Low-latency Live API model for real-time voice agents with interleaved reasoning and async tools
Context
131K
131,072 tokens
Max output
66K
65,536 tokens
Input
$0.75
per 1M tokens
Output
$4.50
per 1M tokens
Providers
1
1 listings
Intelligence
—
Not yet scored
Pricing
USD per 1M tokens · listed by Vercel AI Gateway
| Token type | Standard |
|---|---|
| Input | $0.75 |
| Output | $4.50 |
| Audio input | $3.00 |
| Audio output | $12.00 |
Lowest input price across providers: $0.75.
Capabilities
ReasoningNo
Tool callYes
Structured outputUnknown
TemperatureYes
AttachmentsYes
Interleaved reasoningNo
Open weightsNo
ModeratedUnknown
Input
TextAudio
Output
TextAudio
Benchmarks
Published scores and Design Arena Elo
No published benchmark scores for this model yet.
Rankings
Position on each OneAtlas leaderboard
Providers · 1
1 listings
| Provider | Model ID | Context | Input limit | Output | Input $ | Output $ | Reasoning $ | Cache read | Cache write | Audio in | Audio out | Reasoning | Tools | Structured | Temp. | Updated |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
 Vercel AI Gateway | google/gemini-3.8-live | 131K | — | 66K | $0.75 | $4.50 | — | — | — | $3.00 | $12.00 | No | Yes | Unknown | Yes | Sep 15, 2026 |