# DeepSeek V4 Flash

DeepSeek V4 Flash is a text generation model from DeepSeek, available through the Impossibl API. Its published context window is 1,000,000 tokens. The advertised input rate is $0.19 per million input tokens. The advertised output rate is $0.51 per million output tokens.

- Model identifier: ` deepseek/deepseek-v4-flash `
- Creator: DeepSeek
- Model type: Text generation
- Canonical model page: [DeepSeek V4 Flash](<https://impossibl.com/deepseek/deepseek-v4-flash>)
- API availability: Listed as serving through Impossibl.
- Creator release date: 2026-04-24

## Capabilities and limits

- Context window: 1,000,000 tokens
- Maximum output tokens: Not published in the public catalog; this is separate from the context window.
- Inputs: text
- Outputs: text
- Tool calling: Not published

## API access

Use ` deepseek/deepseek-v4-flash ` as the model identifier through the Impossibl API.

Published API endpoints:

- ` /v1/chat/completions `

[API quickstart](<https://impossibl.com/docs/agent-quickstart>) · [Models and billing documentation](<https://impossibl.com/docs/models>)

## Published API prices

All rates are in USD. An unpublished rate is unknown, not zero. Workspace-specific pricing, taxes, balance-purchase fees, billing adjustments, and tool charges can affect the amount paid.

| Usage | Published base rate | Billing unit |
| --- | --- | --- |
| Input | $0.19 | per million input tokens |
| Output | $0.51 | per million output tokens |
| Cache read | $0.028 | per million cached input tokens |
| Cache write (default retention) | Not published | per million tokens |
| Cache write (one-hour retention) | Not published | per million tokens |
| Audio input | Not published | per million audio input tokens |

## Independent benchmarks

Source: [Artificial Analysis](<https://artificialanalysis.ai/>). Last checked: 2026-09-11T11:52:20.926Z.
Configurations are evaluated separately. API scores retain their original units. Unmeasured scores are omitted.

### DeepSeek V4 Flash 0731 (Reasoning, Max Effort)

Source: [Evaluation source](<https://artificialanalysis.ai/models/deepseek-v4-flash>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 34.53 |
| Omniscience Index | -14.28 |
| GPQA | 90.81% |
| Humanity’s Last Exam | 38.55% |
| SciCode | 50.35% |
| CritPt | 16.57% |
| Terminal-Bench v2.1 | 78.65% |
| Terminal-Bench v4.0 | 12.12% |
| AA-LCR | 79.67% |
| Multilingual LCR | 13.33% |
| GDPval Elo | 1467.78 |
| GDP.pdf All-pass | 11.00% |
| AutomationBench Partial | 53.97% |
| Tau Banking | 39.38% |
| coding index (API) | 69.1 |
| agentic index (API) | 41.7 |
| intelligence index (API) | 34.5 |

### DeepSeek V4 Flash Vision (Reasoning, Max Effort)

Source: [Evaluation source](<https://artificialanalysis.ai/models/deepseek-v4-flash-vision>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 35.01 |
| Omniscience Index | -17.63 |
| GPQA | 91.31% |
| Humanity’s Last Exam | 34.48% |
| SciCode | 49.65% |
| CritPt | 10.86% |
| Terminal-Bench v2.1 | 74.16% |
| Terminal-Bench v4.0 | 12.12% |
| AA-LCR | 81.33% |
| GDPval Elo | 1577.21 |
| GDP.pdf All-pass | 12.00% |
| AutomationBench Partial | 47.47% |
| MMMU-Pro | 74.80% |
| Tau Banking | 41.03% |
| coding index (API) | 65 |
| agentic index (API) | 48.1 |
| intelligence index (API) | 35 |

Full benchmark data and breakdowns: [Complete benchmark snapshot](<https://api.impossibl.com/v1/models/deepseek/deepseek-v4-flash/benchmarks>).


## Availability and retirement

The model is listed as serving. No retirement is announced in the current public catalog.

## Frequently asked questions

### What is DeepSeek V4 Flash?

DeepSeek V4 Flash is a text-generation model from DeepSeek, available through the Impossibl API.

### How much does DeepSeek V4 Flash cost?

DeepSeek V4 Flash costs $0.19 per million input tokens and $0.51 per million output tokens through the Impossibl API. Cache reads cost $0.028 per million tokens. All rates are in USD.

### What is the context length of DeepSeek V4 Flash?

DeepSeek V4 Flash has a 1,000,000-token context window through the Impossibl API.

### What inputs and outputs does DeepSeek V4 Flash support?

DeepSeek V4 Flash accepts text as input. DeepSeek V4 Flash returns text.

### How do I use DeepSeek V4 Flash through an API?

DeepSeek V4 Flash is available through the Impossibl API. Use deepseek/deepseek-v4-flash as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.

### When was DeepSeek V4 Flash released?

DeepSeek released DeepSeek V4 Flash on April 24, 2026.

Sources: [Creator release announcement](<https://api-docs.deepseek.com/updates/>)

## Sources and related links

Prices, limits, capabilities, endpoints, and availability come from the public Impossibl catalog. Creator documentation supplies descriptions and release dates where available; it does not override the published API offering.

- [Public Impossibl model catalog](<https://api.impossibl.com/v1/models>)
- [Full model directory as JSON](<https://impossibl.com/models.json>)
- [DeepSeek V4 Flash: model details and pricing](<https://impossibl.com/deepseek/deepseek-v4-flash>)
- [Model directory](<https://impossibl.com/models>)