Cheaper Inference
Model record / deepseek
deepseek-v4.1-flash-1017-ultrafast is available for text generation from deepseek. Its reported context window is 1,048,576 tokens, with up to 1,048,576 output tokens. Reported inputs: image, text. The served catalog lists image input, streaming.
Ready when you are
Marketplace pricing, capped at list, optimized further.
POST /v1/chat/completions
curl https://api.cheaperinference.com/v1/chat/completions \ -H "Authorization: Bearer ci_live_YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "deepseek-v4.1-flash-1017-ultrafast", "messages": [ { "role": "user", "content": "Reply with the single word OK." } ] }'POST /v1/responses
curl https://api.cheaperinference.com/v1/responses \ -H "Authorization: Bearer ci_live_YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": [ { "role": "user", "content": "Reply with the single word OK." } ], "model": "deepseek-v4.1-flash-1017-ultrafast", "store": false }'POST /v1/messages
curl https://api.cheaperinference.com/v1/messages \ -H "Authorization: Bearer ci_live_YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "deepseek-v4.1-flash-1017-ultrafast", "messages": [ { "role": "user", "content": "Reply with the single word OK." } ], "max_tokens": 1024 }'Capability source · checked
$3.12 estimated at displayed rates
1,000,000 ÷ 1,000,000 × $1.56 + 250,000 ÷ 1,000,000 × $6.24
The same billed quantities at the listed reference rates: $4.80.
Uses uncached input at the displayed standard rates, with no extra modalities or tools. Billed output includes any charged reasoning tokens. Actual token counts, price tiers, and marketplace prices can change the total.
Price quote effective .
Python: pip install openai · Node.js: npm install openai. Set CHEAPER_INFERENCE_API_KEY on your server.
import osfrom openai import OpenAIclient = OpenAI( api_key=os.environ["CHEAPER_INFERENCE_API_KEY"], base_url="https://api.cheaperinference.com/v1",)request = { "model": "deepseek-v4.1-flash-1017-ultrafast", "messages": [ { "role": "user", "content": "Reply with the single word OK.", }, ],}response = client.chat.completions.create(**request)print(response.choices[0].message.content)import OpenAI from "openai";const client = new OpenAI({ apiKey: process.env.CHEAPER_INFERENCE_API_KEY, baseURL: "https://api.cheaperinference.com/v1",});const response = await client.chat.completions.create({ "model": "deepseek-v4.1-flash-1017-ultrafast", "messages": [ { "role": "user", "content": "Reply with the single word OK." } ]});console.log(response.choices[0].message.content);For other supported endpoints and their exact parameters, use the request samples and parameter reference on this page. Read the API integration guide.
| Model | Current pricing | Context limit | Image input listed |
|---|---|---|---|
| deepseek-v4.1-flash-1017-ultrafast (this model)deepseek | $1.56 input / $6.24 output per 1M tokens | 1,048,576 tokens | Yes |
| deepseek-v4.1-flash-1017DeepSeek | $0.066 input / $0.264 output per 1M tokens | 1,048,576 tokens | Yes |
| deepseek-v4.1-flash-1017-fastDeepSeek | $0.39 input / $1.56 output per 1M tokens | 1,048,576 tokens | Yes |
POST /v1/chat/completions
| Field | Values |
|---|---|
| reasoning.exclude | |
| max_tokens | |
| reasoning | effort: none, low, high, max; enabled: true or false |
| response_format | |
| stop | |
| temperature | |
| tool_choice | |
| tools |
POST /v1/messages
| Field | Values |
|---|---|
| max_tokens | |
| thinking | type: enabled with budget_tokens; output_config.effort: none, low, high, max |
| output_config.format | |
| stop_sequences | |
| temperature | |
| tool_choice | |
| tools |
POST /v1/responses
| Field | Values |
|---|---|
| max_output_tokens | |
| reasoning | effort: none, low, high, max |
| text.format | |
| temperature | |
| tool_choice | |
| tools |
See how much this model saves and when its recorded price has been lowest.
Savings are visible now, but a best-time recommendation needs at least 12 observations across 6 different hours.
Average saved
8.3%
Cheapest time
Collecting data
Hourly coverage
6/24
Signal quality
Early
Hover a bar for savings per token and observation counts.
Source buckets are UTC; labels are converted to UTC.
Last 24 hours
—
of 371 ranked models
Last 7 days
—
of 398 ranked models
Last 30 days
—
of 405 ranked models
| $0.132 input / $0.528 output per 1M tokens |
| 1,048,576 tokens |
| Yes |