AI model comparison
Qwen3.5 397B A17B vs GPT-5.1-Codex-Mini
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.
- Input / 1M
- $0.55
- Output / 1M
- $3.50
- Context
- 262K
OpenAI
GPT-5.1-Codex-Mini
GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex
- Input / 1M
- $0.25
- Output / 1M
- $2
- Context
- 400K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
GPT-5.1-Codex-Mini
1.9x cheaper for a typical chat
Higher intelligence score
Qwen3.5 397B A17B
21.4 vs 20.4 on Artificial Analysis
Larger context window
GPT-5.1-Codex-Mini
400K vs 262K tokens
Newer release
Qwen3.5 397B A17B
Released February 16, 2026
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Qwen3.5 397B A17B21.4GPT-5.1-Codex-Mini20.4Coding index
Qwen3.5 397B A17BNot availableGPT-5.1-Codex-MiniNot availableAgentic index
Qwen3.5 397B A17BNot availableGPT-5.1-Codex-MiniNot availablePricing
Qwen3.5 397B A17B vs GPT-5.1-Codex-Mini API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Qwen3.5 397B A17B | GPT-5.1-Codex-Mini |
|---|---|---|
| Input tokensPer 1M tokens | $0.55 | $0.25 |
| Output tokensPer 1M tokens | $3.50 | $2 |
| Cached input (read)Per 1M tokens | $0.22 | $0.03 |
| Cache writePer 1M tokens | Not available | Not available |
| Web searchPer request | Not available | $0.01 |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
Qwen3.5 397B A17B$2.85GPT-5.1-Codex-Mini$1.50Coding task
30K in, 4K out
Qwen3.5 397B A17B$30.50$20.75 cachedGPT-5.1-Codex-Mini$15.50$8.90 cachedLong document summary
150K in, 2K out
Qwen3.5 397B A17B$89.50$40.75 cachedGPT-5.1-Codex-Mini$41.50$8.50 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Qwen3.5 397B A17B | GPT-5.1-Codex-Mini |
|---|---|---|
| Context window | 262K tokens | 400K tokens |
| Max output | 236K tokens | 128K tokens |
| Input types | Image, Text, Video | Image, Text |
| Output types | Text | Text |
| Reasoning effort levels | Not available | High, Medium, Low |
| Default reasoning effort | Not available | Medium |
| Release date | February 16, 2026 | November 13, 2025 |
Features
Supported features
API features available for each model.
| Metric | Qwen3.5 397B A17B | GPT-5.1-Codex-Mini |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Temperature | Supported | Not supported |
| Stop sequences | Supported | Not supported |
| Deterministic seed | Supported | Supported |
| Verbosity control | Not supported | Supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
Qwen3.5 397B A17BView full model details- Qwen3.5 397B A17B vs DeepSeek V4 Flash 0423
- Qwen3.5 397B A17B vs Gemini 3 Flash Preview
- Qwen3.5 397B A17B vs GPT-5.4 Mini
- Qwen3.5 397B A17B vs GLM 5V Turbo
- Qwen3.5 397B A17B vs Gemini 3.5 Flash Lite
- Qwen3.5 397B A17B vs Qwen3.5-27B
- Qwen3.5 397B A17B vs GLM 4.7
- Qwen3.5 397B A17B vs Kimi K2 Thinking
- Qwen3.5 397B A17B vs Qwen3.6 27B
- Qwen3.5 397B A17B vs Claude Sonnet 4.5
- Qwen3.5 397B A17B vs GPT-5 Mini
- Qwen3.5 397B A17B vs Claude Sonnet 4
- Qwen3.5 397B A17B vs Qwen3.5-122B-A10B
GPT-5.1-Codex-MiniView full model details- GPT-5.1-Codex-Mini vs DeepSeek V4 Flash 0423
- GPT-5.1-Codex-Mini vs GPT-5.4 Mini
- GPT-5.1-Codex-Mini vs Nemotron 3 Ultra
- GPT-5.1-Codex-Mini vs Gemini 3.5 Flash Lite
- GPT-5.1-Codex-Mini vs GLM 4.7
- GPT-5.1-Codex-Mini vs GPT-5.4 Nano
- GPT-5.1-Codex-Mini vs GPT-5 Mini
- GPT-5.1-Codex-Mini vs o3
- GPT-5.1-Codex-Mini vs Step 3.7 Flash
- GPT-5.1-Codex-Mini vs GLM 4.6
Our take
GPT-5.1-Codex-Mini is 1.9x cheaper for a typical chat. Qwen3.5 397B A17B scores higher on the Artificial Analysis Intelligence Index (21.4 vs 20.4). GPT-5.1-Codex-Mini has the larger context window (400K vs 262K tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is Qwen3.5 397B A17B or GPT-5.1-Codex-Mini cheaper?
GPT-5.1-Codex-Mini is cheaper for a typical chat (2K input tokens and 500 output tokens). GPT-5.1-Codex-Mini costs $0.25 per 1M input tokens and $2 per 1M output tokens, while Qwen3.5 397B A17B costs $0.55 per 1M input tokens and $3.50 per 1M output tokens.
Which has a bigger context window, Qwen3.5 397B A17B or GPT-5.1-Codex-Mini?
GPT-5.1-Codex-Mini supports up to 400K tokens of context, compared with 262K for Qwen3.5 397B A17B.
Is Qwen3.5 397B A17B smarter than GPT-5.1-Codex-Mini?
On the Artificial Analysis Intelligence Index, Qwen3.5 397B A17B scores 21.4 and GPT-5.1-Codex-Mini scores 20.4, putting Qwen3.5 397B A17B ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Qwen3.5 397B A17B and GPT-5.1-Codex-Mini at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Qwen3.5 397B A17B and GPT-5.1-Codex-Mini answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Qwen3.5 397B A17B and GPT-5.1-Codex-Mini at the same time. Compare the answers side by side and keep the best one.