DeepSeek model

DeepSeek V4 Flash 0731 API

deepseek/deepseek-v4-flash-0731 pins DeepSeek V4 Flash to its 0731 snapshot: $0.45 per million input tokens and $1.33 per million output tokens. The rolling deepseek/deepseek-v4-flash id on the same gateway is listed at $0.14 / $0.28 — the snapshot costs roughly 3x on input. Pay the pin premium only if you need reproducible behavior across a fixed model version; otherwise call the live id. No context window is published for either id.

Read quickstartEstimate cost
DeepSeekPlatform curatedCatalog
Thinking
Input price$0.45 / 1M tokens
Output price$1.33 / 1M tokens
Context length1M tokens
Max output8.2k tokens

What is DeepSeek V4 Flash 0731 API in NextModel?

deepseek/deepseek-v4-flash-0731 pins DeepSeek V4 Flash to its 0731 snapshot: $0.45 per million input tokens and $1.33 per million output tokens. The rolling deepseek/deepseek-v4-flash id on the same gateway is listed at $0.14 / $0.28 — the snapshot costs roughly 3x on input. Pay the pin premium only if you need reproducible behavior across a fixed model version; otherwise call the live id. No context window is published for either id.

DeepSeek-V4-Flash-0731 via NextModel: 1M-token context; $0.45 / 1M tokens in / $1.33 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

Best use cases

  • You need reproducible, date-pinned behavior for evals or regulated workflows and accept $0.45 / $1.33.
  • You are comparing fixed V4 Flash snapshots against each other over time.
  • You accept paying roughly 3x the live id's input price for the pin.

When not to use

  • You just want DeepSeek V4 Flash: the rolling deepseek-v4-flash id is listed at $0.14 / $0.28.
  • You need a published context window: neither id publishes one.
  • Your budget cannot absorb $1.33 per million output tokens.

OpenAI-compatible code example

request.sh
curl https://api.nextmodel.app/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $NEXTMODEL_API_KEY" \
  -d '{"model":"deepseek/deepseek-v4-flash-0731","messages":[{"role":"user","content":"Reply with OK."}]}'

Switching models only changes the model field.

Try it in the playground

Similar alternatives

DeepSeekCatalog

Deepseek-V4-Pro-0813

Deepseek-V4-Pro-0813 via NextModel: 1M-token context; $1.33 / 1M tokens in / $3.98 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

$1.33 / 1M tokensInput$3.98 / 1M tokensOutput1MContext
Best forChinese Q&A, general chat
StreamingTool callingJSON modeLong context
Platform curatedCurated and maintained in the NextModel catalog
View details
DeepSeekCatalog

DeepSeek-V4-Flash

DeepSeek-V4-Flash via NextModel: 1M-token context; $0.14 / 1M tokens in / $0.28 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

$0.14 / 1M tokensInput$0.28 / 1M tokensOutput1MContext
Best forChinese Q&A, general chat
StreamingTool callingJSON modeLong context
Platform curatedCurated and maintained in the NextModel catalog
View details
DeepSeekCatalog

DeepSeek-V4-Pro

DeepSeek-V4-Pro via NextModel: 1M-token context; $1.65 / 1M tokens in / $3.31 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

$1.65 / 1M tokensInput$3.31 / 1M tokensOutput1MContext
Best forChinese Q&A, general chat
StreamingTool callingJSON modeLong context
Platform curatedCurated and maintained in the NextModel catalog
View details

Compare DeepSeek-V4-Flash-0731

DeepSeek-V4-Flash-0731 vs Deepseek-V4-Pro-0813DeepSeek-V4-Flash-0731 vs DeepSeek-V4-FlashDeepSeek-V4-Flash-0731 vs DeepSeek-V4-ProDeepSeek-V4-Flash-0731 vs Qwen3.7 FlashDeepSeek-V4-Flash-0731 vs Gemini 3.5 Flash-Lite

Reading

Articles that explain DeepSeek-V4-Flash-0731

FAQ

DeepSeek-V4-Flash-0731 API questions

What model id do I send for the 0731 snapshot?

Send deepseek/deepseek-v4-flash-0731 to https://api.nextmodel.app/v1 with your OpenAI SDK. If that id is missing from /v1/models, the page is stale.

Why is this more expensive than deepseek-v4-flash?

The pinned 0731 snapshot is listed at $0.45 / $1.33 per 1M tokens while the rolling deepseek-v4-flash id is $0.14 / $0.28. You pay a premium for version pinning, not for extra capability the catalog can verify.

Is a context window published?

No. The catalog snapshot publishes no context window for this id.

Start now

Ready to start building?

Passwordless signup, pay-as-you-go billing, and one OpenAI-compatible endpoint for every model. Create your key and send your first request in minutes.

Get your API keyRead the quickstart