deepseek-v4-flash API pricing
deepseek-v4-flash on InferSpeed: $0.09 input, $0.36 output, $0.0018 cache read per 1M tokens, 40% below the official list price. OpenAI-compatible API, pay per token.
Price (USD per 1M tokens)
| Input | Output | Cache read | |
|---|---|---|---|
| Price | $0.09 | $0.36 | $0.0018 |
| Official list price | $0.15 | $0.60 | — |
40% below the official list price.
Endpoints
| API | Base URL |
|---|---|
OpenAI Chat Completions (/chat/completions) | https://api.inferspeed.ai/v1 |
Authentication: Authorization: Bearer $INFERSPEED_API_KEY (x-api-key also works).
FAQ
How much does the deepseek-v4-flash API cost?
InferSpeed charges $0.09 per 1M input tokens, $0.36 per 1M output tokens and $0.0018 per 1M cache-read tokens (USD), billed per token from a prepaid balance. The official list price is $0.15 input / $0.60 output, so this is 40% below the official list price.
Which APIs can I call deepseek-v4-flash with?
The price list names these APIs for deepseek-v4-flash: OpenAI Chat Completions (POST https://api.inferspeed.ai/v1/chat/completions). Authentication: Authorization: Bearer $INFERSPEED_API_KEY (x-api-key also works).
Which API key do I need for deepseek-v4-flash?
One API key calls every live model, deepseek-v4-flash included: create a key at https://inferspeed.ai/keys and name the model in the request. Each request is billed at the price of the model that served it.
How do I call deepseek-v4-flash?
Set the model explicitly in the request:
curl https://api.inferspeed.ai/v1/chat/completions \
-H "Authorization: Bearer $INFERSPEED_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-flash",
"messages": [{"role": "user", "content": "Say hello in one sentence."}]
}'What happens if I request a model my key cannot call?
It is routed to an available model instead of failing: agent default names such as claude-* and gpt-* go to glm-5.3 (kimi-k3 on a Kimi key). The model field and the X-Served-Model header name the model that served the request (the name you sent is in X-Model-Routed-From), and you are billed at that model's price. Send X-Model-Strict: 1 to get an error instead.
More
Setup for Claude Code, Codex CLI, OpenCode and SDKs: /developers.md. All models and prices: /model-plaza. Prices as JSON: /api/v1/public/pricing.