The V4 architecture combines Compressed Sparse Attention (CSA) with Heavily Compressed Attention (HCA), and uses ManifoldConstrained Hyper-Connections (mHC) in place of standard residual connections. The combination targets efficient inference at the context window of 1.0M tokens. Maximum output is 1.0M tokens per response, which gives long reasoning chains and tool-call sequences room to finish in a single call.

AI Gateway routes DeepSeek V4 Flash 0731 across Baseten, DeepInfra, Novita AI, Alibaba Cloud, Wafer, Runware, Morph, Parasail, Together AI, DigitalOcean, StreamLake, Inceptron, Relace, Boundless, GMICloud, with retries and automatic failover. Provider coverage grew after the updated weights first shipped, so check the list on this page for who serves the checkpoint today. Prefer a specific provider by passing an `order` array under `providerOptions.gateway`, which is also how you route to a provider running a promotional rate while one is active.

Set the model to `deepseek/deepseek-v4-flash-0731` in the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python. Authenticate with an AI Gateway API key or OIDC token, so you don't need a separate DeepSeek platform account. AI Gateway mirrors provider pricing with no markup and adds no platform fee on inference, including for Bring Your Own Key requests.

## What to consider

The `0731` suffix names a dated checkpoint. `deepseek/deepseek-v4-flash-0731` stays on that snapshot of the weights, while `deepseek/deepseek-v4-flash` picks up whatever DeepSeek ships as current. Pin the checkpoint when you need reproducible behavior across deploys and evaluation runs, and use the undated model ID when you want new weights automatically.

Provider coverage differs between the two IDs, including which backing providers offer Zero Data Retention. Check the provider list on this page, and use the `order` option under `providerOptions.gateway` when you need traffic to prefer one provider. Individual providers sometimes run time-limited promotional rates that end on a set date, so read the pricing panel on this page rather than assuming a past rate still applies.

## When to use

### Best For

- **Pinned Production Behavior:** A dated checkpoint holds model behavior steady across deploys and evaluation runs
- **Coding Agent Tasks:** Terminal-Bench gains land on repository work such as fixing tests and opening pull requests
- **High-Volume Short-Form Traffic:** Classification, routing, and extraction pipelines at efficiency-tier pricing
- **Long-Context Workloads:** A context window of 1.0M tokens and up to 1.0M tokens output tokens cover large inputs
- **Provider-Controlled Routing:** The `order` option pins traffic to a preferred provider for cost or compliance reasons

### Consider Alternatives When

- **Automatic Weight Updates:** DeepSeek V4 Flash tracks the current weights with no model ID change on your side
- **Deeper Reasoning Work:** DeepSeek V4 Pro targets complex reasoning, multi-step problem solving, and agentic planning
- **Dedicated Reasoning Specialist:** DeepSeek-R1 remains the open-weights option for extended chain-of-thought workloads

## Best for

- **Pinned Production Behavior:** A dated checkpoint holds model behavior steady across deploys and evaluation runs
- **Coding Agent Tasks:** Terminal-Bench gains land on repository work such as fixing tests and opening pull requests
- **High-Volume Short-Form Traffic:** Classification, routing, and extraction pipelines at efficiency-tier pricing
- **Long-Context Workloads:** A context window of 1.0M tokens and up to 1.0M tokens output tokens cover large inputs
- **Provider-Controlled Routing:** The `order` option pins traffic to a preferred provider for cost or compliance reasons

## Consider alternatives

- **Automatic Weight Updates:** DeepSeek V4 Flash tracks the current weights with no model ID change on your side
- **Deeper Reasoning Work:** DeepSeek V4 Pro targets complex reasoning, multi-step problem solving, and agentic planning
- **Dedicated Reasoning Specialist:** DeepSeek-R1 remains the open-weights option for extended chain-of-thought workloads

## Frequently asked questions

### What does the `0731` suffix in `deepseek/deepseek-v4-flash-0731` mean?

It names a dated checkpoint of the weights. `deepseek/deepseek-v4-flash-0731` stays on that snapshot, while `deepseek/deepseek-v4-flash` picks up whatever DeepSeek ships as current.

### How does DeepSeek V4 Flash 0731 compare with the April preview weights?

DeepSeek V4 Flash 0731 has notably stronger agentic capabilities. On Terminal-Bench, DeepSeek V4 Flash 0731 scores 82.7, up 25.8 points from 56.9 in the April preview.

### When should I pin DeepSeek V4 Flash 0731 instead of using `deepseek/deepseek-v4-flash`?

Pin DeepSeek V4 Flash 0731 when you need reproducible behavior, such as stable evaluation baselines or a release you don't want shifting underneath you. Use the undated model ID when you'd rather pick up new weights without a code change.

### What is the context window and maximum output for DeepSeek V4 Flash 0731?

The context window is 1.0M tokens and the maximum output is 1.0M tokens per response.

### What does the V4 hybrid attention architecture change for inference?

DeepSeek V4 Flash 0731 combines Compressed Sparse Attention (CSA) with Heavily Compressed Attention (HCA), and uses ManifoldConstrained Hyper-Connections (mHC) in place of standard residual connections. The combination targets efficient inference across the full context window of 1.0M tokens.

### Does DeepSeek V4 Flash 0731 work in a coding agent?

Yes. The updated weights target agentic work such as fixing failing tests and opening pull requests. Run `vercel ai-gateway setup` to connect your agents to AI Gateway, then select `deepseek/deepseek-v4-flash-0731` in the agent's model configuration.

### How do I route DeepSeek V4 Flash 0731 to a specific provider?

Pass an `order` array under `providerOptions.gateway` with the provider slugs you want tried first. If none of them can serve the request, AI Gateway falls back to the remaining providers.

### What is the pricing for DeepSeek V4 Flash 0731?

AI Gateway mirrors provider pricing with no markup and adds no platform fee on inference. Rates are listed on this page and shift when providers update their pricing. Individual providers sometimes run promotional rates that expire on a set date and then return to standard rates.

### Does DeepSeek V4 Flash 0731 support zero data retention?

Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

### How do I call DeepSeek V4 Flash 0731 through AI Gateway?

Set the model to `deepseek/deepseek-v4-flash-0731` in the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python. Authenticate with an AI Gateway API key or OIDC token, and AI Gateway handles retries and failover across `baseten`, `deepinfra`, `novita`, `alibaba`, `wafer`, `runware`, `morph`, `parasail`, `togetherai`, `digitalocean`, `streamlake`, `inceptron`, `relace`, `boundless`, `gmicloud`.

## Links

- [Model page](https://vercel.com/ai-gateway/models/deepseek-v4-flash-0731)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://app.baseten.co/model-apis/deepseek-ai/DeepSeek-V4-Flash-0731)