{ "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-09", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "tool": { "slug": "gemini-live", "name": "Gemini Live API", "vendor": "Google", "vendorUrl": "https://ai.google.dev", "kind": "http-api", "category": "voice-agents", "summary": "Google's Live API runs real-time spoken conversations with Gemini audio-to-audio models over a stateful WebSocket. It takes audio, images and text, speaks back, and supports interruptions, function calling and Google Search grounding.", "url": "https://www.anchorterminal.com/tools/gemini-live", "markdownUrl": "https://www.anchorterminal.com/tools/gemini-live.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/gemini-live.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/gemini-live.json", "repo": "https://github.com/google-gemini/gemini-live-api-examples", "license": "Proprietary service under the Gemini API Additional Terms of Service. The Python and JavaScript SDKs are Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://generativelanguage.googleapis.com/v1beta", "packages": [ { "registry": "pypi", "name": "google-genai" }, { "registry": "npm", "name": "@google/genai" } ], "auth": "api-key", "authNotes": "Self-serve API key from Google AI Studio, tied to a Google Cloud project. Keys created since 28 May 2026 are authorisation keys bound to a service account and restricted to the Gemini API, and unrestricted standard keys are rejected. The raw WebSocket guide passes the key as a `key` query parameter. For browsers and phones, a backend mints an ephemeral token (preview) at `POST /v1beta/auth_tokens`, single use by default, 1 minute to start a session and 30 minutes to use it, optionally locked to a model and configuration.", "pricing": "freemium", "pricingNotes": "Free tier on the Live models with no billing account, where content is used to improve Google products. Paid tier per 1M tokens on `gemini-3.8-live`, the extended thinking model and `gemini-3.1-flash-live-preview`. Text in $0.75, audio in $3.00 (about $0.005 a minute), image or video in $1.00, text out $4.50, audio out $12.00 (about $0.018 a minute). Google Search grounding $14 per 1,000 queries after 5,000 free a month. Each turn re-bills the whole session context. Paid tier needs a linked billing account and a $5 minimum prepayment (https://ai.google.dev/gemini-api/docs/pricing, checked 2026-10-08).", "priceSummary": "$14 / 1k req", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the Live API docs, the pricing page or the billing guide (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 29486957, "pypiWeekly": 34128301, "asOf": "2026-10-08" }, "docsUrl": "https://ai.google.dev/gemini-api/docs/live-api", "llmsTxt": "https://ai.google.dev/gemini-api/docs/llms.txt", "capabilities": [ "voice.agent", "voice.speech-to-speech", "voice.tools" ], "tags": [ "hosted", "freemium", "free-tier", "closed-source", "speech-to-speech", "websocket", "streaming", "python", "typescript", "llms-txt", "api-key", "function-calling" ], "lastRelease": "2026-09-15", "graded": true, "anchor": { "graded": true, "score": 57.1, "grade": "C", "agentReady": false, "rank": 560, "ranked": true, "rankOf": 842, "categoryRank": 7, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 69, "maintenance": 83, "payments": 40, "reliability": 41, "schema": 66, "security": 48, "transparency": 72 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 41, "points": 8.2, "reason": "Graded as a hosted API on the Gemini Developer API. A status page exists at aistudio.google.com/status, but it is drawn by script and we could read no components or history on 8 October (10 of 20, and 5 of 30 for the incident line with no readable record). Session limits are published, 15 minutes for audio and 2 for audio with video without compression, connections of about 10 minutes, and spend limits of $10, $50 and $200 per 10 minutes on Tiers 1 to 3. Per-model request limits and concurrent sessions are shown only in AI Studio (8 of 15). The server sends a GoAway message with `timeLeft` before closing, session resumption handles last 2 hours, and the troubleshooting guide gives exponential backoff with jitter for 429 and 503 (12 of 15). No SLA found for the Developer API (0). `gemini-3.8-live` is stable and generally available since 15 September, but the endpoint is `v1beta`, ephemeral tokens are in preview and three docs pages still label the Live API a preview (6 of 10)." }, { "key": "performance", "name": "Performance", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes." }, { "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "effectiveWeight": 16.25, "score": 66, "points": 10.73, "reason": "No AsyncAPI or similar file for the WebSocket messages was found. The keyless Discovery document (revision 20261006) types `auth_tokens.create` and five related schemas, `BidiGenerateContentSetup` among them, but not the client and server messages (8 of 25). llms.txt with a Markdown twin of every