As of August 20, 2026, DeepSeek-V3.1 is 89% cheaper per million tokens than GPT-5. DeepSeek-V3.1 is $0.27 / $1.00 per million input/output tokens versus GPT-5 at $1.25 / $10.00. Sources: https://api-docs.deepseek.com/quick_start/pricing and https://developers.openai.com/api/docs/pricing
Sources: DeepSeek API pricing (https://api-docs.deepseek.com/quick_start/pricing); OpenAI API pricing (https://developers.openai.com/api/docs/pricing)
DeepSeek-V3.1
DeepSeek
Input
$0.27
Output
$1.00
GPT-5
OpenAI
Input
$1.25
Output
$10.00
Token pricing, specs, and benchmarks side by side
DeepSeek-V3.1GPT-5Verdict
DeepSeek-V3.1 offers significantly lower pricing, while GPT-5 leads on benchmark performance. Your choice depends on whether cost efficiency or raw capability matters more for your use case.
As of August 20, 2026, DeepSeek-V3.1 is 89% cheaper on blended LLM API pricing. DeepSeek-V3.1 costs $0.27 per million input tokens and $1.00 per million output tokens ($1.27 blended 1M-in + 1M-out). GPT-5 costs $1.25 / $10.00 per million tokens ($11.25 blended). Sources: https://api-docs.deepseek.com/quick_start/pricing and https://developers.openai.com/api/docs/pricing. The cheapest LLM for your app still depends on how many output tokens you generate.
DeepSeek-V3.1 DeepSeek API pricing is $0.27 input and $1.00 output per million tokens via DeepSeek. GPT-5 OpenAI API pricing is $1.25 input and $10.00 output per million tokens via OpenAI. Use those four numbers, not ChatGPT Plus or Claude Pro subscription prices, when you are comparing APIs.
GPT-5 leads on SWE-bench Verified: DeepSeek-V3.1 at 66% vs GPT-5 at 74.9%. SWE-bench measures real GitHub fixes; LiveCodeBench measures contest programming.
DeepSeek-V3.1 supports a 164K token context window, while GPT-5 supports 400K tokens. GPT-5 offers a larger context window. Filling a larger window bills more input tokens, so the cheaper-per-million model can still cost more on long documents.
GPT-5 leads on 12 of 13 shared benchmarks versus DeepSeek-V3.1's 1 wins. Check the comparison table for GPQA Diamond, SWE-bench, MMLU, HLE, and the other evals we track. Token price and benchmark score together are the usual LLM comparison, not either number alone.
Both DeepSeek-V3.1 and GPT-5 are production API models. For cost-sensitive production traffic, DeepSeek-V3.1 has better economics on the blended 1M-in + 1M-out scale. For maximum capability, weight the benchmark table for your domain. Many production stacks route cheap models for drafts and a frontier model for the hard turn, which is usually cheaper than sending everything to the expensive API.
Yes. Call DeepSeek-V3.1 through DeepSeek and GPT-5 through OpenAI with separate API keys, or through a gateway that already wraps both. Keep prompts in tokens, not characters, when you estimate the invoice. AnotherWrapper templates can swap providers without rewriting auth and billing.
List rates are the latest published DeepSeek API pricing and OpenAI API pricing, quoted per million tokens. Official rate sheets: https://api-docs.deepseek.com/quick_start/pricing and https://developers.openai.com/api/docs/pricing. Prompt caching, batch APIs, and committed-use discounts can change the invoice. Benchmark scores are from official publications and independent evals, updated as new numbers land.
DeepSeek-V3.1 supports up to 164K output tokens per request, while GPT-5 supports up to 128K output tokens. Output tokens are usually the expensive half of API pricing, so a higher max output cap is a capability, not a discount.
GPT-5 has a measured throughput of approximately 100 tokens/second. Throughput data for DeepSeek-V3.1 is not yet available. Throughput (tokens per second) and time-to-first-token are why two models with the same per-million-token price can still feel different in chat and agents.
Use the model pickers at the top of this LLM comparison. Search any model in the index and the URL updates. Open DeepSeek-V3.1 or GPT-5 from the sidebar for the single-model API pricing page, or go back to the LLM pricing table to sort by cheapest blended cost.
This comparison covers API pricing, context window, throughput, and benchmark scores. DeepSeek-V3.1 costs $0.27/M input and $1.00/M output. GPT-5 costs $1.25/M input and $10.00/M output.
Rank both on the LLM leaderboard, SWE-bench, and Humanity's Last Exam.
The index
280 models across 33 providers. Search or jump to a lab — every model page stays linked here.
Next step
Auth, billing, and the API layer are already decided. Fork 8 finished AI apps, or have us build the first version with you.
