Get started
DeepSeek
DeepSeek

Models/deepseek V4 PRO

Models/deepseek V4 PRO is a reasoning model by DeepSeek with function calling — designed for complex, multi-step problem solving where accuracy matters more than speed. It supports a 1M token context window with up to 131K tokens of output. Priced at $1.15 per million input tokens and $2.415 per million output tokens. Access Models/deepseek V4 PRO through Inworld Router with OpenAI SDK compatibility, built-in failover, and intelligent routing across providers.
Function CallingReasoningreasoningCapabilityresponseFormatCapability

Step 1 — Create Router

curl --location 'https://api.inworld.ai/router/v1/routers' \ --header 'Authorization: Basic <your-api-key>' \ --header 'Content-Type: application/json' \ --data '{ "name": "compare-frontier-models", "defaultRoute": { "route_id": "default", "variants": [ { "variant": { "variant_id": "inworld/models/deepseek-v4-pro-a", "model_id": "inworld/models/deepseek-v4-pro" }, "weight": 33 }, { "variant": { "variant_id": "deepinfra/deepseek-ai/DeepSeek-R1-0528-b", "model_id": "deepinfra/deepseek-ai/DeepSeek-R1-0528" }, "weight": 33 }, { "variant": { "variant_id": "deepinfra/deepseek-ai/DeepSeek-V3-c", "model_id": "deepinfra/deepseek-ai/DeepSeek-V3" }, "weight": 34 } ] } }'

Step 2 — Chat Completion

curl --location 'https://api.inworld.ai/v1/chat/completions' \ --header 'Authorization: Basic <your-api-key>' \ --header 'Content-Type: application/json' \ --data '{ "model": "inworld/compare-frontier-models", "messages": [{"role": "user", "content": "Hello!"}] }'

Models/deepseek V4 PRO pricing and providers

Access Models/deepseek V4 PRO through Inworld via Inworld Router or Realtime API. By using the AI provider(s) below you acknowledge you reviewed and agree to their terms listed in the Legal section under the AI provider's name.
CapabilitiesInput modalitiesOutput modalities
InworldInworld1M131.1K$1.15$2.415+1

Other DeepSeek models available through Inworld

Compare Models/deepseek V4 PRO with other DeepSeek models available through Inworld Router or Realtime API.
CapabilitiesInput modalitiesOutput modalitiesInference provider
DeepSeekDeepseek Ai/DeepSeek R1 0528163.8K163.8K$0.50$2.15+2
DeepSeekDeepseek Ai/DeepSeek V3163.8K163.8K$0.32$0.89
DeepSeekDeepseek Ai/DeepSeek V3 0324163.8K163.8K$0.20$0.77
DeepSeekDeepseek Ai/DeepSeek V3.1 Terminus163.8K163.8K$0.21$0.79+2
DeepSeekDeepseek Ai/DeepSeek V3.2163.8K$0.26$0.38+2
DeepSeekDeepseek Ai/DeepSeek V4 Flash1M$0.10$0.20+2
DeepSeekDeepseek Ai/DeepSeek V4 PRO1M$1.30$2.60+2
DeepSeekDeepseek V4 Flash1M$0.149$0.297+1
DeepSeekDeepseek V4 PRO1M$0.462$0.923+1
DeepSeekModels/deepseek V3.2163.8K$0.26$0.38
DeepSeekModels/deepseek V4 Flash1M131.1K$0.10$0.20

Start building with Models/deepseek V4 PRO

Access Models/deepseek V4 PRO and every other model through Inworld Router or Realtime API. Create your free account and start routing in minutes.
Copyright © 2021-2026 Inworld AI
Models/deepseek V4 PRO by DeepSeek — Pricing, Specs & API Access | Inworld