page (10). The capabilities guide, model comparison table and best practices page say when to use each model, voice activity mode and tool behaviour (16 of 20). The reference at ai.google.dev/api/live lists every message with field types, enums such as `ActivityHandling`, `TurnCoverage` and the sensitivity levels, and required marks, as tables and not as a schema (12 of 15). Python and JavaScript examples on every guide, but no list of WebSocket close codes or Live error responses was found (8 of 15). Dated changelog and versioned model names, less 3 because the tools page omits the 3.8 models, the overview says 70 languages where the capabilities guide lists 99, and preview banners remain after general availability (12 of 15)." }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 69, "points": 11.21, "reason": "Scored as an API. Context can be sized with sliding-window compression and a trigger token count, media resolution is configurable and `UsageMetadata` reports token counts (18 of 25). No lists to page. Output controls are turn coverage, optional transcription of either side and the compression window (12 of 20). Server signals an agent can act on are `interrupted`, `generationComplete`, GoAway and tool call cancellation, but there is no documented error catalogue for the socket (10 of 20). Session resumption makes reconnects safe, resuming does not spend a token use, and non-blocking function calls take `SILENT`, `WHEN_IDLE` or `INTERRUPT` scheduling. No idempotency guidance for tool side effects after an interruption (14 of 20). A session needs only a model and a response modality, voice activity detection is automatic, and there are official Python and JavaScript SDKs (15)." }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 48, "points": 8.4, "reason": "Keys created since 28 May 2026 are authorisation keys bound to a service account and restricted to the Gemini API, with IP and origin restrictions, a leak checklist and rejection of unrestricted standard keys. Ephemeral tokens add expiry and use counts (25 of 30). The WebSocket guide's documented method is the API key in a `key` query parameter, and ephemeral tokens in `access_token`, so we deduct 10 (15 of 30). Ephemeral tokens can be locked to a model and configuration and to one session, which keeps system instructions server side. There is no approval step for tool calls, which the client runs itself (12 of 20). The model hears callers and can ground on Google Search, and the best practices page covers guardrails in system instructions but not prompt injection (5 of 15). Opt-in logs exist for billed projects, and we did not confirm they cover Live sessions. Usage is visible per project (8 of 15). security.txt on google.com valid to 2030 with a vulnerability reward programme. No certification naming the Developer API was found (8 of 20)." }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 40, "points": 5, "reason": "No x402, MPP or L402 (0 of 40). Per-token prices with per-minute equivalents are published without a login (20). The Live models are free of charge on the free tier, and the billing guide says new accounts start there with billing linked only to move to the paid tier (20). A key needs a Google account and AI Studio, so a person signs up in a browser (0)." }, { "key": "tasks", "name": "Task success", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored." }, { "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "effectiveWeight": 8.75, "score": 83, "points": 7.26, "reason": "`gemini-3.8-live` went generally available on 15 September 2026, 23 days before the check (30). Three dated Live entries in the last 90 days, the robotics streaming model on 30 July, `gemini-3.5-transcribe-live` on 26 August and the 3.8 Live models on 15 September (20). Closed service with a changelog updated several times a month. Support channels were not tested (10 of 15). Current official SDKs, `google-genai` v2.29.0 and `@google/genai` v2.28.0, both tagged 7 October with about weekly tags since August (15). Apache-2.0 SDKs with type-check workflows in the Python repository and Node 20 or later stated. CI results were not read (8 of 10)." }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 72, "points": 6.3, "note": "editorial 55, provenance 89", "reason": "Closed service with clear terms, SDKs under Apache-2.0 (15 of 30). The terms, pricing page and zero data retention page agree that free-tier content improves Google products and paid content does not. The terms say abuse logs are kept for a limited period and the abuse monitoring page gives 55 days. Session state is kept up to 24 hours when resumption is on, and Search grounding data 30 days (20 of 30). A deprecations table gives earliest shutdown dates and replacements, with 17 November 2026 for the two older Live previews, about nine weeks after the replacement shipped, and no stated minimum notice (15 of 20). The terms say data may be stored transiently or cached in