DeepSeek V4 Flash (0731)
Provider list prices: no platform markup, pay-as-you-go. These are official list prices. Logged-in customers may see effective prices including workspace discounts on /console/pricing. Effective input at a 70% cache-hit rate:$0.088/M. Automatic disk KV-prefix caching: cache hits bill at the discounted cache-read rate with no opt-in and no write fee.
Use DeepSeek V4 Flash (0731) in 30 seconds
OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions
from openai import OpenAI
client = OpenAI(
base_url="https://synthorai.io/v1",
api_key="sk-syn-...",
)
resp = client.chat.completions.create(
model="deepseek-v4-flash-0731",
messages=[{"role": "user", "content": "Summarize this diff"}],
reasoning_effort="medium",
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://synthorai.io/v1",
apiKey: "sk-syn-...",
});
const resp = await client.chat.completions.create({
model: "deepseek-v4-flash-0731",
messages: [{ role: "user", content: "Summarize this diff" }],
reasoning_effort: "medium",
});
console.log(resp.choices[0].message.content);curl https://synthorai.io/v1/chat/completions \
-H "Authorization: Bearer sk-syn-..." \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-flash-0731",
"messages": [{"role": "user", "content": "Hello"}],
"reasoning_effort": "medium"
}'package main
import (
"context"
"fmt"
"github.com/openai/openai-go/v3"
"github.com/openai/openai-go/v3/option"
)
func main() {
client := openai.NewClient(
option.WithBaseURL("https://synthorai.io/v1"),
option.WithAPIKey("sk-syn-..."),
)
resp, _ := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
Model: "deepseek-v4-flash-0731",
Messages: []openai.ChatCompletionMessageParamUnion{
openai.UserMessage("Summarize this diff"),
},
ReasoningEffort: openai.ReasoningEffortMedium,
})
fmt.Println(resp.Choices[0].Message.Content)
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;
import com.openai.models.ReasoningEffort;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
ChatCompletion resp = client.chat().completions().create(
ChatCompletionCreateParams.builder()
.model("deepseek-v4-flash-0731")
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));Specs & limits
Tokens
- Context window (vendor spec)
- 1,000,000
- Max output (vendor spec)
- 393,216
Prompt caching
- How it caches
- automatic
Thinking
- Parameter
- reasoning_effort
- Values
- minimal · low · medium · high accepted set is the provider's
Model
- Modalities
- text → text
- Parameters
- 284B total · 13B active MoE
- License
- MIT
- July 2026 release of DeepSeek V4 Flash
- same 284B/13B-active MoE design, gains from a stronger post-training pipeline rather than a new architecture
About DeepSeek V4 Flash (0731)
DeepSeek V4 Flash 0731 is the July 2026 release of DeepSeek's fast, economical V4 Flash line, and it supersedes the earlier V4 Flash rather than sitting beside it as a variant.
- The architecture and the size are unchanged — a Mixture-of-Experts model with 284B total parameters and 13B activated at inference — and DeepSeek attributes the improvement to a substantially stronger post-training pipeline rather than to a new design, with the work concentrated on agentic workflows and reasoning quality.
- Everything that made the line attractive operationally carries over: the 1M-token context window, a 384K maximum output, MIT-licensed weights, function calling, structured output and streaming.
- Thinking is enabled by default and the trace comes back in reasoning_content, which matters more here than on most models: on short prompts the reasoning trace can account for the large majority of the completion tokens, so a tight max_tokens budget will return an empty answer while still being billed for the tokens spent thinking.
- Budget for that, or lower the reasoning effort, before wiring it into latency-sensitive paths.
- The model is text-only in and text-only out; image input is not supported, so pair it with a vision model rather than sending multimodal messages.
- Because both the dated release and the rolling name remain callable, pin the dated id when you need reproducible behaviour and expect the undated name to move forward over time.
- Synthorai serves it through the OpenAI-compatible chat completions endpoint.
FAQ
Is the DeepSeek V4 Flash (0731) API free to try?
Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $0.2/M input tokens, that credit alone covers roughly 625 requests of ~8K tokens against DeepSeek V4 Flash (0731).
What is DeepSeek V4 Flash (0731) best at?
284B MoE with 13B activated, MIT-licensed; supersedes the earlier V4 Flash release; 1M context with 384K maximum output. See the About section for the full picture from the vendor's own release notes.
How much does DeepSeek V4 Flash (0731) cost?
DeepSeek V4 Flash (0731) costs $0.2 per million input tokens and $0.4 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.04/M.
Does DeepSeek V4 Flash (0731) support prompt caching?
Yes, automatically: DeepSeek-served prompts cache with no code changes. Cached input tokens bill at $0.04/M vs $0.2/M uncached. Prompt caching guide →
How do I get access to DeepSeek V4 Flash (0731)?
Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="deepseek-v4-flash-0731", and you're done. One API key covers every model on the gateway.
Is DeepSeek V4 Flash (0731) open source?
Yes: the weights are published under the MIT license. Or skip the GPUs: the hosted version here is pay-as-you-go with no infrastructure to run. Running open-weight models →