DeepSeek V4 Pro vs GPT-6.1 Sol: API price, context and cost per task
DeepSeek's open-weight Mixture-of-Experts model (1.6T total, 49B active parameters) against OpenAI's GPT-6.1 Sol.
On output, DeepSeek V4 Pro is 5.2x cheaper ($1.91 vs $10 per million tokens). On input, DeepSeek V4 Pro is 2.1x cheaper ($0.955 vs $2 per million tokens). GPT-6.1 Sol reads more per request: 1,050,000 tokens against 1,048,576.
Data updated 2026-11-11 - source: public OpenRouter model list, refreshed daily. Prices in USD, excluding VAT.
Specs and prices side by side
| DeepSeek V4 Pro | GPT-6.1 Sol | |
|---|---|---|
| Vendor | DeepSeek | OpenAI |
| Input, per 1M tokens | $0.955 | $2 |
| Output, per 1M tokens | $1.91 | $10 |
| Cached input, per 1M | $0.0796 | $0.1 |
| Batch (input / output) | not offered | $1 / $5 |
| Context window | 1,048,576 | 1,050,000 |
| Max output | 384,000 | 128,000 |
| Input types | text | text, images, files |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| On OpenRouter since | 24 Apr 2026 | 29 Sep 2026 |
Highlighted: the cheaper price or the larger limit. "Not published" means the figure is not in the public model listing yet.
What a month of work costs
Four typical workloads at today's list prices. Reasoning models also bill their thinking as output tokens, so treat output-heavy numbers as a floor.
| Workload | DeepSeek V4 Pro | GPT-6.1 Sol | Difference |
|---|---|---|---|
| Support chatbot10,000 conversations a month, about 1,500 input and 400 output tokens each | $21.97 | $70 | DeepSeek V4 Pro 3.2x cheaper |
| Coding agent300 tasks a month, about 80,000 input tokens (code context re-read across steps) and 8,000 output tokens each | $27.51 | $72 | DeepSeek V4 Pro 2.6x cheaper |
| Coding agent with caching70% of input served from the prompt cache | $12.80 | $40.08 | |
| Long-document analysis1,000 documents a month, about 50,000 tokens in and a 1,500-token summary out | $50.63 | $115 | DeepSeek V4 Pro 2.3x cheaper |
| Content drafting600 articles a month, about 3,000 tokens of brief in and 2,500 tokens of draft out | $4.59 | $18.60 | DeepSeek V4 Pro 4.1x cheaper |
Price stability over the last 30 days
- DeepSeek V4 Pro: 12 price changes since 12 Oct 2026. Input ranged $0.209 - $1.6, output $0.418 - $3.2 per million tokens. Volatile: the listed price follows whichever provider OpenRouter currently routes to, so budget with the upper end of the range.
- GPT-6.1 Sol: no change in the last 30 days.
DeepSeek V4 Pro: price log
| Date | Input | Output |
|---|---|---|
| 2026-11-10 | $0.955 | $1.91 |
| 2026-11-08 | $0.424 | $0.848 |
| 2026-11-07 | $0.88 | $1.76 |
| 2026-11-06 | $0.955 | $1.91 |
| 2026-10-31 | $1.6 | $3.2 |
| 2026-10-30 | $0.816 | $1.63 |
| 2026-10-26 | $0.955 | $1.91 |
| 2026-10-25 | $0.209 | $0.418 |
What the vendors and benchmarks say
DeepSeek V4 Pro
"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window."model card on OpenRouter
- Open-weight model. The same model can cost several times more or less depending on which provider serves it through OpenRouter. Source: OpenRouter provider listings
GPT-6.1 Sol
"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series."model card on OpenRouter
- Listed on OpenRouter on 29 September 2026, one week after GPT-6 Sol, which it upgrades. Source: OpenRouter
Which one to pick
DeepSeek V4 Pro is many times cheaper on OpenRouter, but its listed price moves almost daily as different providers serve it - see the 30-day range above. For bulk processing, extraction and code or math tasks where you can validate outputs, V4 Pro is the cost leader. For image and file input (V4 Pro accepts text only) and predictable billing, Sol is simpler.
Cheaper models with a similar context window
Models from our comparison set that cost less than both on a blended basis and support tool calling. They are not equivalent in quality - test before switching.
- GLM-5.3 (Z.ai): $0.0699 / $1.4 per million tokens, 1.05M context
- GPT-6 Luna (OpenAI): $0.1 / $0.5 per million tokens, 1.05M context
- DeepSeek V4.1 Flash (DeepSeek): $0.051 / $0.567 per million tokens, 1.05M context
Related reading
- DeepSeek V4 Pro 0813 Appears on OpenRouter With No Announcement
- DeepSeek, GLM, Kimi and Qwen: Free AI or Cheap API?
- DeepSeek V4.1 Flash 1017: API Pricing, Search API and My Test
- Gemini 4 Carbon test: 50+ tasks vs Argon, Claude Fable 5.2 and GPT-6.1 Sol
- Claude Fable 5.2 vs GPT-6.1 Sol vs Gemini 4 Argon: Price, Benchmarks
- GPT-6.1 Terra vs Claude Sonnet 5.5: Polish Test Results
How we calculate
Prices are the public per-token list rates from OpenRouter's model list, which match the vendors' own API prices for first-party models and show the current routed price for open-weight models served by several hosts. Monthly costs multiply those rates by the token volumes in each workload; caching assumes the stated share of input is billed at the cached-input rate. Benchmarks and claims are quoted from the named sources, mostly the vendors themselves - treat them as a guide and test on your own tasks. See also the AI cost calculator and all tracked model prices.
Frequently asked questions
Which is cheaper, DeepSeek V4 Pro or GPT-6.1 Sol?
As of 11 Nov 2026, DeepSeek V4 Pro costs $0.955 per million input tokens and $1.91 per million output tokens; GPT-6.1 Sol costs $2 and $10. DeepSeek V4 Pro is cheaper in 4 of the 4 monthly workloads we price on this page. The real bill also depends on how many reasoning tokens each model writes.
Which has the larger context window?
DeepSeek V4 Pro reads up to 1,048,576 tokens and can write up to 384,000; GPT-6.1 Sol reads up to 1,050,000 and writes up to 128,000.
How much does a support chatbot cost on each model?
For 10,000 conversations a month (about 15 million input and 4 million output tokens) you would pay about $21.97 on DeepSeek V4 Pro and $70 on GPT-6.1 Sol at list prices, before any caching or batch discounts.
Do they offer prompt caching or batch discounts?
DeepSeek V4 Pro lists cached input at $0.0796 per million. GPT-6.1 Sol lists cached input at $0.1 per million and a batch rate of $1 / $5. Caching matters most for agents and chatbots that resend the same context on every turn.
// follow
New tests and price changes, straight to your feed reader
Free RSS, no account and no email needed.
Follow Quantslant →