any country where Google has facilities. The Data Processing Addendum applies to paid services, and no sub-processor list was read (5 of 20)." } ], "assessment": { "date": "2026-10-08", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "Scored as an API. Context can be sized with sliding-window compression and a trigger token count, media resolution is configurable and `UsageMetadata` reports token counts (18 of 25). No lists to page. Output controls are turn coverage, optional transcription of either side and the compression window (12 of 20). Server signals an agent can act on are `interrupted`, `generationComplete`, GoAway and tool call cancellation, but there is no documented error catalogue for the socket (10 of 20). Session resumption makes reconnects safe, resuming does not spend a token use, and non-blocking function calls take `SILENT`, `WHEN_IDLE` or `INTERRUPT` scheduling. No idempotency guidance for tool side effects after an interruption (14 of 20). A session needs only a model and a response modality, voice activity detection is automatic, and there are official Python and JavaScript SDKs (15).", "maintenance": "`gemini-3.8-live` went generally available on 15 September 2026, 23 days before the check (30). Three dated Live entries in the last 90 days, the robotics streaming model on 30 July, `gemini-3.5-transcribe-live` on 26 August and the 3.8 Live models on 15 September (20). Closed service with a changelog updated several times a month. Support channels were not tested (10 of 15). Current official SDKs, `google-genai` v2.29.0 and `@google/genai` v2.28.0, both tagged 7 October with about weekly tags since August (15). Apache-2.0 SDKs with type-check workflows in the Python repository and Node 20 or later stated. CI results were not read (8 of 10).", "payments": "No x402, MPP or L402 (0 of 40). Per-token prices with per-minute equivalents are published without a login (20). The Live models are free of charge on the free tier, and the billing guide says new accounts start there with billing linked only to move to the paid tier (20). A key needs a Google account and AI Studio, so a person signs up in a browser (0).", "reliability": "Graded as a hosted API on the Gemini Developer API. A status page exists at aistudio.google.com/status, but it is drawn by script and we could read no components or history on 8 October (10 of 20, and 5 of 30 for the incident line with no readable record). Session limits are published, 15 minutes for audio and 2 for audio with video without compression, connections of about 10 minutes, and spend limits of $10, $50 and $200 per 10 minutes on Tiers 1 to 3. Per-model request limits and concurrent sessions are shown only in AI Studio (8 of 15). The server sends a GoAway message with `timeLeft` before closing, session resumption handles last 2 hours, and the troubleshooting guide gives exponential backoff with jitter for 429 and 503 (12 of 15). No SLA found for the Developer API (0). `gemini-3.8-live` is stable and generally available since 15 September, but the endpoint is `v1beta`, ephemeral tokens are in preview and three docs pages still label the Live API a preview (6 of 10).", "schema": "No AsyncAPI or similar file for the WebSocket messages was found. The keyless Discovery document (revision 20261006) types `auth_tokens.create` and five related schemas, `BidiGenerateContentSetup` among them, but not the client and server messages (8 of 25). llms.txt with a Markdown twin of every page (10). The capabilities guide, model comparison table and best practices page say when to use each model, voice activity mode and tool behaviour (16 of 20). The reference at ai.google.dev/api/live lists every message with field types, enums such as `ActivityHandling`, `TurnCoverage` and the sensitivity levels, and required marks, as tables and not as a schema (12 of 15). Python and JavaScript examples on every guide, but no list of WebSocket close codes or Live error responses was found (8 of 15). Dated changelog and versioned model names, less 3 because the tools page omits the 3.8 models, the overview says 70 languages where the capabilities guide lists 99, and preview banners remain after general availability (12 of 15).", "security": "Keys created since 28 May 2026 are authorisation keys bound to a service account and restricted to the Gemini API, with IP and origin restrictions, a leak checklist and rejection of unrestricted standard keys. Ephemeral tokens add expiry and use counts (25 of 30). The WebSocket guide's documented method is the API key in a `key` query parameter, and ephemeral tokens in `access_token`, so we deduct 10 (15 of 30). Ephemeral tokens can be locked to a model and configuration and to one session, which keeps system instructions server side. There is no approval step for tool calls, which the client runs itself (12 of 20). The model hears callers and can ground on Google Search, and the best practices page covers guardrails in system