DeepSeek model

DeepSeek V4 PRO API

Send deepseek/deepseek-v4-pro when the Chinese job is worth 1.65 / 3.31. The catalog still does not publish a context window or a CacheSafety row. If you have not compared that bill to Flash at 0.14 / 0.28, do not make PRO the default.

Read quickstartEstimate cost
DeepSeekPlatform curatedCatalog
ThinkingFunction Calling
Input price$1.65 / 1M tokens
Output price$3.31 / 1M tokens
Context length1M tokens
Max output8.2k tokens

What is DeepSeek V4 PRO API in NextModel?

Send deepseek/deepseek-v4-pro when the Chinese job is worth 1.65 / 3.31. The catalog still does not publish a context window or a CacheSafety row. If you have not compared that bill to Flash at 0.14 / 0.28, do not make PRO the default.

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.

Best use cases

  • Explicit PRO spend on Chinese streaming.
  • A paid DeepSeek id behind Flash on the same gateway.
  • Workloads that already rejected V3.2 at 0.29 / 0.44.

When not to use

  • You wanted cheap Chinese tokens. That is Flash.
  • You need a published context window. PRO does not have one either.
  • You need tools or vision. Those flags are not listed.

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-pro","messages":[{"role":"user","content":"Reply with OK."}]}'

Switching models only changes the model field.

Try it in the playground

Similar alternatives

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
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-Pro

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

Reading

Articles that explain DeepSeek-V4-Pro

FAQ

DeepSeek-V4-Pro API questions

What model id do I send for DeepSeek V4 PRO?

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

How much more than Flash?

1.65 / 3.31 versus 0.14 / 0.28. About 12x on input. Context unpublished on both.

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