Fireworks AIDeepSeek V4 Pro model ID, context window & pricing
deepseek-thinking
Quick facts
Model ID accounts/fireworks/models/deepseek-v4-pro
Source Fireworks AI
Context Window 1000000
Pricing $1.74 input / $3.48 output per 1M tokens
Capabilities tool calling, reasoning, structured output, temperature control, open weights
Model overview
DeepSeek V4 Pro is an AI model from Fireworks AI with 1000000 token context window and text input support.
Published pricing is $1.74 input and $3.48 output per 1M tokens.
- Workloads that use text inputs with text outputs.
- Agent and tool workflows that need function calling.
- Reasoning-heavy prompts where stepwise problem solving matters.
Model ID accounts/fireworks/models/deepseek-v4-pro
Provider Fireworks AI
Family deepseek-thinking
Status -
Knowledge Cutoff 2025-05
Release Date 2026-04-24
Input Modalities text
Output Modalities text
Context Window 1000000
Input Limit -
Output Limit 384000
Tool Calling Yes
Reasoning Yes
Structured Output Yes
Temperature Control Yes
Open Weights Yes
Input Cost / 1M tokens $1.74
Output Cost / 1M tokens $3.48
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens $0.14
Cache Write Cost / 1M tokens -