instructions but not prompt injection (5 of 15). Opt-in logs exist for billed projects, and we did not confirm they cover Live sessions. Usage is visible per project (8 of 15). security.txt on google.com valid to 2030 with a vulnerability reward programme. No certification naming the Developer API was found (8 of 20).", "transparency": "Closed service with clear terms, SDKs under Apache-2.0 (15 of 30). The terms, pricing page and zero data retention page agree that free-tier content improves Google products and paid content does not. The terms say abuse logs are kept for a limited period and the abuse monitoring page gives 55 days. Session state is kept up to 24 hours when resumption is on, and Search grounding data 30 days (20 of 30). A deprecations table gives earliest shutdown dates and replacements, with 17 November 2026 for the two older Live previews, about nine weeks after the replacement shipped, and no stated minimum notice (15 of 20). The terms say data may be stored transiently or cached in any country where Google has facilities. The Data Processing Addendum applies to paid services, and no sub-processor list was read (5 of 20)." }, "sources": [ { "what": "Live API overview (Markdown twin)", "url": "https://ai.google.dev/gemini-api/docs/live-api.md.txt", "seen": "2026-10-08" }, { "what": "capabilities guide, model comparison, limits and languages", "url": "https://ai.google.dev/gemini-api/docs/live-api/capabilities.md.txt", "seen": "2026-10-08" }, { "what": "session management", "url": "https://ai.google.dev/gemini-api/docs/live-api/session-management.md.txt", "seen": "2026-10-08" }, { "what": "ephemeral tokens", "url": "https://ai.google.dev/gemini-api/docs/live-api/ephemeral-tokens.md.txt", "seen": "2026-10-08" }, { "what": "WebSocket quickstart and authentication", "url": "https://ai.google.dev/gemini-api/docs/live-api/get-started-websocket.md.txt", "seen": "2026-10-08" }, { "what": "tool use", "url": "https://ai.google.dev/gemini-api/docs/live-api/tools.md.txt", "seen": "2026-10-08" }, { "what": "best practices and billing model", "url": "https://ai.google.dev/gemini-api/docs/live-api/best-practices.md.txt", "seen": "2026-10-08" }, { "what": "Live API reference", "url": "https://ai.google.dev/api/live.md.txt", "seen": "2026-10-08" }, { "what": "gemini-3.8-live model page", "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.8-live.md.txt", "seen": "2026-10-08" }, { "what": "pricing", "url": "https://ai.google.dev/gemini-api/docs/pricing.md.txt", "seen": "2026-10-08" }, { "what": "rate limits", "url": "https://ai.google.dev/gemini-api/docs/rate-limits.md.txt", "seen": "2026-10-08" }, { "what": "billing", "url": "https://ai.google.dev/gemini-api/docs/billing.md.txt", "seen": "2026-10-08" }, { "what": "release notes", "url": "https://ai.google.dev/gemini-api/docs/changelog.md.txt", "seen": "2026-10-08" }, { "what": "deprecations", "url": "https://ai.google.dev/gemini-api/docs/deprecations.md.txt", "seen": "2026-10-08" }, { "what": "API keys", "url": "https://ai.google.dev/gemini-api/docs/api-key.md.txt", "seen": "2026-10-08" }, { "what": "zero data retention", "url": "https://ai.google.dev/gemini-api/docs/zdr.md.txt", "seen": "2026-10-08" }, { "what": "abuse monitoring", "url": "https://ai.google.dev/gemini-api/docs/usage-policies.md.txt", "seen": "2026-10-08" }, { "what": "logs policy", "url": "https://ai.google.dev/gemini-api/docs/logs-policy.md.txt", "seen": "2026-10-08" }, { "what": "troubleshooting and retry guidance", "url": "https://ai.google.dev/gemini-api/docs/troubleshooting.md.txt", "seen": "2026-10-08" }, { "what": "coding agent resources", "url": "https://ai.google.dev/gemini-api/docs/coding-agents.md.txt", "seen": "2026-10-08" }, { "what": "Gemini API Additional Terms of Service", "url": "https://ai.google.dev/gemini-api/terms", "seen": "2026-10-08" }, { "what": "Google Privacy Policy", "url": "https://policies.google.com/privacy", "seen": "2026-10-08" }, { "what": "Discovery document", "url": "https://generativelanguage.googleapis.com/$discovery/rest?version=v1beta", "seen": "2026-10-08" }, { "what": "status page (not readable)", "url": "https://aistudio.google.com/status", "seen": "2026-10-08" }, { "what": "security.txt", "url": "https://www.google.com/.well-known/security.txt", "seen": "2026-10-08" }, { "what": "Python SDK tags", "url": "https://github.com/googleapis/python-genai", "seen": "2026-10-08" }, { "what": "JavaScript SDK tags", "url": "https://github.com/googleapis/js-genai", "seen": "2026-10-08" }, { "what": "npm latest version", "url": "https://registry.npmjs.org/@google/genai/latest", "seen": "2026-10-08" }, { "what": "example apps repository", "url": "https://github.com/google-gemini/gemini-live-api-examples", "seen": "2026-10-08" } ], "openQuestions": [ "unchecked: the incident history and components on aistudio.google.com/status, which is drawn by script", "unchecked: per-model request limits and concurrent session limits for the Live models, shown