DeepSeek model

DeepSeek V4 Flash API

Send deepseek/deepseek-v4-flash when Chinese streaming cost is the constraint. Listed price is 0.14 / 0.28. The catalog lists a 1,000,000-token context window for this id, and there is no CacheSafety row. V3.2 is 0.29 / 0.44, still unpublished context.

Read quickstartEstimate cost
DeepSeekPlatform curatedCatalog
ThinkingFunction Calling
Input price$0.14 / 1M tokens
Output price$0.28 / 1M tokens
Context length1M tokens
Max output8.2k tokens

What is DeepSeek V4 Flash API in NextModel?

Send deepseek/deepseek-v4-flash when Chinese streaming cost is the constraint. Listed price is 0.14 / 0.28. The catalog lists a 1,000,000-token context window for this id, and there is no CacheSafety row. V3.2 is 0.29 / 0.44, still unpublished context.

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.

Best use cases

  • High-volume Chinese chat where 0.14 input matters.
  • A cheap DeepSeek id before paying V4 PRO at 1.65 / 3.31.
  • Thinking and tool work. The catalog lists Thinking and Function Calling, not vision.

When not to use

  • You need a context window beyond 1,000,000 tokens. That is this id's published limit.
  • You need JSON or vision. Those flags are not listed.
  • You need cache scores. None exist for this id.

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","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

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
MoonshotaiCatalog

Kimi-K2.6

Kimi-K2.6 via NextModel: 256k-token context; $0.9 / 1M tokens in / $3.72 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

$0.9 / 1M tokensInput$3.72 / 1M tokensOutput256kContext
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
View details
OpenAICatalog

GPT-5.5

GPT-5.5 via NextModel: 1M-token context; Starting at $5 / 1M tokens in / $30 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.

Starting at $5 / 1M tokensInput$30 / 1M tokensOutput1MContext
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
View details

Compare DeepSeek-V4-Flash

DeepSeek-V4-Flash vs DeepSeek-V4-ProDeepSeek-V4-Flash vs Kimi-K2.6DeepSeek-V4-Flash vs GPT-5.5DeepSeek-V4-Flash vs Qwen3.6 FlashDeepSeek-V4-Flash vs DeepSeek-V4-Flash-0731

Reading

Articles that explain DeepSeek-V4-Flash

FAQ

DeepSeek-V4-Flash API questions

What model id do I send for DeepSeek V4 Flash?

Send deepseek/deepseek-v4-flash to https://api.nextmodel.app/v1.

How cheap versus V3.2?

Flash 0.14 / 0.28 with a 1,000,000-token window. V3.2 0.29 / 0.44.

CacheSafety?

Unpublished for this exact 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