Modelflare
deepseek-v4-flash
Compare DeepSeek V4 Flash API prices and supported Chat Completions and Responses endpoints. Review context limits and model-group access.
API
openai
Models & Pricing
Prices are in USD. The listed group rate applies before any request-specific multiplier. Your account may have different access or discounts.
| Group | Price | Conditions | Unit | Price |
|---|---|---|---|---|
| deepseek-award | Input | Standard | Per 1M tokens | USD 0.10542168674698796 |
| deepseek-award | Output | Standard | Per 1M tokens | USD 0.42168674698795183 |
| deepseek-award | Cache Read | Standard | Per 1M tokens | USD 0.002108433734939759 |
| deepseek-stable | Input | Standard | Per 1M tokens | USD 0.18072289156626506 |
| deepseek-stable | Output | Standard | Per 1M tokens | USD 0.7228915662650602 |
| deepseek-stable | Cache Read | Standard | Per 1M tokens | USD 0.0036144578313253013 |
Integration guide
Use Responses for a client built around response items, or Chat Completions for a client built around chat messages when that endpoint is listed. Keep the exact model ID in requests and verify that your API key permits the selected model group.
Read the integration documentation
Frequently asked questions
Which price applies to my request?
Use the price for your model group and billing unit in the table. Input, output and cached tokens may have different rates. Media specifications and request conditions can change the quote; the final charge is recorded in usage logs.
Can I use my existing API client?
Check the supported endpoints on this page. Point a compatible client at Modelflare, use a Modelflare API key and keep the model ID exactly as shown. Protocol compatibility does not imply that every provider-specific parameter is available.
Why might a listed model be unavailable to my key?
Model-group access, API-key restrictions, balance and request limits are checked separately from the public catalog. Review your account permissions and the returned error before retrying.