Near-Astra performance for complex coding, computer use, and professional work at a lower cost.
Specification
openai listing
Context
1.1M
Max output
128K
Released
2026-09-29
Knowledge cutoff
2026-04-30
Retires
—
Open weights
no
Input
text, image, pdf
Output
text
Price
US dollars per million tokens · openai list price
Input
$2.00
Output
$10.00
Cache read
$0.10
Cache write
$2.50
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Batch input | openai | $1.00 |
| Batch output | openai | $5.00 |
| Priority input | openai | $4.00 |
| Priority output | openai | $20.00 |
Batch input is 50% below the interactive input price at the same listing.
Long-context price tiers
the rate above each context threshold
| Above | Price | $/M |
|---|---|---|
| 272K | Cache read | $0.20 |
| 272K | Cache write | $5.00 |
| 272K | Input | $4.00 |
| 272K | Output | $15.00 |
Quality
1 benchmark · 1 source
Composite
95th
percentile of 340 scored models
Rank
17 / 340
±0.70 sd
Evidence
1 × 1
too little evidence to place with confidence
Effort range
0.7
points between effort settings
general92nd1/1 bench
By reasoning effort
every setting placed on the same scale as the leaderboard
| Setting | Composite | Benchmarks behind it |
|---|---|---|
| max | 97th | 1 |
| xhigh | 95th | 1 |
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| LiveBench | 82.5 | max · 23 runs | LiveBench | 2026-06-25 |
| ↳ | 81.8 | xhigh · 23 runs | LiveBench | 2026-06-25 |
| Settings differ by 0.7 points on this benchmark. | ||||
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 21 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| openaivendor | $2.00 | $10.00 | $0.10 | $2.50 | 1.1M 922K | 128K | — |
| openrouter · batch | $1.00 | $5.00 | $0.05 | $1.25 | 1.1M | 128K | — |
| azure | $2.00 | $10.00 | $0.10 | $2.50 | 1.1M 922K | 128K | — |
| azure_ai | $2.00 | $10.00 | $0.10 | $2.50 | 922K | 128K | — |
| azure-cognitive-services | $2.00 | $10.00 | $0.10 | $2.50 | 1.1M | 128K | — |
| bedrock_converse | $2.00 | $10.00 | $0.10 | $2.50 | 1.1M | 131K | — |
| bedrock_converse · global | $2.00 | $10.00 | $0.10 | $2.50 | 1.1M | 131K | — |
| edenai | $2.00 | $10.00 | $0.10 | $2.50 | 1.1M | 128K | — |
| github-copilot | $2.00 | $10.00 | $0.10 | $2.50 | 1.1M | 128K | — |
| kilo | $2.00 | $10.00 | $0.10 | $2.50 | 1.1M | 128K | — |
| llmgateway | $2.00 | $10.00 | $0.10 | $2.50 | 1.1M | 128K | — |
| llmgateway-providers | $2.00 | $10.00 | $0.10 | $2.50 | 1.1M | 128K | — |
| merge-gateway | $2.00 | $10.00 | $0.10 | $2.50 | 1.1M | 128K | — |
| nano-gpt | $2.00 | $10.00 | $0.10 | $2.50 | 1.1M | 128K | — |
| opencode | $2.00 | $10.00 | $0.10 | $2.50 | 1.1M | 128K | — |
| openrouter | $2.00 | $10.00 | $0.10 | $2.50 | 1.1M | 128K | — |
| requesty | $2.00 | $10.00 | $0.10 | — | 1.1M | 128K | — |
| vercel | $2.00 | $10.00 | $0.10 | $2.50 | 1.1M | 128K | — |
| bedrock_converse · us | $2.20 | $11.00 | $0.11 | $2.75 | 1.1M | 131K | — |
| bedrock_mantle · bedrock-mantle | $2.20 | $11.00 | $0.11 | $2.75 | 1.1M | 131K | — |
| cortecs | $2.40 | $11.999 | $0.12 | $3.00 | 1.1M | 128K | — |
Other listings of this model
same model, different key
More from OpenAI
most-hosted first