DeepSeek V4 Pro 0813 vs GPT-6.1 Sol
DeepSeek V4 Pro 0813 costs less on output ($1.188 against $3.00 per million tokens); GPT-6.1 Sol costs less on input ($0.60 against $0.75). Both on one key at UplinkSwitch, each next to its developer's list price.
Prices · per million tokens, USD
| Tokens | DeepSeek V4 Pro 0813deepseek-v4-pro-0813 | GPT-6.1 Solgpt-6.1-sol |
|---|---|---|
| Input | $0.75DeepSeek lists $1.32 · 43% under | $0.60OpenAI lists $2.00 · 70% under |
| Cached input | $0.0625DeepSeek lists $0.044 | $0.06OpenAI lists $0.10 · 40% under |
| Output | $1.188DeepSeek lists $3.96 · 70% under | $3.00OpenAI lists $10.00 · 70% under |
| Context window | 1,048,576 tokens | 1,050,000 tokens |
| Max output | 393,216 tokens | 128,000 tokens |
| Input | text | text, image |
| Released | 2026-08-13 | 2026-09-29 |
| Formats | OpenAI SDK | OpenAI SDK |
| Developer | DeepSeek | OpenAI |
List price: each developer's published rate, read October 2026. A model with no cached rate bills cached tokens at its input rate. Live from GET https://api.uplinkswitch.com/v1/catalog.
What the same work costs · USD, here and at list
| Work | DeepSeek V4 Pro 0813 | GPT-6.1 Sol |
|---|---|---|
| 1,000 chat requests | $2.09list $4.62 | $2.70list $9.00 |
| 100 long documents | $3.99list $7.39 | $3.60list $12.00 |
| A month of both, daily | $182.45list $360.36 | $189.00list $630.00 |
A chat request is 2,000 input and 500 output tokens; a long document is 50,000 in and 2,000 out; the month is 1,000 chats and 100 documents a day for 30 days, uncached. Over that month DeepSeek V4 Pro 0813 costs $6.55 less here.
Same key, same URL
One base URL and one key serve both models. The request below calls DeepSeek V4 Pro 0813; put gpt-6.1-sol in the model field to call GPT-6.1 Sol instead.
shell
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"deepseek-v4-pro-0813","messages":[{"role":"user","content":"Hello"}]}'Model pages: DeepSeek V4 Pro 0813, GPT-6.1 Sol. Pricing by family: DeepSeek, GPT. More comparisons: Qwen3.7 Max vs DeepSeek V4 Pro 0813, GLM 5.3 vs DeepSeek V4 Pro 0813, Claude Sonnet 5.5 vs DeepSeek V4 Pro 0813, Claude Opus 5.5 vs GPT-6.1 Sol.
Questions
- Which costs less, DeepSeek V4 Pro 0813 or GPT-6.1 Sol?
- DeepSeek V4 Pro 0813 costs less on output ($1.188 against $3.00 per million tokens); GPT-6.1 Sol costs less on input ($0.60 against $0.75).
- Can I switch between them by changing the model id?
- Yes. Both answer in the OpenAI SDK format at the same base URL with the same key. Change the model id from deepseek-v4-pro-0813 to gpt-6.1-sol and nothing else.
- Is there a subscription?
- No. Prepaid credit from $10, with no subscription or monthly fee. Each top-up locks your prices for 30 days.
- Is DeepSeek V4 Pro 0813 better than GPT-6.1 Sol?
- Better depends on the job; this page compares what the catalog can measure. DeepSeek V4 Pro 0813 costs less on output ($1.188 against $3.00 per million tokens); GPT-6.1 Sol costs less on input ($0.60 against $0.75). DeepSeek V4 Pro 0813 takes 1,048,576 tokens of context against 1,050,000 for GPT-6.1 Sol. GPT-6.1 Sol is the newer release. Both run on the same key, so the fair test is your own prompt sent to each model id.