Models
Ids and behaviour observed 2026-11-10. Context window, output cap: official model pages. Prices: official pricing page, USD per million tokens (standard tier, prompts up to 272K tokens).
Recommended: gpt-6-astra (flagship), gpt-6.1-sol (balanced default), gpt-6.1-terra (fast), gpt-6-luna (cheapest).
| Model | Context | Max output | Input | Cached input | Output | Batch in / out |
|---|---|---|---|---|---|---|
gpt-6-sol |
1.05M | 128K | $2 | $0.2 | $10 | $1 / $5 |
gpt-6.1-terra |
1.05M | 128K | $1 | $0.05 | $5 | $0.5 / $2.5 |
gpt-6.1-sol |
1.05M | 128K | $2 | $0.1 | $10 | $1 / $5 |
gpt-6-luna |
1.05M | 128K | $0.1 | $0.01 | $0.5 | $0.05 / $0.25 |
gpt-5.6-terra |
1.05M | 128K | $2 | $0.2 | $12 | $1 / $6 |
gpt-5.6-sol |
1.05M | 128K | $4 | $0.4 | $20 | $2 / $10 |
gpt-6-astra |
1.05M | 128K | $10 | $1 | $50 | $5 / $25 |
gpt-5.5 |
1.05M | 128K | $5 | $0.5 | $30 | $2.5 / $15 |
gpt-5.4 |
1.05M | 128K | $2.5 | $0.25 | $15 | $1.25 / $7.5 |
gpt-5.4-mini |
400K | 128K | $0.75 | $0.075 | $4.5 | $0.375 / $2.25 |
gpt-5.4-nano |
400K | 128K | $0.2 | $0.02 | $1.25 | $0.1 / $0.625 |
gpt-5.3-codex |
400K | 128K | — | — | — | — |
gpt-5.2 |
400K | 128K | $1.75 | $0.175 | $14 | $0.875 / $7 |
gpt-5.6-luna |
1.05M | 128K | $0.2 | $0.02 | $1.2 | $0.1 / $0.6 |
gpt-5.1 |
400K | 128K | $1.25 | $0.125 | $10 | $0.625 / $5 |
gpt-5.2-pro |
400K | 128K | $21 | — | $168 | $10.5 / $84 |
gpt-5-mini |
400K | 128K | $0.25 | $0.025 | $2 | $0.125 / $1 |
gpt-5-nano |
400K | 128K | $0.05 | $0.005 | $0.4 | $0.025 / $0.2 |
gpt-5 |
400K | 128K | $1.25 | $0.125 | $10 | $0.625 / $5 |
gpt-4.1 |
1.05M | 33K | $2 | $0.5 | $8 | $1 / $4 |
gpt-4.1-mini |
1.05M | 33K | $0.4 | $0.1 | $1.6 | $0.2 / $0.8 |
gpt-4o |
128K | 16K | $2.5 | $1.25 | $10 | $1.25 / $5 |
gpt-4o-mini |
128K | 16K | $0.15 | $0.075 | $0.6 | $0.075 / $0.3 |
o3 |
200K | 100K | $2 | $0.5 | $8 | $1 / $4 |
gpt-5-pro |
400K | 272K | $15 | — | $120 | $7.5 / $60 |
chat-latest |
400K | 128K | — | — | — | — |
gpt-5.4-pro |
1.05M | 128K | $30 | — | $180 | $15 / $90 |
gpt-5.5-pro |
1.05M | 128K | $30 | — | $180 | $15 / $90 |
o3-pro |
200K | 100K | $20 | — | $80 | $10 / $40 |
Notes:
- "—" means the official pricing page lists no price; the scripts report it as unknown rather than guess.
- Above 272K input tokens the newest models switch to long-context rates (about 2× input, 1.5× output).
costapplies them. - Fast mode (formerly priority processing) costs about 2×; flex and batch about half.
- Reasoning tokens are billed as output tokens and count against
max_output_tokens. - Embeddings:
text-embedding-3-small$0.02,text-embedding-3-large$0.13 per million tokens. Moderation is free. - Dated snapshots (
gpt-5.4-2026-03-05) resolve to their alias in the scripts. - The models endpoint returns ids only. Never write an id from memory: run
node scripts/openai-api.mjs models.