Compact GPT model for low-latency assistance and high-volume workloads
Specification
openai listing
Context
16K
Max output
4K
Released
2023-03-01
Knowledge cutoff
2021-09-01
Retires
2026-10-23
Open weights
no
Input
text
Output
text
Price
US dollars per million tokens · openai list price
Input
$0.50
Output
$1.50
Cache read
free
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Batch input | openai | $0.25 |
| Batch input | openai | $1.00 |
| Batch output | openai | $0.75 |
| Batch output | openai | $2.00 |
Batch input is 50% below the interactive input price at the same listing.
Quality
6 benchmarks · 1 source
Composite
9th
percentile of 334 scored models
Rank
304 / 334
±0.07 sd
Evidence
6 × 1
one source, or fewer than 3 benchmarks
Effort range
—
one configuration only
reasoning12th3/4 bench
math3rd3/7 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| Chess Puzzles | 0.0 ±0.0 | default | Epoch AI | 2026-08-07 |
| Mystery Game Puzzles | 3.0 ±1.7 | default | Epoch AI | 2026-08-27 |
| MATH level 5 | 13.8 ±0.6 | default · 2 runs | Epoch AI | 2025-01-27 |
| OTIS Mock AIME 2024-2025 | 2.2 ±2.2 | default | Epoch AI | 2026-08-07 |
| GPQA diamond | 27.6 ±1.9 | default · 2 runs | Epoch AI | 2025-01-27 |
| FrontierMath-Tiers-1-3-v2 | 0.0 ±0.0 | default | Epoch AI | 2026-08-27 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 16 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| openaivendor | $0.50 $1.00 | $1.50 $2.00 | free | — | 16K | 4K | 2026-10-23 2026-09-28 |
| poe | $0.45 | $1.40 | — | — | 16K | 2K | — |
| azure | $1.00 $0.50 | $2.00 $1.50 | — | — | 16K 4K | 16K 4K | 2025-03-31 |
| azure-cognitive-services | $0.50 $1.00 | $1.50 $2.00 | — | — | 16K | 16K | — |
| edenai | $0.50 | $1.50 | — | — | 16K | 4K | — |
| impossibl | $0.50 | $1.50 | — | — | 16K | 4K | — |
| llmgateway | $0.50 | $1.50 | free | — | 16K | 4K | — |
| llmgateway-providers | $0.50 | $1.50 | — | — | 16K | 4K | — |
| merge-gateway | $0.50 | $1.50 | — | — | 16K | 4K | — |
| nano-gpt | $0.50 | $1.50 | — | — | 16K | 4K | — |
| openrouter | $1.00 $0.50 | $2.00 $1.50 | — | — | 4K 16K | 4K 4K | — |
| orcarouter | $0.50 | $1.50 | free | — | 16K | 4K | — |
| vercel | $0.50 | $1.50 | — | — | 16K | 4K | — |
| vercel_ai_gateway · vercel-ai-gateway | $0.50 | $1.50 | — | — | 16K | 4K | — |
| kilo | $1.00 $0.50 | $2.00 $1.50 | — | — | 4K 16K | 4K 4K | — |
| github_copilot · github-copilot | — | — | — | — | 16K | 4K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | kilo | Input | $0.50 |
| 2026-09-04 | kilo | Input | $1.00 |
| 2026-09-02 | openrouter | Input | $0.50 |
| 2026-09-04 | openrouter | Input | $1.00 |
| 2026-09-06 | openrouter | Input | $1.00 |
| 2026-09-02 | kilo | Output | $1.50 |
| 2026-09-04 | kilo | Output | $2.00 |
| 2026-09-02 | openrouter | Output | $1.50 |
| 2026-09-04 | openrouter | Output | $2.00 |
| 2026-09-06 | openrouter | Output | $2.00 |
Other listings of this model
same model, different key
More from OpenAI
most-hosted first