Amazon Nova 2 Sonic vs OpenAI Realtime API

Amazon Nova 2 Sonic 95

Hosted reading. AWS Health Dashboard with per-service, per-Region history (20). The dashboard history file (newest event 30 October 2026) lists no Bedrock event in the 90 days from 8 August, and the 3 September us-west-2 event names STS, Connect and IAM Identity Center, not Bedrock. The public dashboard records broad events only, so 25 of 30, as amazon-nova-embeddings was read. Quotas published, 20 concurrent requests per Region, not adjustable (15). The stream API lists ThrottlingException (429), ServiceUnavailableException (503), ModelTimeoutException (408) and ModelStreamErrorException (424), Bedrock's troubleshooting guide advises backoff with jitter, and the 8-minute connection limit comes with a session-continuation sample (15). Bedrock's SLA of 99.9 per cent a month per Region for model APIs, as read for amazon-nova-embeddings on 1 November (10). Generally available since 2 December 2025 (10). 20 + 25 + 15 + 15 + 10 + 10 = 95.

OpenAI Realtime API 62

Graded as a hosted API. status.openai.com (incident.io) lists Realtime as a component of the API group with history (20). The feed, read on 2 November (102 items, 4 August to 30 October), names Realtime in three incidents in the 90 days from 4 August, and each incident page gives the component's impact. Elevated error rates across API models on 17 September, with Realtime degraded from 20:20 to 21:20 UTC alongside ten other API components, and elevated errors across ChatGPT, Codex and the API on 29 September, with Realtime degraded from 17:52 to 23:14 UTC, are each an hour or more of wide errors, so two majors. Degraded performance across ChatGPT, Codex and the APIs on 21 October listed Realtime for 22 minutes (02:26 to 02:48 UTC), so minor. The 11 August incident on the API, Codex and Work Mode lists no components and isn't counted, as on the other OpenAI listings, and the July incidents the 9 October check counted have left the window. Two majors give 5, as the OpenAI API, Moderation, Embeddings and Speech-to-text listings read the same two incidents (5 of 30, was 20 when the durations were unread). The gpt-realtime-2.1 model page, read on 2 November, gives 400 requests and 200,000 tokens a minute on Build, 10,000 and 4 million on Launch and 20,000 and 15 million on Grow (15, was 5 when the limits were known only from account settings). The docs describe Retry-After on 429 and 503, exponential backoff with jitter and SDK retries, sessions emit rate_limits.updated, and SIP webhooks carry a webhook-id for deduplication, per the 9 October check. No idempotency key for call control was found, so safe-retry guidance without keys (12 of 15). No SLA covering Realtime was found, read as on the other OpenAI listings, where the Scale Tier SLA names GPT and o-series models (0). Generally available since 28 August 2025 (10). 20 + 5 + 15 + 12 + 0 + 10 = 62.

Amazon Nova 2 Sonic 50

Read as a model. The newest dated change is the May 2026 refresh, completed on 28 May, 162 days before this check (10). No Sonic release note or document history entry in the 90 days from 8 August. The pre-alpha Python SDK shipped 0.9.0, 0.10.0, 0.11.0 and 0.12.0 in the window, counted half (10 of 20). Release notes, document history, re:Post and AWS Support (10 of 15). The JavaScript Bedrock runtime client is current at 3.1163.0, while the Python route is pre-alpha (10 of 15). The SDKs ship on AWS's release train; CI not read (10). Total 50.

OpenAI Realtime API 82

The last dated changelog entry tagged v1/realtime is the 26 August 2026 deprecation of whisper-1, gpt-4o-transcribe and two related models, which Realtime sessions can use for input transcripts, after gpt-transcribe for committed Realtime turns on 28 July. The listing's own package, @openai/agents-realtime, released 0.21.0 on 20 October 2026, 13 days before the check, with Realtime fixes (WebRTC connections rejected when the server reports an error before the session is configured, Twilio audio defaults kept), read from a clone. A release that changes the product's own package sets the recency line in this run (30, was 20 when SDK releases weren't read on this line). In the 90 days from 4 August the changelog has one v1/realtime entry and the SDK has 11 version tags, 0.14.3 on 5 August to 0.21.0, at least seven of which change the Realtime package's source. SDK tags count half, so 1 + 3.5 clears three (20, was 0). Closed service with a changelog updated several times a week, plus a community forum and Discord linked from the docs, which we did not test (10 of 15). Current official SDKs, @openai/agents and @openai/agents-realtime 0.21.0 (15). The SDK is MIT but still 0.x, and its CI results were not read (7 of 10). 30 + 20 + 10 + 15 + 7 = 82.

Amazon Nova 2 Sonic 10

No x402, MPP or L402 (0). The Nova and Bedrock pricing pages carry a speech-to-speech table drawn by script, so the per-token prices weren't read and this line scores absent, which is our reader's limit and not the vendor's (0). New accounts get up to $200 in Free Tier credits, and the Free Tier FAQ says most new customers need no payment method, read as half on the other AWS listings (10). A person signs up for an AWS account in a browser (0). Total 10.

OpenAI Realtime API 30

No x402, MPP or L402 on the pricing page, re-read on 2 November, or in the OpenAPI file (0 of 40). Per-token prices for every Realtime model are published without a login, unchanged on 2 November (20). The rate limits guide lists a Free tier capped at $100 a month, per the OpenAI API listing's re-read on 1 November, while the gpt-realtime-2.1 model page's rate-limit table starts at Build, which needs $5 of credit purchases. Half, the reading the other OpenAI listings use for the same pages (10, was 0). API keys are created in the platform settings after a browser sign-in (0). 0 + 20 + 10 + 0 = 30.

