DeepSeek Models & API
Browse the DeepSeek models currently available on TokenHub. Compare pricing, context windows, and supported capabilities, then start with one OpenAI-compatible API workflow.
DeepSeek Models & API Pricing
Compare current DeepSeek API pricing, input and output token costs, context windows, and supported endpoints. Open a model page for full specifications and request examples.
Compare input, output, and cache-read prices separately from model capabilities.
Compare context windows, maximum output, reasoning, tool calling, endpoints, and release dates.
Pricing, model availability, context windows, and endpoint support reflect the current TokenHub catalog. Confirm the model detail page before a production release because specifications and availability can change.
Last updated: 2026-08-25Get started with the DeepSeek API
Use the DeepSeek OpenAI-compatible API with Chat Completions or Responses, or call DeepSeek through the Claude Messages API. OpenAI SDK examples are available in Python and Node.js; streaming support depends on the selected endpoint.
- 01Create a TokenHub API key
- 02Choose an available DeepSeek model
- 03Choose an API protocol
- 04Use the published endpoint and model ID
- 05Send your first request
Choose an API protocol
import OpenAI from "openai"
const client = new OpenAI({
apiKey: process.env.TOKENHUB_API_KEY,
baseURL: "https://us-api.tokenhub.com/v1",
})
const result = await client.chat.completions.create({
"model": "deepseek-v3.2-think",
"messages": [
{
"role": "user",
"content": "Explain why low latency matters for an AI product in one sentence."
}
]
})
console.log(result.choices[0]?.message?.content)import json
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ.get("TOKENHUB_API_KEY"),
base_url="https://us-api.tokenhub.com/v1",
)
request = json.loads("{\"model\":\"deepseek-v3.2-think\",\"messages\":[{\"role\":\"user\",\"content\":\"Explain why low latency matters for an AI product in one sentence.\"}]}")
result = client.chat.completions.create(**request)
print(result.choices[0].message.content)curl 'https://us-api.tokenhub.com/v1/chat/completions' \
-X 'POST' \
-H "Authorization: Bearer $TOKENHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v3.2-think",
"messages": [
{
"role": "user",
"content": "Explain why low latency matters for an AI product in one sentence."
}
]
}'const response = await fetch("https://us-api.tokenhub.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.TOKENHUB_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "deepseek-v3.2-think",
"messages": [
{
"role": "user",
"content": "Explain why low latency matters for an AI product in one sentence."
}
]
}),
})
const data = await response.json()
console.log(data)import os
import requests
response = requests.request(method="POST", url="https://us-api.tokenhub.com/v1/chat/completions",
headers={
"Authorization": f"Bearer {os.environ['TOKENHUB_API_KEY']}",
"Content-Type": "application/json",
},
json=__import__("json").loads("{\"model\":\"deepseek-v3.2-think\",\"messages\":[{\"role\":\"user\",\"content\":\"Explain why low latency matters for an AI product in one sentence.\"}]}"),
)
response.raise_for_status()
print(response.json())import OpenAI from "openai"
const client = new OpenAI({
apiKey: process.env.TOKENHUB_API_KEY,
baseURL: "https://us-api.tokenhub.com/v1",
})
const result = await client.responses.create({
"model": "deepseek-v3.2-think",
"input": "Explain why low latency matters for an AI product in one sentence."
})
console.log(result.output_text)import json
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ.get("TOKENHUB_API_KEY"),
base_url="https://us-api.tokenhub.com/v1",
)
request = json.loads("{\"model\":\"deepseek-v3.2-think\",\"input\":\"Explain why low latency matters for an AI product in one sentence.\"}")
result = client.responses.create(**request)
print(result.output_text)curl 'https://us-api.tokenhub.com/v1/responses' \
-X 'POST' \
-H "Authorization: Bearer $TOKENHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v3.2-think",
"input": "Explain why low latency matters for an AI product in one sentence."
}'const response = await fetch("https://us-api.tokenhub.com/v1/responses", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.TOKENHUB_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "deepseek-v3.2-think",
"input": "Explain why low latency matters for an AI product in one sentence."
