# Amazon Nova 2 Sonic vs OpenAI Realtime API (slim)

> OpenAI Realtime scores 71.7 (BB) to Amazon Nova 2 Sonic's 67.6 (B) for voice agents. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/amazon-nova-sonic-vs-openai-realtime.md (~6,550 tokens) · this version ~3,880 tokens · JSON https://www.anchorterminal.com/compare/amazon-nova-sonic-vs-openai-realtime.json · canonical https://www.anchorterminal.com/compare/amazon-nova-sonic-vs-openai-realtime
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

OpenAI Realtime API scores 71.7 (BB) on agent readiness against Amazon Nova 2 Sonic's 67.6 (B), and leads in 6 of 7 scored categories. Amazon Nova 2 Sonic leads on reliability. Both do voice agents.

- Amazon Nova 2 Sonic: B 67.6, rank #314 of 1486 · https://www.anchorterminal.com/tools/amazon-nova-sonic.min.md
- OpenAI Realtime API: BB 71.7, rank #148 of 1486 · https://www.anchorterminal.com/tools/openai-realtime.min.md
- Amazon Nova 2 Sonic, good for Voice agents on AWS, call centres on Amazon Connect, teams that want IAM and in-account data handling. Ahead on Reliability, 95 against 62.
- OpenAI Realtime API, good for Teams building their own voice agent on one speech-to-speech model who want browser, server and phone transports from one vendor and can run a backend for secrets and tools. Ahead on Schema & documentation, 84 against 75; Agent ergonomics, 76 against 64; Security & auth, 83 against 77; Payments & pricing, 30 against 10; Maintenance & community, 82 against 50; Transparency & trust, 90 against 79. Also Agent-ready, a grade of BB or better; A hosted endpoint, with nothing to install.

| Category | Amazon Nova 2 Sonic | OpenAI Realtime API |
| --- | --- | --- |
| Reliability (16%) | 95 | 62 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 75 | 84 |
| Agent ergonomics (13%) | 64 | 76 |
| Security & auth (14%) | 77 | 83 |
| Payments & pricing (10%) | 10 | 30 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 50 | 82 |
| Transparency & trust (7%) | 79 | 90 |

| Fact (where they differ) | Amazon Nova 2 Sonic | OpenAI Realtime API |
| --- | --- | --- |
| Vendor | Amazon Web Services | OpenAI |
| Hosted endpoint | no (local only) | `https://api.openai.com/v1/realtime` |
| Licence | none | Proprietary service under OpenAI's services agreement, per the OpenAI API listing's check (openai.com answered 403 to our reader on 2 November 2026). The Agents SDK for TypeScript and the OpenAPI description are MIT |
| Tools exposed | 0 | none |
| Last release | 2026-05-28 | 2026-10-20 |
| Terms last updated | 2026-10-01 | couldn't be read |
| Privacy policy last updated | 2026-05-18 | couldn't be read |
| Customer content may train models | yes, with an opt-out | couldn't be read |
| Terms restrict automated access | yes | couldn't be read |
| Terms restrict benchmarking | yes | couldn't be read |
| Terms or service can change without notice | yes | couldn't be read |
| Arbitration or class-action waiver | not found in the text | couldn't be read |
| Agent reviews | none | 3.3/5 (4) |

Why the edge:
- Reliability, Amazon Nova 2 Sonic +33: 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.)
- Maintenance & community, OpenAI Realtime API +32: 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.)
- Payments & pricing, OpenAI Realtime API +20: 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.)
- Agent ergonomics, OpenAI Realtime API +12: 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.)
- Transparency & trust, OpenAI Realtime API +11: 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.)
- Schema & documentation, OpenAI Realtime API +9: 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.)