High-volume, cost-sensitive work
Choose DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 costs 15% less on a typical mix of three input tokens for every output token ($0.15 against $0.18 per million tokens).
DeepSeek V4 Flash 0731 vs GPT-4.1 nano: price, context and capabilities
Choose DeepSeek V4 Flash 0731 for high-volume, cost-sensitive work, writing and code generation, reused prompts and documents (RAG, agents) and the latest release. Choose GPT-4.1 nano for images as input.
In short
- DeepSeek V4 Flash 0731 is 15% cheaper than GPT-4.1 nano at the headline price ($0.1488 / 1M tokens vs $0.175 / 1M tokens).
- DeepSeek V4 Flash 0731 reads more per request: 1.05M tokens against 1.05M.
- DeepSeek V4 Flash 0731 is the newer model (Jul 31, 2026, against Apr 14, 2025).
- Only DeepSeek V4 Flash 0731 offers reasoning.
- Only GPT-4.1 nano offers vision, batch api.
Which should you choose?
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Writing and code generation
Choose DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 charges $0.24 per million output tokens, against $0.40 for GPT-4.1 nano. Output dominates the bill when answers are long.
Reused prompts and documents (RAG, agents)
Choose DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 charges $0.02 per million cached input tokens, against $0.03 for GPT-4.1 nano.
Images as input
Choose GPT-4.1 nano
GPT-4.1 nano accepts images as input; DeepSeek V4 Flash 0731 does not.
Latest release
Choose DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 is the newer release (Jul 31, 2026, against Apr 14, 2025 for GPT-4.1 nano).
Monthly cost at three volumes
| Volume | DeepSeek V4 Flash 0731 | GPT-4.1 nano | Difference |
|---|---|---|---|
| Prototype: 1M input, 250K output tokens | $0.18 | $0.20 | DeepSeek V4 Flash 0731, $0.02 less |
| Production: 20M input, 5M output tokens | $3.57 | $4.00 | DeepSeek V4 Flash 0731, $0.43 less |
| Scale: 500M input, 100M output tokens | $83.30 | $90.00 | DeepSeek V4 Flash 0731, $6.70 less |
Standard rates, without caching or batch discounts. Volumes are per month.
Specifications side by side
| DeepSeek V4 Flash 0731 | GPT-4.1 nano | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Category | Language models | Language models |
| Status | Generally available | Deprecated |
| Headline price | $0.1488 / 1M tokens | $0.175 / 1M tokens |
| Input | $0.119 / 1M tokens | $0.10 / 1M tokens |
| Output | $0.238 / 1M tokens | $0.40 / 1M tokens |
| Cached input | $0.0238 / 1M tokens | $0.025 / 1M tokens |
| Context window | 1.05M | 1.05M |
| Max output | 944k | 33k |
| Released | Jul 31, 2026 | Apr 14, 2025 |
| Knowledge cutoff | No data | June 2024 |
| Licence | Proprietary | Proprietary |
| Capabilities | Reasoning, Tool calling, Structured output, Prompt caching | Vision, Tool calling, Structured output, Prompt caching, Batch API |
| API model id | deepseek-v4-flash-0731 | gpt-4.1-nano |
Benchmarks side by side
Leader in bold.
| Benchmark | DeepSeek V4 Flash 0731 | GPT-4.1 nano |
|---|---|---|
| Terminal-Bench Hard | No data | 3.8% |
| GPQA Diamond | No data | 51.2% |
| Humanity's Last Exam | No data | 3.8% |
| IFBench (instruction following) | No data | 32% |
| τ²-Bench (agentic tool use) | No data | 17.3% |
| MMMU-Pro (visual reasoning) | No data | 40.1% |
| Long-context reasoning (AA-LCR) | No data | 20.3% |
Independent evaluations by Artificial Analysis, run the same way for every model, at the reasoning setting shown. Percentages unless marked as an index.
Frequently asked questions
Should I choose DeepSeek V4 Flash 0731 or GPT-4.1 nano?
Choose DeepSeek V4 Flash 0731 for high-volume, cost-sensitive work, writing and code generation, reused prompts and documents (RAG, agents) and the latest release. Choose GPT-4.1 nano for images as input.
Which is cheaper, DeepSeek V4 Flash 0731 or GPT-4.1 nano?
DeepSeek V4 Flash 0731 is 15% cheaper than GPT-4.1 nano at the headline price ($0.1488 / 1M tokens vs $0.175 / 1M tokens).
Which has the larger context window, DeepSeek V4 Flash 0731 or GPT-4.1 nano?
DeepSeek V4 Flash 0731 reads more per request: 1.05M tokens against 1.05M.
What is the difference between DeepSeek V4 Flash 0731 and GPT-4.1 nano?
DeepSeek V4 Flash 0731 is made by DeepSeek and GPT-4.1 nano by OpenAI. DeepSeek V4 Flash 0731 is 15% cheaper than GPT-4.1 nano at the headline price ($0.1488 / 1M tokens vs $0.175 / 1M tokens). DeepSeek V4 Flash 0731 reads more per request: 1.05M tokens against 1.05M. DeepSeek V4 Flash 0731 is the newer model (Jul 31, 2026, against Apr 14, 2025). Only DeepSeek V4 Flash 0731 offers reasoning. Only GPT-4.1 nano offers vision, batch api.
How much do DeepSeek V4 Flash 0731 and GPT-4.1 nano cost per month?
At 20 million input and 5 million output tokens a month, DeepSeek V4 Flash 0731 costs $3.57 and GPT-4.1 nano costs $4.00, at standard rates.
Which is newer, DeepSeek V4 Flash 0731 or GPT-4.1 nano?
DeepSeek V4 Flash 0731 was released on Jul 31, 2026 and GPT-4.1 nano on Apr 14, 2025.