Fireworks AI API pricing calculator
DeepSeek V4 Flash Pricing Calculator: Input and Output Token Costs
Estimate prompt, response, cached input, and volume costs for DeepSeek V4 Flash. Pricing verified 2026-06-25 from the provider source.
Quick estimate
No API key needed. Pick a model, paste your question, choose the answer length, and get a close cost estimate.
3. How long will the AI answer be?
Your estimate will appear here.
Paste a prompt, choose an answer length, and calculate.
Pricing table
Input: $0.14 per 1M tokens
Output: $0.28 per 1M tokens
Cached input: $0.028 per 1M tokens
Context window: Provider-specific tokens
Example prompt costs
A 2,000 token prompt and 1,000 token answer costs about $0.000560 before tool add-ons.
Low-cost Fireworks serverless model.
How much does DeepSeek V4 Flash cost per 1M input tokens?
DeepSeek V4 Flash is seeded at $0.14 per 1M input tokens for the serverless_standard tier.
How much does DeepSeek V4 Flash cost per 1M output tokens?
DeepSeek V4 Flash is seeded at $0.28 per 1M output tokens.
Does DeepSeek V4 Flash support cached input pricing?
Yes. The cached input seed price is $0.028 per 1M tokens.