only at aistudio.google.com/rate-limit, a path robots.txt disallows", "unchecked: whether opt-in AI Studio logs record Live API sessions", "unchecked: GitHub star counts, because the GitHub API was rate limited", "unchecked: the Live API on Vertex AI (Gemini Enterprise Agent Platform), its SLA, certifications and zero data retention terms. This listing grades the Gemini Developer API", "unchecked: Google's sub-processor list and the Data Processing Addendum text", "Whether Live responses are produced in 70 or 99 languages. The overview and the capabilities guide disagree", "Whether the 24-hour session state retention on the zero data retention page and the 2-hour handle validity on the session page describe the same store", "Go and Java SDK support for Live was not checked" ] }, "negative": 0, "verdict": "A speech-to-speech API with per-token prices published, a free tier and a generally available model, `gemini-3.8-live`, since 15 September 2026. The documented raw WebSocket connection carries the API key in the URL, connections reset about every 10 minutes, and no SLA or readable incident history was found for the Developer API.", "bestFor": "Teams building their own voice or vision assistant on a single speech-to-speech model with function calling and Search grounding, who can run a backend for tokens and audio transport.", "strengths": [ "`gemini-3.8-live` went generally available on 15 September 2026 with asynchronous function calling as the default and three response scheduling modes.", "Ephemeral tokens can be single use, expire in 30 minutes by default and be locked to a model and session configuration.", "Prices are public per million tokens with per-minute equivalents, $0.005 a minute of audio in and $0.018 a minute of audio out.", "Session resumption handles, a GoAway message with `timeLeft` and sliding-window context compression are documented for long sessions.", "Free tier on the Live models with no billing account, and paid-tier content isn't used to improve Google products per the pricing page." ], "weaknesses": [ "The WebSocket guide authenticates with the API key as a `key` query parameter, and ephemeral tokens as an `access_token` query parameter.", "The status page at aistudio.google.com/status renders in the browser only, so no incident history could be read, and no SLA was found for the Developer API.", "No machine-readable contract for the WebSocket messages was found. The Discovery document types only the setup and token schemas.", "The capabilities, best practices and API reference pages still say the Live API is in preview, and the docs give both 70 and 99 supported languages.", "No telephony. Phone calls need a partner such as Voximplant, LiveKit or Pipecat, and concurrent session limits are shown only inside AI Studio." ], "agentNotes": [ "Enable `sessionResumption` and keep the newest handle. Connections end after about 10 minutes, and handles stay valid for 2 hours.", "Set `contextWindowCompression` with a sliding window. Without it audio sessions stop at 15 minutes and audio with video at 2 minutes, and every turn re-bills the whole context.", "On `gemini-3.8-live` function calls are non-blocking by default. Set `behavior: BLOCKING` if the model must wait for the tool response.", "Send 16 kHz 16-bit PCM in 20 to 40 ms chunks and discard buffered playback when `interrupted` is true.", "Keep the API key on a server and send it through the SDK. Give browsers an ephemeral token from `POST /v1beta/auth_tokens`, locked with `liveConnectConstraints`." ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 57.1 } ], "editorialScores": { "ergonomics": 69, "maintenance": 83, "payments": 40, "reliability": 41, "schema": 66, "security": 48, "transparency": 55 }, "provenanceScore": 89 }, "connect": { "install": "pip install google-genai # or: npm i @google/genai", "http": "curl -X POST \"https://generativelanguage.googleapis.com/v1beta/auth_tokens\" \\\n -H \"x-goog-api-key: $GEMINI_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"uses\": 1, \"liveConnectConstraints\": {\"model\": \"models/gemini-3.8-live\", \"config\": {\"sessionResumption\": {}, \"responseModalities\": [\"AUDIO\"]}}}'" }, "letme": { "capability": "https://letme.dev/voice.agent", "tool": "https://letme.dev/gemini-live" }, "sameCompany": [ "gemini-api", "gemini-embedding", "vertex-ai-tuning", "google-model-armor", "google-imagen", "google-veo", "google-lyria", "google-speech-to-text", "google-adk", "google-secret-manager", "google-weather-api", "chrome-devtools-mcp", "google-maps-platform", "google-cloud-translation", "google-calendar-api", "firebase-cloud-messaging", "google-drive-api", "gemini-cli", "google-search-console", "google-ads-api", "google-forms", "google-sheets-api", "gmail-api" ], "notable": [ "`gemini-3.8-live` and `gemini-3.8-live-extended-thinking` went generally available on 15 September 2026 (https://ai.google.dev/gemini-api/docs/changelog)", "`gemini-3.1-flash-live-preview` and `gemini-2.5-flash-native-audio-preview-12-2025` have an earliest shutdown date of 17 November 2026, with `gemini-3.8-live` named as the replacement (https://ai.google.dev/gemini-api/docs/deprecations)", "Billing compounds. Each turn is charged for all tokens in the session context window, audio accumulates at about 25 tokens a second, and transcription adds text output tokens (https://ai.google.dev/gemini-api/docs/live-api/best-practices)", "Proactive audio is permanently on in the 3.8 Live models, so input tokens are charged the whole time the API is listening (https://ai.google.dev/gemini-api/docs/live-api/best-practices)", "If a session resumption handle is generated, conversation state including audio and video is kept for up to 24 hours. Zero retention needs `SessionResumptionConfig` left unset (https://ai.google.dev/gemini-api/docs/zdr)", "Prompts, context and output are kept 55 days for abuse monitoring, and Google Search grounding stores them 30 days with no way to turn that off (https://ai.google.dev/gemini-api/docs/usage-policies, https://ai.google.dev/gemini-api/docs/zdr)", "Partner integrations listed for WebRTC and telephony are LiveKit, Pipecat, Fishjam, Vision Agents, Voximplant, Agora and Firebase AI Logic (https://ai.google.dev/gemini-api/docs/live-api)", "Google publishes a `gemini-live-api-dev` agent skill and a docs MCP server with `gemini_search_docs` and `gemini_get_doc` (https://ai.google.dev/gemini-api/docs/coding-agents)" ], "area": "voice", "details": [ { "label": "Architecture", "value": "Speech-to-speech. Native audio models take audio in and speak audio out over one stateful WebSocket, with optional text transcripts of both sides" }, { "label": "Endpoint", "value": "`wss://generativelanguage.googleapis.com/ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent`, and `BidiGenerateContentConstrained` for ephemeral tokens" }, { "label": "Models", "value": "`gemini-3.8-live` (stable, default), `gemini-3.8-live-extended-thinking`, `gemini-3.1-flash-live-preview` and `gemini-2.5-flash-native-audio-preview-12-2025` (both with an earliest shutdown of 17 November 2026). `gemini-3.5-live-translate-preview` and `gemini-3.5-transcribe-live` use the same API" }, { "label": "Audio", "value": "Input raw 16-bit PCM at 16 kHz, images as JPEG at up to 1 frame a second, and text. Output raw 16-bit PCM at 24 kHz. Audio is the only response modality on native audio models" }, { "label": "Languages", "value": "The overview page says 70 and the capabilities guide lists 99. The model detects the spoken language without a language code" }, { "label": "Latency", "value": "No figure published in the docs read. Google describes the API as low latency" }, { "label": "Interruptions", "value": "Automatic voice activity detection by default, with start and end sensitivity, prefix padding and silence duration settings. Hybrid and manual modes. The server sends `interrupted: true` when the user barges in" }, { "label": "Tool calling", "value": "Function declarations and Google Search grounding. Non-blocking calls by default on `gemini-3.8-live`, with `SILENT`, `WHEN_IDLE` and `INTERRUPT` scheduling. No code execution, URL context or Google Maps. The client must send tool responses itself" }, { "label": "Telephony", "value": "None built in. Partner integrations such as Voximplant, LiveKit, Pipecat and Agora connect calls" }, { "label": "Session limits", "value": "Audio sessions 15 minutes and audio with video 2 minutes without context compression. A connection lasts about 10 minutes. Resumption handles are valid 2 hours. Context window 128k tokens on native audio models" }, { "label": "Credentials", "value": "API key from AI Studio, an authorisation key bound to a service account by default since 28 May 2026. Ephemeral tokens (preview) from `POST /v1beta/auth_tokens` with `uses`, `expireTime`, `newSessionExpireTime` and `liveConnectConstraints`" }, { "label": "Free tier", "value": "Live models are free of charge on the free tier, where content is used to improve Google products. Limits are shown in AI Studio" }, { "label": "Rate limits", "value": "Per project and usage tier, shown in AI Studio. Public figures are the spend limits of $10, $50 and $200 per 10 minutes on Tiers 1 to 3. No concurrent session figure in the public docs" }, { "label": "Data retention", "value": "55 days for abuse monitoring. Up to 24 hours of session state when resumption is on. 30 days for Google Search grounding. Paid-tier content isn't used to improve Google products" }, { "label": "SDKs", "value": "`google-genai` v2.29.0 for Python and `@google/genai` v2.28.0 for JavaScript, both tagged 7 October 2026, Apache-2.0" } ], "unitPrices": [ { "item": "gemini-3.8-live audio input", "unit": "audio-minute", "usd": 0.005, "note": "$3.00 per 1M audio tokens, charged while the API is listening" }, { "item": "gemini-3.8-live audio output", "unit": "audio-minute", "usd": 0.018, "note": "$12.00 per 1M audio