}),
})
const data = await response.json()
console.log(data)import os
import requests
response = requests.request(method="POST", url="https://us-api.tokenhub.com/v1/responses",
headers={
"Authorization": f"Bearer {os.environ['TOKENHUB_API_KEY']}",
"Content-Type": "application/json",
},
json=__import__("json").loads("{\"model\":\"deepseek-v3.2-think\",\"input\":\"Explain why low latency matters for an AI product in one sentence.\"}"),
)
response.raise_for_status()
print(response.json())curl 'https://us-api.tokenhub.com/v1/messages' \
-X 'POST' \
-H "Authorization: Bearer $TOKENHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v3.2-think",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": "Explain why low latency matters for an AI product in one sentence."
}
]
}'const response = await fetch("https://us-api.tokenhub.com/v1/messages", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.TOKENHUB_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "deepseek-v3.2-think",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": "Explain why low latency matters for an AI product in one sentence."
}
]
}),
})
const data = await response.json()
console.log(data)import os
import requests
response = requests.request(method="POST", url="https://us-api.tokenhub.com/v1/messages",
headers={
"Authorization": f"Bearer {os.environ['TOKENHUB_API_KEY']}",
"Content-Type": "application/json",
},
json=__import__("json").loads("{\"model\":\"deepseek-v3.2-think\",\"max_tokens\":1024,\"messages\":[{\"role\":\"user\",\"content\":\"Explain why low latency matters for an AI product in one sentence.\"}]}"),
)
response.raise_for_status()
print(response.json())Which DeepSeek model should you choose?
Use this DeepSeek model selection guide to match the API workload to a model, then verify DeepSeek API pricing, context window, and endpoint support before shipping.
| API workload | Start with | When it fits | Verify before launch |
|---|---|---|---|
| High-volume, cost-aware API calls | DeepSeek V4 Flash | Chat, summarization, generation, and batch work where fast iteration matters. | DeepSeek API pricing, throughput, and output-token cost |
| Complex reasoning | DeepSeek R1 | Multi-step analysis, code reasoning, and tasks where answer quality matters more than latency. | Reasoning latency, output length, and total request cost |
| General production workflows | DeepSeek V3.2 Think | Everyday assistants, extraction, and product features using one DeepSeek API integration. | Task accuracy, endpoint support, and production price |
| Long documents and conversations | DeepSeek V4 Flash | Long-context DeepSeek API requests where prompts, files, or chat history are the constraint. | Context window, input-token pricing, and streaming support |
| High-quality or high-stakes delivery | DeepSeek V4 Pro | Final outputs where capability headroom matters more than the lowest possible unit cost. | Task-specific quality, latency, and the cost difference versus Flash |
Compare DeepSeek
Compare capability, API pricing, and context windows before choosing a model.
Integrate DeepSeek
Use TokenHub to connect DeepSeek to the development tools already in your workflow.
DeepSeek API FAQ
Which DeepSeek models are available on TokenHub?
The model list on this page reflects the DeepSeek models currently available in the TokenHub catalog. Availability can change, so open a model detail page before integrating.
Which DeepSeek model should I use?
Start with the workload: use a fast model for cost-aware iteration, a reasoning-capable model for complex tasks, and compare context windows when long inputs matter.
How is DeepSeek API pricing calculated?
Pricing depends on the selected model and billing type. Review input, output, cache, or per-request pricing in the catalog and model detail page.
Can I use the OpenAI SDK with DeepSeek models on TokenHub?
Yes. Use the OpenAI Python or Node.js SDK with the TokenHub Base URL, API key, and DeepSeek model ID for Chat Completions or Responses requests.
Which API protocols can I use to call DeepSeek?
TokenHub provides DeepSeek examples for OpenAI Chat Completions, OpenAI Responses, and Claude Messages. Streaming support depends on the endpoint used by your request.
Where do I find the DeepSeek model ID?
Each pricing row shows its model ID. You can also find it on the corresponding model detail page.
Start building with DeepSeek
Choose a model, create a TokenHub API key, and keep the same API workflow as your application evolves.