DeepSeek V3.2 is a reasoning-first text model that DeepSeek says can keep thinking while using tools, a change from earlier releases that split tool use and reasoning.
- Input
- text $0.28/M
- Output
- text $0.42/M
- Cache read
- $0.028/M
- Context
- 128K
- vs GPT-4o
- ~94% cheaper
- Knowledge cutoff
- 2025-03
Rates by prompt length
The whole request uses the rate for its input-length tier. Prices are USD per million tokens.
| Input tokens | Input | Output | Thinking input |
|---|
Benchmarks
Vendor-published: Alibaba (Qwen) Alibaba (Qwen) Alibaba (Qwen) Alibaba (Qwen) Alibaba (Qwen) Alibaba (Qwen) Alibaba (Qwen) Alibaba (Qwen) Anthropic Anthropic ByteDance DeepSeek DeepSeek Google MiniMax Moonshot OpenAI OpenAI OpenAI OpenAI Tencent Z.ai Z.ai Z.ai
Price in context
Where the price sits among 78 comparable models
The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.
Specs & limits
Tokens
| Context window (vendor spec) | 164,000 |
|---|---|
| Max output (vendor spec) | 8,192 |
| Knowledge cutoff | 2025-03 |
Prompt caching
| How it caches | automatic |
|---|---|
| Lifetime | no fixed TTL (evicted when unused) |
Thinking
| Parameter | reasoning_effort |
|---|---|
| Values | minimal · low · medium · high accepted set is the provider's |
Model
| Modalities | text → text |
|---|
Use DeepSeek V3.2 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-3.2",
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-3.2",
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-3.2",
"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-3.2",
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-3.2")
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));About DeepSeek V3.2
- Its linked model card lists a 164K-token context, 8K maximum output and March 2025 knowledge cutoff; Synthorai's current feed separately caps input at 128K.
- Use it for tool-driven text workflows and check those route-specific limits before sending long prompts.
- It does not accept image or audio input in the published model card.
FAQ
Is the DeepSeek V3.2 API free to try?
Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $0.28/M input tokens, that credit alone covers roughly 446 requests of ~8K tokens against DeepSeek V3.2.
What is DeepSeek V3.2 best at?
Reasoning while using tools; text-only input and output; gateway feed caps input at 128K. See the About section for the full picture from the vendor's own release notes.
How much does DeepSeek V3.2 cost?
DeepSeek V3.2 costs $0.28 per million input tokens and $0.42 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.028/M.
What is DeepSeek V3.2's context window?
DeepSeek V3.2 has a context window of 128K tokens on Synthorai. A single response can be up to 8,192 tokens long.
Does DeepSeek V3.2 support prompt caching?
Yes, automatically: DeepSeek-served prompts cache with no code changes. Cached input tokens bill at $0.028/M vs $0.28/M uncached (TTL no fixed TTL (evicted when unused)). Prompt caching guide →
How do I get access to DeepSeek V3.2?
Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="deepseek-3.2", and you're done. One API key covers every model on the gateway.
What is DeepSeek V3.2's knowledge cutoff?
DeepSeek V3.2's knowledge cutoff is 2025-03, per the vendor's official documentation (as of 2026-10-31).
Related models
Compare
Specifications and vendor benchmarks link to their sources. Gateway support describes the Synthorai implementation. Archived examples are individual gateway requests, not a guarantee of general model performance. Prices use the public feed or its build snapshot.