Head to head
GPT-5.3 Codex vs DeepSeek V4 Pro
GPT-5.3 Codex: currentDeepSeek V4 Pro: currentheavy tier
No verdict
Cost per solved task needs a published pass rate for both models. At least one has none, so it is reported as missing rather than estimated.
verified 2026-08-21 · prices from each provider's pricing page
Input $/M tokens
lower is better
Output $/M tokens
lower is better
Cost per solved task
needs a pass rate for both
| GPT-5.3 Codex | DeepSeek V4 Pro | |
|---|---|---|
| Input $/Mtok | $1.75 | $1.32 |
| Output $/Mtok | $14 | $3.96 |
| Cached input $/Mtok | $0.175 | $0.044 |
| Pass rate | missing | missing |
| Pass rate source | missing | missing |
| Cost basis | missing | missing |
| Cost per solved task | missing | missing |
verified 2026-08-21 · heavy task tier; measured rows ignore the tier· Methodology· GPT-5.3 Codex· DeepSeek V4 Pro