Best GPT-5.2 Codex Alternatives
GPT-5.2 Codex by OpenAI is a flagship model priced at $1.75/14 per 1M tokens (in/out). It's on the expensive side — there are cheaper options with similar quality.
GPT-5.2 Codex
OpenAIFlagshipInput
$1.75/1M
Output
$14/1M
Context
200K
Max Output
66K
Why Switch from GPT-5.2 Codex?
Top Alternatives
Dramatically cheaper (56% less), comparable performance.
Input
$2/1M
14% more
Output
$5/1M
64% cheaper
Context
128K
Max Output
16K
11% cheaper, higher benchmark scores, 1M context (5x more).
Input
$2/1M
14% more
Output
$12/1M
14% cheaper
Context
1M
Max Output
64K
11% cheaper, comparable performance, 1M context (5x more).
Input
$2/1M
14% more
Output
$12/1M
14% cheaper
Context
1M
Max Output
66K
Comparable performance.
Input
$2/1M
14% more
Output
$16/1M
14% more
Context
200K
Max Output
66K
29% cheaper, comparable performance, adds audio.
Input
$1.25/1M
29% cheaper
Output
$10/1M
29% cheaper
Context
128K
Max Output
16K
Comparable performance.
Input
$5/1M
186% more
Output
$25/1M
79% more
Context
200K
Max Output
32K
Dramatically cheaper (65% less), comparable performance.
Input
$1.1/1M
37% cheaper
Output
$4.4/1M
69% cheaper
Context
200K
Max Output
100K
Adds web-search.
Input
$3/1M
71% more
Output
$15/1M
7% more
Context
128K
Max Output
16K
Full Comparison Table
| Model | Input $/1M | Output $/1M | Context | MMLU-Pro | HumanEval | Score |
|---|---|---|---|---|---|---|
| Mistral Large 3Mistral | $2.0014% more | $5.0064% cheaper | 128K | 83%-6.0% | 91%-4.5% | 100 |
| Gemini 3.1 ProGoogle | $2.0014% more | $12.0014% cheaper | 1M | 91%+2.0% | 95%-0.5% | 95 |
| Gemini 3 ProGoogle | $2.0014% more | $12.0014% cheaper | 1M | 89.8%+0.8% | 94%-1.5% | 95 |
| GPT-5.3 CodexOpenAI | $2.0014% more | $16.0014% more | 200K | 90%+1.0% | 96.5%+1.0% | 90 |
| GPT-5OpenAI | $1.2529% cheaper | $10.0029% cheaper | 128K | 88.5%-0.5% | 95%-0.5% | 88 |
| Claude Opus 4.6Anthropic | $5.00186% more | $25.0079% more | 200K | 89.5%+0.5% | 95%-0.5% | 83 |
| o4-miniOpenAI | $1.1037% cheaper | $4.4069% cheaper | 200K | 85%-4.0% | 93.5%-2.0% | 78 |
| Grok 4xAI | $3.0071% more | $15.007% more | 128K | 86%-3.0% | 93%-2.5% | 78 |
| o3OpenAI | $0.4077% cheaper | $1.6089% cheaper | 200K | 87%-2.0% | 94.5%-1.0% | 75 |
| GLM-5Zhipu AI | $1.0043% cheaper | $3.2077% cheaper | 200K | 70.4%-18.6% | 91%-4.5% | 75 |
| Gemini 2.5 ProGoogle | $1.2529% cheaper | $10.0029% cheaper | 1M | 87.5%-1.5% | 93.5%-2.0% | 73 |
| Claude Sonnet 4.6Anthropic | $3.0071% more | $15.007% more | 200K | 86%-3.0% | 94%-1.5% | 68 |
| Claude Sonnet 4.5Anthropic | $3.0071% more | $15.007% more | 200K | 84.5%-4.5% | 93%-2.5% | 68 |
| Gemini 3 FlashGoogle | $0.5071% cheaper | $3.0079% cheaper | 1M | 78%-11.0% | 90%-5.5% | 68 |
| GLM-4.7Zhipu AI | $0.6066% cheaper | $2.2084% cheaper | 200K | 84.3%-4.7% | — | 62 |
| GPT-4oOpenAI | $2.5043% more | $10.0029% cheaper | 128K | 80.5%-8.5% | 91%-4.5% | 60 |
| Gemini 2.5 FlashGoogle | $0.1591% cheaper | $0.6096% cheaper | 1M | 76%-13.0% | 89.5%-6.0% | 58 |
| DeepSeek R1DeepSeek | $0.5569% cheaper | $2.1984% cheaper | 128K | 84%-5.0% | 92%-3.5% | 56 |
| Claude Haiku 4.5Anthropic | $0.8054% cheaper | $4.0071% cheaper | 200K | 69.4%-19.6% | 88.1%-7.4% | 54 |
| Mistral Medium 3Mistral | $0.4077% cheaper | $2.0086% cheaper | 128K | 76%-13.0% | 87%-8.5% | 54 |
| Llama 4 MaverickMeta | $0.3182% cheaper | $0.8594% cheaper | 1M | 80.5%-8.5% | 90.2%-5.3% | 46 |
| DeepSeek V3DeepSeek | $0.1492% cheaper | $0.2898% cheaper | 164K | 78%-11.0% | 89%-6.5% | 46 |
| MiniMax M2.5MiniMax | $0.3083% cheaper | $1.2091% cheaper | 200K | 82%-7.0% | 90%-5.5% | 46 |
| GPT-4o MiniOpenAI | $0.1591% cheaper | $0.6096% cheaper | 128K | 68%-21.0% | 87.2%-8.3% | 44 |
| Llama 4 ScoutMeta | $0.1890% cheaper | $0.6396% cheaper | 10M | 74.2%-14.8% | 86%-9.5% | 38 |