Compact GPT model for low-latency assistance and high-volume workloads
Specification
most-agreed values
Context
400K
Max output
128K
Released
2026-05-05
Knowledge cutoff
2025-12-01
Retires
2027-05-18
Open weights
no
Input
text, image, pdf
Output
text
Price
US dollars per million tokens · most-agreed
Input
$5.00
Output
$30.00
Cache read
$0.50
Cache write
$2.50
Available from 7 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| nano-gpt | $2.00 | $10.00 | $0.10 | $2.50 | 1.1M | 128K | — |
| aihubmix · aihubmix | $5.00 | $30.00 | $0.50 | — | 400K | 128K | — |
| azure | $5.00 $5.50 | $30.00 $33.00 | $0.50 $0.55 | — | 400K 128K | 128K | 2027-05-18 |
| azure_ai | $5.00 | $30.00 | $0.50 | — | 128K | 128K | 2027-05-18 |
| azure-cognitive-services | $5.00 | $30.00 | $0.50 | — | 400K | 128K | — |
| kilo | $5.00 | $30.00 | $0.50 | — | 400K | 128K | — |
| openrouter | $5.00 | $30.00 | $0.50 | — | 400K | 128K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | azure | Cache read | $0.50 |
| 2026-09-15 | azure | Cache read | $0.50 |
| 2026-09-02 | nano-gpt | Cache read | $0.20 |
| 2026-10-28 | nano-gpt | Cache read | $0.10 |
| 2026-09-02 | openrouter | Cache read | $0.50 |
| 2026-09-13 | openrouter | Cache read | $0.50 |
| 2026-10-10 | openrouter | Cache read | $0.50 |
| 2026-09-02 | azure | Input | $5.00 |
| 2026-09-15 | azure | Input | $5.00 |
| 2026-09-02 | openrouter | Input | $5.00 |
| 2026-09-13 | openrouter | Input | $5.00 |
| 2026-10-10 | openrouter | Input | $5.00 |
| 2026-09-02 | azure | Output | $30.00 |
| 2026-09-15 | azure | Output | $30.00 |
| 2026-09-02 | openrouter | Output | $30.00 |
| 2026-09-13 | openrouter | Output | $30.00 |
| 2026-10-10 | openrouter | Output | $30.00 |
More from OpenAI
most-hosted first