tokens" }, { "item": "gemini-3.8-live text input", "unit": "1m-tokens", "usd": 0.75 }, { "item": "gemini-3.8-live text output", "unit": "1m-tokens", "usd": 4.5, "note": "includes thinking tokens and transcription text" }, { "item": "Google Search grounding", "unit": "1k-requests", "usd": 14, "note": "after 5,000 free search queries a month shared across Gemini 3.x models" } ], "provenance": { "legalEntity": "Google LLC", "domain": "google.com", "domainRegistered": "1997-09-15", "endpointOnVendorDomain": true, "terms": "https://ai.google.dev/gemini-api/terms", "privacy": "https://policies.google.com/privacy", "statusPage": "https://aistudio.google.com/status", "changelog": "https://ai.google.dev/gemini-api/docs/changelog", "securityTxt": "valid", "checked": "2026-10-08", "notes": [ "The WebSocket and the token endpoint are on generativelanguage.googleapis.com, Google's API domain. The docs are on ai.google.dev.", "RDAP for google.com gives a registration date of 1997-09-15.", "The Gemini API Additional Terms of Service are effective 23 March 2026 and incorporate the Google APIs Terms of Service. Paid services fall under Google's Data Processing Addendum for products where Google is a data processor.", "The Google Privacy Policy read on 8 October 2026 is effective 1 October 2026. It is Google's general policy, and the terms page is where API data use is set out.", "www.google.com/.well-known/security.txt expires 2030-04-01 and points to g.co/vulnz and the vulnerability reward programme. ai.google.dev has no security.txt of its own (404).", "aistudio.google.com/status answered 200 with a page drawn by script, so no component or incident history was read." ], "score": 89, "checks": [ { "check": "Legal entity named", "value": "Google LLC", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "google.com, registered 1997-09-15 (29 years)", "points": 15, "max": 15, "state": "ok" }, { "check": "Endpoint on the vendor's domain", "value": "generativelanguage.googleapis.com", "points": 15, "max": 15, "state": "ok" }, { "check": "Terms of service", "value": "read, states 4 of the 7 things a reader expects, and has 3 clauses that cost points", "points": 1.4, "max": 10, "state": "part" }, { "check": "Privacy policy", "value": "read, states 7 of the 8 things a reader expects, and has 1 clause that costs points", "points": 7.3, "max": 10, "state": "part" }, { "check": "Status page", "value": "aistudio.google.com/status", "points": 10, "max": 10, "state": "ok" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "valid", "points": 10, "max": 10, "state": "ok" } ], "policies": [ { "kind": "terms", "url": "https://ai.google.dev/gemini-api/terms", "state": "read", "readAt": "2026-10-08", "statedDate": "2026-04-28", "words": 3632, "points": 1.4, "max": 10, "expected": [ { "key": "terms.date", "label": "Gives the date it was last updated", "found": true, "quote": "Last updated 2026-04-28 UTC.", "says": "Last updated 2026-04-28" }, { "key": "terms.law", "label": "Names the governing law or courts", "found": true, "quote": "the Pricing and Billing Terms of the Service Specific Terms at https://cloud.google.com/terms/service-terms, including the Supplemental Paid Credit Terms at https://cloud.google.com/terms/supplemental-paid-credit (the \"Supplemental Paid Credit Terms\")." }, { "key": "terms.liability", "label": "States a limit on its liability", "found": false }, { "key": "terms.termination", "label": "Says how the agreement or account can be ended", "found": true, "quote": "This subsection \"Grounding with Google Search\" will survive termination of the Agreement, as applicable." }, { "key": "terms.changes", "label": "Says how changes to the terms are announced", "found": false }, { "key": "terms.use", "label": "Lists what users may not do", "found": true, "quote": "You may not use the Services to develop models that compete with the Services (e.g., Gemini API or Google AI Studio)." }, { "key": "terms.sla", "label": "Refers to a service level or uptime commitment", "found": false } ], "toKnow": [ { "key": "training", "label": "Says it may use customer content to train or improve models, and no opt-out was found", "found": true, "quote": "When you use Unpaid Services, including, for example, Google AI Studio and the unpaid quota on Gemini API, Google uses the content you submit to the Services and any generated responses to provide, improve, and develop Google products and services and machine learning technologies, including Google's enterprise featur…", "costsPoints": true }, { "key": "terms.automated", "label": "Restricts automated access", "found": true, "quote": "scrape or export any Google Maps Data;", "costsPoints": true }, { "key": "terms.benchmark", "label": "Restricts benchmarking or competitive use", "found": true, "quote": "You may not use the Services to develop models that compete with the Services (e.g., Gemini API or Google AI Studio).", "costsPoints": true } ], "notes": [ { "date": "2026-10-08", "text": "The