Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | — | 480B |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 1M | 256k |
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $0.40 | $1.00 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | $1.60 | $5.00 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | $0.10 | — |
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.40Azure | $0.22Google |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.60Azure | $1.00DeepInfra |
| $160OpenAI list price | $110DeepInfra · turbo · fp4 | |
| These models have no shared benchmark scores. | ||
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | — | 20% |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 23.6% | — |
| Overview | ||
| Company | OpenAI | Qwen |
| Release date | Apr 14 2025 | Jul 22 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
GPT-4.1 minivsClaude Haiku 5.5Qwen3-CodervsClaude Haiku 5.5GPT-4.1 minivsGemini 4 ArgonQwen3-CodervsGemini 4 ArgonGPT-4.1 minivsMuse Spark OpenQwen3-CodervsMuse Spark OpenGPT-4.1 minivsGrok 4.7Qwen3-CodervsGrok 4.7GPT-4.1 minivsDeepSeek-V4.1-Flash-1017Qwen3-CodervsDeepSeek-V4.1-Flash-1017GPT-4.1 minivsMistral Large 4Qwen3-CodervsMistral Large 4Frequently asked questions
GPT-4.1 mini and Qwen3-Coder don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. GPT-4.1 mini is cheaper on both input and output: $0.40 vs $1.00 per million input tokens, and $1.60 vs $5.00 per million output tokens. Figures are base-tier rates. GPT-4.1 mini shipped 99 days before Qwen3-Coder, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (GPT-4.1 mini) vs 256k (Qwen3-Coder). GPT-4.1 mini is closed, while Qwen3-Coder is open weight.
Direct benchmark comparisons are unavailable — GPT-4.1 mini and Qwen3-Coder don't publish scores on any of the same benchmarks.