Amazon Nova 2 Sonic 64

Scored as an API. Responses carry transcripts of both sides and usage events, chat history is capped at 200 KB and can be injected once per session (15 of 25). Output controls are voice, turn-taking sensitivity and text or audio input (12 of 20). Typed exceptions with HTTP codes, while errors inside the event stream are less documented (15 of 20). Asynchronous tool calls let the model keep talking, and AWS samples show how to resume after the 8-minute limit, with nothing on repeating tool side effects after a reconnect (12 of 20). A session needs a sequence of start events before audio. The JavaScript SDK is current, but the Python SDK the quickstart uses is pre-alpha and needs Python 3.12 (10 of 15). Total 64.

OpenAI Realtime API 76

Read on the API lines, per the 9 October check of the guides, not re-read on 2 November. Context can be capped with truncation, retention_ratio and token_limits.post_instructions, items can be deleted, prompt caching is automatic, and response.done reports token usage by modality (22 of 25). There are no lists to page. Output controls are output_modalities, max_output_tokens, optional input transcription and allowed_tools (14 of 20). The error event returns the event_id of the client event that caused it, and MCP tool listing and calls have their own failure events (15 of 20). Client events take an event_id, webhooks carry a webhook-id, and interruptions cancel the response. No session resumption after a dropped connection and no idempotency key for call control were found (10 of 20). A session needs only a model, voice activity detection is automatic, and the Agents SDK starts a browser voice agent in about ten lines, with examples in five languages (15). 22 + 14 + 15 + 10 + 15 = 76.

Amazon Nova 2 Sonic 79

Closed model under the AWS Service Terms, with Apache-2.0 SDKs and samples (15). Bedrock stores no inputs or outputs by default and model providers can't see them, Sonic isn't on the abuse-detection page's list of models whose traffic is stored, and section 50.3 doesn't list Bedrock among services whose content improves AWS services, as read for amazon-nova-embeddings on 1 November (22 of 30). Bedrock's lifecycle policy for models launched before 7 September 2026 promises 12 months and a Legacy period of at least 6 months, but the March and May refreshes changed the model in place under the same ID (15 of 20). Regions are listed, with sub-processors not read (12 of 20). Total 64.

OpenAI Realtime API 90

Closed service with clear terms, per the OpenAI API listing's check of the services agreement, which answered 403 to our reader again on 2 November. The Agents SDK for TypeScript and the OpenAPI file are MIT (15, was 10). The data controls page, re-read on 2 November, lists /v1/realtime with no training use, abuse monitoring logs kept up to 30 days, no stored application state and Zero Data Retention eligibility. The DPA, effective 1 January 2026, commits to return or deletion of customer data on termination, 30 days to object to a new subprocessor, and SCCs with the UK Addendum, and nothing in it conflicts with the guide, per the OpenAI API listing's 4 October check, not re-read on 2 November. The same reading as the other OpenAI listings (30, was 18). The deprecations page, re-read on 2 November, states at least six months' notice for generally available models and lists shutdown dates with replacements, including gpt-realtime and gpt-realtime-mini on 20 January 2027 (20). The guide documents residency for /v1/realtime in the United States and Europe for storage and processing, with a sip-eu.api.openai.com endpoint, and says tracing on /v1/realtime isn't EU residency compliant. The subprocessor list, updated 9 July 2026, names third-party subprocessors and OpenAI affiliates with processing countries for each and a form for notice of new ones, per the OpenAI API listing's 4 October check, not re-read on 2 November. The guide states the residency limit, which counts as disclosure, so the same reading as the other OpenAI listings (20, was 10). 15 + 30 + 20 + 20 = 85.

Amazon Nova 2 Sonic 75

The Bedrock service model types InvokeModelWithBidirectionalStream, but the Sonic events inside it (session, prompt, content, tool and usage events) are JSON payloads documented only in the guide, with no schema file (12 of 25). llms.txt and Markdown copies of the Nova 2 guide (10). Guides on the event lifecycle, barge-in, turn-taking, async tools and chat history say when and how to use each (16 of 20). Event fields are documented as JSON examples and tables, not typed schemas (10 of 15). Sample repositories in several languages and the API's exceptions with HTTP codes (12 of 15). Release notes and document history, with in-place model refreshes and a versioned model ID (15). Total 75.

OpenAI Realtime API 84

The OpenAPI 3.1 file in openai/openai-openapi (version 2.3.0, last committed 31 October 2026, read from a clone on 2 November) has nine /realtime paths and 185 Realtime schemas, with 11 client events and 46 server events in its main event unions and separate translation session events. It is not an AsyncAPI document, so the WebSocket channel itself is not described (22 of 25). llms.txt and a Markdown twin of every docs page, re-read on 2 November (10). The tools guide has a table of when to use function, mcp with server_url or a connector, and the transport guides say when to choose WebRTC, WebSocket or SIP, per the 9 October check (16 of 20). Session fields carry enums and ranges, such as expires_after.seconds from 10 to 7200, though model also accepts any string (13 of 15). Examples in JavaScript, Python, Java, Ruby and C#, an error event with type, code, message and param, and a list of common MCP failures. No catalogue of Realtime error codes was found (11 of 15). Dated changelog and dated snapshots for the older models (gpt-realtime-2.1 lists only its alias), less 3 because the OpenAPI file still names gpt-4o-realtime-preview models (12 mentions on 2 November) that the deprecations page says were removed on 7 May 2026, and several guides mix GPT-Live and Realtime text on one page (12 of 15). 22 + 10 + 16 + 13 + 11 + 12 = 84.