gpt-5.6-terra
- Input / 1M
- $2.00
- Output / 1M
- $12.00
- Cached input
- $0.20
- Context
- 1.1M
A 1,000-token prompt costs $0.00200 to send. Token counts for OpenAI models are exact — run through the published tokenizer.
- Vision
- Tool calling
- Reasoning
- Max output 128K
Long-context rate
Past 272K tokens in a single request, gpt-5.6-terra switches to $4.00 input and $18.00 output per million — 2.0× the base input rate. Most calculators quote only the base figure.
Writing to the cache costs $2.50 . Reads are $0.20.
Priced closest to this
| Model | Provider | Input | Output | |
|---|---|---|---|---|
| claude-sonnet-5 | Anthropic | $2.00 | $10.00 | compare |
| gemini-3-pro-preview | $2.00 | $12.00 | ||
| gemini-3.1-pro-preview | $2.00 | $12.00 | ||
| gemini-3.1-pro-preview-customtools | $2.00 | $12.00 | ||
| gemini-robotics-er-2-preview | $2.00 | $10.00 | ||
| gpt-4.1 | OpenAI | $2.00 | $8.00 |
Compare gpt-5.6-terra
- vs claude-fable-5
- vs claude-opus-5
- vs claude-sonnet-5
- vs command-r
- vs command-r-plus
- vs deepseek-v3.2
- vs deepseek-v4-flash
- vs deepseek-v4-pro
- vs gemini-3.5-flash
- vs gemini-3.5-flash-lite
- vs gemini-3.6-flash
- vs gpt-5.6
- vs gpt-5.6-sol
- vs gpt-oss-120b
- vs grok-4-1-fast
- vs grok-4-1-fast-reasoning
- vs grok-4.20-0309-reasoning
- vs jamba-large-1.6
- vs jamba-large-1.7
- vs jamba-mini-1.7
- vs kimi-k2-0905-preview
- vs kimi-k2.5
- vs kimi-k2.6
- vs llama-3.1-70b-instruct
- vs llama-3.1-8b-instant
- vs llama-3.1-8b-instruct
- vs llama-3.3-70b-versatile
- vs ministral-8b-latest
- vs mistral-large-3
- vs mistral-medium-3-5
- vs sonar-pro
- vs zai-glm-4.6
- vs zai-glm-4.7