agentic services section, which names the Computer Use API, says the customer will not automatically bypass any requests for human confirmation.", "quote": "You will not automatically bypass any requests for human confirmation." }, { "date": "2026-10-08", "text": "On the unpaid services, human reviewers may read, annotate and process API input and output.", "quote": "To help with quality and improve our products, human reviewers may read, annotate, and process your API input and output." }, { "date": "2026-10-08", "text": "Customers may not cache, analyse, train on or otherwise learn from Grounded Results or Search Suggestions returned by Grounding with Google Search.", "quote": "You will not, and will not allow your end user or any third party to, cache, frame, syndicate, resell, analyze, train on, or otherwise learn from Grounded Results or Search Suggestions." } ] }, { "kind": "privacy", "url": "https://policies.google.com/privacy", "state": "read", "readAt": "2026-10-08", "statedDate": "2026-10-01", "words": 14332, "points": 7.3, "max": 10, "expected": [ { "key": "privacy.date", "label": "Gives the date it was last updated", "found": true, "quote": "Effective October 1, 2026 | Archived versions | Download PDF", "says": "Last updated 2026-10-01" }, { "key": "privacy.collected", "label": "Says what personal data is collected", "found": true, "quote": "This Privacy Policy is meant to help you understand what information we collect, why we collect it, and how you can update, manage, export, and delete your information." }, { "key": "privacy.retention", "label": "Says how long data is kept", "found": true, "quote": "The types of location data we collect and how long we store it depend in part on your device and account settings." }, { "key": "privacy.processors", "label": "Says who else receives the data", "found": true, "quote": "For example, we use service providers to help operate our data centers, deliver our products and services, improve our internal business processes, and offer additional support to customers and users." }, { "key": "privacy.sale", "label": "Says whether personal data is sold or shared for advertising", "found": true, "quote": "If Google is involved in a merger, acquisition, or sale of assets, we’ll continue to ensure the confidentiality of your personal information and give affected users notice before personal information is transferred or becomes subject to a different privacy policy." }, { "key": "privacy.rights", "label": "Says what rights people have over their data", "found": true, "quote": "If European Union or United Kingdom data protection law applies to the processing of your information, you can review the European requirements section below to learn more about your rights and Google’s compliance with these laws." }, { "key": "privacy.contact", "label": "Gives a privacy contact", "found": true, "quote": "And if you have any questions about this Privacy Policy, you can contact us." }, { "key": "privacy.transfers", "label": "Says where data is transferred or stored", "found": false } ], "toKnow": [ { "key": "training", "label": "Says it may use customer content to train or improve models, and no opt-out was found", "found": true, "quote": "We use your interactions with AI models and technologies like Gemini Apps to develop, train, fine-tune, and improve these models to better handle your requests, and update their classifiers and filters including for safety, language understanding, and factuality.", "costsPoints": true } ], "notes": [ { "date": "2026-10-08", "text": "Members of organisations using Google Workspace or Google Cloud Platform are referred to the separate Google Cloud Privacy Notice for how those services collect and use personal information.", "quote": "If you’re a member of an organization that uses Google Workspace or Google Cloud Platform, learn how these services collect and use your personal information in the Google Cloud Privacy Notice." }, { "date": "2026-10-08", "text": "Google says it uses publicly available information from the web and other public sources to help train machine learning models behind products such as Google Translate, Gemini Apps and Cloud AI.", "quote": "We use publicly available information online or from other public sources to help train new machine learning models and build foundational technologies that power various Google products such as Google Translate, Gemini Apps, and Cloud AI capabilities." } ] } ] }, "pageJsonUrl": "https://www.anchorterminal.com/tools/gemini-live.json", "live": { "slug": "gemini-live", "probe": { "target": "https://generativelanguage.googleapis.com/v1beta", "method": "get", "lastAt": "2026-10-09T10:14:15.574275828Z", "lastOk": true, "lastStatus": 404, "lastMs": 14, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 17, "p95ms24h": 45, "samples24h": 28, "samples30d": 28, "days": [ { "date": "2026-10-09", "probes": 28, "ok": 28 } ] }, "updatedAt": "2026-10-09T10:14:15.574275828Z" } } }