Proprietary dense model from OpenAI. Parameter count is undisclosed. Native 1,050,000-token context, 128K max output, knowledge cutoff February 16, 2026. Text + image in, text out. Reasoning effort spans none through max; medium is default. Supports programmatic tool calling, explicit prompt caching (cache writes billed at 1.25x input), persisted reasoning, and a pro reasoning mode for harder tasks.
-
Pricing: $5/1M input, $30/1M output.
Agents on Rails benchmark (Aug 2026, Le Mans round). 84.1% accuracy on 63 runs - solidly frontier but behind the Opus 5 / Fable 5 / Kimi K3 cluster. Cost was about $0.52 mean per run. A good default for complex Rails work if you do not need the last few points of accuracy.
AI-generated content marks
The provider reports that this model does not add embedded watermarks or provenance metadata to generated output.
Provider transparency docs →
coding
reasoning
agentic
- Context
- 1050k
- License
- proprietary
- Origin
-
🇺🇸
USA
- Released
- Aug 2026
Or run it in the cloud
Live per-provider pricing, throughput and uptime - refreshed 2 months ago via OpenRouter. Click a column to sort.
some pricing may be stale - last verified 2026-08-15
|
Provider
|
Type
|
Input $/M
|
Output $/M
|
Cache $/M
|
Tok/s
|
Latency
|
Uptime
|
Value
|
|
|
API
|
5.00 |
30.00 |
0.500 |
- |
- |
- |
cheapest
|
|
|
API
|
5.00 |
30.00 |
- |
- |
- |
- |
|
Default order: throughput among 95%+ uptime providers, then latency; subscriptions last. Sort by any column. Subscription rows show $/mo in the Value column - per-token columns are "-". Affiliate links are marked sponsored / nofollow. Confirm current pricing on the provider's site before committing.
PRICE HISTORY
Inference cost over time
Data accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API.
Loading price history...