GPT-5.3 Codex vs GPT-5.6 Terra
GPT-5.3 Codex (OpenAI) versus GPT-5.6 Terra (OpenAI): API pricing, context window, capabilities and uptime, from the same data as each model page, at the KumoAPI default channel price. Input costs 1.75 Credits / M for GPT-5.3 Codex and 2 Credits / M for GPT-5.6 Terra, so GPT-5.3 Codex is 13% cheaper. Context windows are 400K and 1.05M.
GPT-5.3 Codexgpt-5.3-codexGPT-5.6 Terragpt-5.6-terraSpecs side by side
| Item | GPT-5.3 Codexgpt-5.3-codex | GPT-5.6 Terragpt-5.6-terra |
|---|---|---|
| Input (prompt) · Credits / M | 1.75 | 2 |
| Output (completion) · Credits / M | 14 | 12 |
| Cache read · Credits / M | 0.175 | 0.2 |
| Context window | 400K | 1.05M |
| Max output | 128K | 128K |
| 7-day uptime | — | — |
| Latest probe latency | — | — |
| Measured throughput | — | — |
| Protocols | — | — |
| Sample monthly cost (10M in + 2M out) | 45.5 | 44 |
Prices are the KumoAPI default channel price in Credits (1 Credit = ¥1); green marks the better side. Uptime and latency come from KumoAPI probes; a dash means the model is not probed yet.
Capabilities
FAQ
Which is cheaper, GPT-5.3 Codex or GPT-5.6 Terra?
At the KumoAPI default channel price, GPT-5.3 Codex input costs 1.75 Credits / M and GPT-5.6 Terra input costs 2 Credits / M, so GPT-5.3 Codex is 13% cheaper. Output and cache prices are in the specs table above.
Which has the larger context window, GPT-5.3 Codex or GPT-5.6 Terra?
GPT-5.3 Codex offers 400K tokens, GPT-5.6 Terra offers 1.05M tokens.
Can I switch between GPT-5.3 Codex and GPT-5.6 Terra at any time?
Yes. KumoAPI calls every model with the same API key; switching is just changing the model field in the request, and billing is split per model in one console.
How do the capabilities of GPT-5.3 Codex and GPT-5.6 Terra differ?
Only GPT-5.6 Terra: Response Schema. Every other capability is either supported by both or by neither; see the capability table above.
More comparisons
One API key for both GPT-5.3 Codex and GPT-5.6 Terra
Free credits on sign-up, pay as you go, no monthly fee.