GPT-6.1 Sol
- Input / 1M tokens
- $2.00
- Output / 1M tokens
- $10.00
API models · Side by side
GPT-6.1 Sol vs DeepSeek V4.1 Flash
GPT-6.1 Sol is a mid-priced all-rounder that reads files. DeepSeek V4.1 Flash is a fraction of the price and handles text and images. The question is whether Sol's extras are worth the difference.
DeepSeek V4.1 Flash
- Input / 1M tokens
- $0.15
- Output / 1M tokens
- $0.60
The short answer
Sol charges $2 per million input tokens and $10 per million output tokens. DeepSeek charges $0.15 and $0.60 off-peak, and $0.30 and $1.20 at weekday peak times. Sol accepts files; DeepSeek doesn't. DeepSeek can write much longer replies: about 393,000 tokens vs 128,000.
Compare the details
Compare context, supported inputs and usage costs. Highlighted rows show a difference.
| Feature | GPT-6.1 Sol | DeepSeek V4.1 Flash |
|---|---|---|
| Input formats | file, image, text | image, text |
| Output formats | text | text |
| Context / position limit | 1,050,000 | 1,048,576 |
| Maximum output tokens | 128,000 | 393,216 |
| Developer features | Reasoning output, Completion limit, Output limit, Reasoning controls, Thinking effort, Response format, Seed, Structured output, Tool selection, Tool calling, Response length | frequency penalty, Reasoning output, logit bias, logprobs, Output limit, min p, presence penalty, Reasoning controls, Thinking effort, repetition penalty, Response format, Seed, Stop sequences, Structured output, Temperature, Tool selection, Tool calling, top k, top logprobs, Sampling controls |
| Cached input / 1M tokens | $0.10 | $0.003000 |
| Cache write / 1M tokens | $2.50 | Unknown |
| USD input / 1M tokens | $2.00 | $0.15 |
| USD output / 1M tokens | $10.00 | $0.60 |
| Model identifier | openai/gpt-6.1-sol | deepseek/deepseek-v4.1-flash |
API pricing
Prices are in USD per million tokens. Input is what you send; output is what the model generates. Claude and ChatGPT subscriptions are billed separately.
GPT-6.1 Sol: long-prompt rates
- Long-prompt threshold: 272,000 prompt tokens. Input: $4.00 / 1M. Output: $15.00 / 1M.
DeepSeek V4.1 Flash: long-prompt rates
- Long-prompt threshold: 0 prompt tokens. Input: $0.15 / 1M. Output: $0.60 / 1M.
- Long-prompt threshold: 0 prompt tokens. Input: $0.15 / 1M. Output: $0.60 / 1M.
- Long-prompt threshold: 0 prompt tokens. Input: $0.30 / 1M. Output: $1.20 / 1M.
- Long-prompt threshold: 0 prompt tokens. Input: $0.15 / 1M. Output: $0.60 / 1M.
- Long-prompt threshold: 0 prompt tokens. Input: $0.30 / 1M. Output: $1.20 / 1M.
- Long-prompt threshold: 0 prompt tokens. Input: $0.15 / 1M. Output: $0.60 / 1M.
Tools, images and additional reasoning can add charges. The examples below cover input and output tokens only.
Compare local modelsWhat those prices mean in practice
Each example uses the same token budget for both models. These are calculations, not measured workloads. Cache discounts, media, tools and extra reasoning are excluded.
| Workload | GPT-6.1 Sol | DeepSeek V4.1 Flash |
|---|---|---|
| 1,000 short requestsPer request: 2,000 input + 500 output tokens | $9.00 | $0.60 |
| 100 document summariesPer request: 20,000 input + 1,000 output tokens | $5.00 | $0.36 |
| 10 long-document requestsPer request: 300,000 input + 2,000 output tokens | $12.30 | $0.46 |
Estimate = requests × (input tokens × input price + output tokens × output price) ÷ 1,000,000. Long-prompt rates are applied where the pricing data provides them. Real requests can use different amounts of output.
Beyond the price tag
Coding sessions add up
A coding assistant reads files, calls tools, makes changes and reviews them, re-sending context every step. Compare the cost of a finished task, not one message. At these rates, DeepSeek's savings multiply quickly over a long session.
Files change the setup
Sol takes PDFs and other files directly. With DeepSeek, your app must first convert documents to text or images. That's fine for plain prose, but tables and diagrams may need extra care.
Where to start
Clearly defined jobs, like classification, extraction and drafting, are the best place to try DeepSeek first. Include tricky cases in your tests, and count retries and human corrections in the real cost.
Which one should you pick?
Choose DeepSeek V4.1 Flash for high-volume text and image work where cost matters most. Choose GPT-6.1 Sol for document-heavy apps, or when your tests show it needs much less correction.
Common questions
Are these costs for running DeepSeek myself?
No. They're hosted API prices. Self-hosting has separate hardware costs.
Do the cost examples include everything?
They cover input and output tokens. Reasoning, retries and tools add to the total.