OpenAI: GPT-5.6 Luna (batch)
Pricing matrix USD per 1M tokens
| Field | Consensus | Evidence |
|---|---|---|
| Input | $0.1 | single source 2 sources |
| Output | $0.6 | single source 2 sources |
| Cache read | $0.01 | single source 2 sources |
| Cache write (5m) | Unverified（未验证，不填 0） | not published |
| Cache write (1h) | Unverified（未验证，不填 0） | not published |
| Reasoning tokens | Unverified（未验证，不填 0） | not published |
证据链：各源原值并列（audit trail，点击展开）
| Field | Source | Raw value (USD/1M) | Independent | Observed |
|---|---|---|---|---|
| input | openrouter | 0.1000 | yes | 2026-10-01 08:00 |
| input | litellm <span class="badge mute">mirror</span> | 0.1000 | no | 2026-10-01 08:00 |
| output | openrouter | 0.6000 | yes | 2026-10-01 08:00 |
| output | litellm <span class="badge mute">mirror</span> | 0.6000 | no | 2026-10-01 08:00 |
| cache_read | openrouter | 0.0100 | yes | 2026-10-01 08:00 |
| cache_read | litellm <span class="badge mute">mirror</span> | 0.0100 | no | 2026-10-01 08:00 |
Long-context tier jumps ⚠
When prompt tokens cross a threshold, the entire request is re-priced at the higher tier — not just the excess. This is the #1 hidden cost on long-context workloads.
| Prompt ≥ tokens | input | output | cache read |
|---|---|---|---|
| 0 (base) | $0.1 | $0.6 | $0.01 |
| 272,000 | 未验证 | 未验证 | 未验证 |
Run this model through the real-bill calculator →
Sources
- OpenRouter — live API (primary)
- LiteLLM — model_prices_and_context_window.json (pinned to commit at fetch time)
- models.dev — api.json
This is an estimate based on public sticker prices, not your invoice. Machine-readable: /data/v1/pricing/openai-gpt-5-6-luna-batch.json