Gemini 3.8 Live Extended Thinking
Gemini 3.8 Live Extended Thinking is worth evaluating for rag, agents, and long context when its provider route and context window match the workload.
Use it for
- Teams evaluating rag, agents, and long context
- Workloads that can use a 131k context window
- Buyers comparing 1 tracked provider route
Do not use it for
- Workloads where another current model has stronger sourced task evidence
- Family
- Gemini 3.8
- Released
- 2026-09-15
- Context
- 131k
- Max output
- 65,536
- Specialization
- realtime-voice
- Openness
- Proprietary
- License
- ProprietaryCommercial use: conditional
- Weights
- Not released
- Code
- Unknown
- Training
- Pretrained
Cheapest of 1 route · Google AI Studio
About
Gemini 3.8 Live Extended Thinking (API model code gemini-3.8-live-extended-thinking) is Google DeepMind's high-reasoning Live API audio-to-audio model for complex multi-step voice interactions, announced with Gemini 3.8 Live on September 15, 2026 (~17:00 UTC). First-party AI.dev: inputs text/images/audio/video; outputs text and audio; 131,072 input / 65,536 output tokens; Live API supported; Thinking supported; function calling async-only; search grounding supported; structured outputs / caching / code execution / batch not supported. Product blog positions it for deeper background reasoning while streaming continuous audio; ranks #1 on Artificial Analysis Speech-to-Speech leaderboard per Google blog claim.
Top use-case fit: coding, agents, and build tasks
RAG
Included by capability and metadata signals in the decision map.
Agents
Included by capability and metadata signals in the decision map.
Long context
Included by capability and metadata signals in the decision map.
Provider price ladder
Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Google AI Studio | $0.750 | $4.50 | Serverless |
Available via routers & gateways(13)
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
OpenRouter
HybridUnified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.
Portkey
GatewayProduction AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.
AIRouter
RouterCommercial LLM router that analyzes incoming requests and routes to the optimal model for cost/quality/latency via a drop-in OpenAI-compatible API, with a privacy-preserving embedding mode that avoids sending prompt content.
Helicone
GatewayObservability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache 2.0 open-source core with a managed hosted tier for logging and analytics.
Kong AI Gateway
GatewayMulti-LLM AI gateway built on Kong Gateway 3.x, adding semantic routing, load balancing, guardrails, and MCP traffic analytics as plugins over Kong's existing API management platform.
Capabilities
Benchmark peer barsfor RAG
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
gemini-3.8-live-extended-thinkingCheapest of 1 route · Google AI Studio