# Bria API > Bria's API generates and edits images with its FIBO models, trained on licensed data. It runs as an asynchronous REST API with Python and TypeScript SDKs and an MCP server. - Canonical: https://www.anchorterminal.com/tools/bria - Markdown: https://www.anchorterminal.com/tools/bria.md (~6,900 tokens) - Slim: https://www.anchorterminal.com/tools/bria.min.md (~1,730 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/bria.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - Updated: 2026-10-08 ## Overview **Grade B · 63.7/100 · rank #298 of 722 · #4 in Image generation · not agent-ready · confidence medium** ## Assessment Per-image prices, 100 free calls without a card, OpenAPI files and Markdown docs make a first call quick, and the terms warrant that customer content is not used for training. Keys are organisation-wide with no scopes, and the API has no changelog or deprecation policy. ## Facts | Field | Value | | --- | --- | | Vendor | Bria AI (https://bria.ai) | | Kind | Model API | | Category | Image generation (https://www.anchorterminal.com/categories/image-generation) | | Transport | HTTP, Streamable HTTP, stdio | | Endpoint | `https://engine.prod.bria-api.com/v2` | | Auth | OAuth or key · Self-serve organisation API key from the Bria Console, sent in the `api_token` header. An organisation can hold several named keys and revoke each one. No scopes. The hosted MCP server also accepts an OAuth 2.1 bearer token (PKCE, dynamic client registration, device flow) tied to a Bria account. The streaming WebSocket takes `api_token` or `oauth` as a query parameter (https://docs.bria.ai/getting-started/authentication.md). | | Pricing | Freemium ($0.02 / call) · Free plan with 100 calls, no card, at 10 requests a minute. Pay-as-you-go is billed per image, call or second of video, from $0.018 (background removal) to $0.03 (FIBO generation, FIBO Edit) an image, at 60 requests a minute. Enterprise is priced by sales and adds unlimited IP indemnification, SSO, audit logs and self-hosting (https://bria.ai/pricing). | | x402 | No · No x402, MPP or L402 in the API docs, the OpenAPI files or the pricing page (checked 2026-10-08). | | Licence | unknown | | Tools exposed | 18 | | Packages | pypi: `bria-client`; npm: `@bria-ai/client`; pypi: `bria-mcp` | | Source | https://github.com/Bria-AI/bria-client | | Docs | https://docs.bria.ai/ | | llms.txt | https://docs.bria.ai/llms.txt | | Last release | 2026-10-04 | | npm downloads / week | 341 | | PyPI downloads / week | 3,909 | | Models | Own models. FIBO (default) and FIBO Lite for generation, FIBO Edit for instruction editing, RMBG 2.0 for background removal | | Max resolution | `resolution` is 1MP or 4MP on `/v2/image/generate`. 4MP is asynchronous only and adds about 30 seconds, per the docs. Nine aspect ratios from 9:16 to 16:9. Output PNG or JPEG | | Edit support | Instruction editing with 1 to 4 images and an optional mask, erase, generative fill, expand, background removal, replacement and blur, relight, restyle, colourise, restore, enhance, increase resolution, product shots and virtual try-on | | Output licence | Bria assigns its rights in output to the customer. Output may not be used to train generative models or placed in a public image bank (Online Terms and Conditions, sections 2.1 and 2.3) | | Content policy | Models trained without public figures, fictional characters or NSFW content, per Bria. Moderation of prompts and images is opt-in per request and returns 422. `ip_signal` adds a warning for prompts naming protected content | | Provenance | C2PA manifest and an invisible watermark on output. Public verification endpoints `POST /v2/image/verify` and `POST /v2/video/verify` need no token | | Open weights | FIBO, FIBO Edit, FIBO Lite and RMBG 2.0 on Hugging Face, source-available for non-commercial use | | Free tier | 100 free calls, no card, every endpoint, 10 requests a minute | | Rate limits | Per organisation and per endpoint. Free 10 requests a minute, Pay-as-you-go 60, Enterprise 1,000 and customisable. Status polls count | | Result storage | Image URLs expire after 3 days by default, video does not expire, Ad Delayer results 30 days, legacy `/v1/product/*` results 1 hour. Inputs are not retained beyond processing, per the docs | | MCP server | Hosted at https://mcp.prod.bria-api.com/mcp (Streamable HTTP, `api_token` header or OAuth 2.1 with PKCE and dynamic client registration) or local with `uvx bria-mcp`. 18 tools in `bria-mcp` 2.2.1 | | Capabilities | image.generate, image.edit, image.upscale, image.reference | | Tags | hosted, closed-source, mcp, oauth, openapi, llms-txt, python, typescript, async-jobs, webhooks, open-weights, c2pa, watermark, commercial-licence, status-page | | JSON | https://www.anchorterminal.com/api/v1/tools/bria.json | ## Score breakdown (methodology v0.4, October 2026 research run) Assessed 2026-10-08 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Reliability | 16% | 20 | 83 | 16.6 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 84 | 13.7 | | Agent ergonomics | 13% | 16.2 | 76 | 12.3 | | Security & auth | 14% | 17.5 | 33 | 5.8 | | Payments & pricing | 10% | 12.5 | 40 | 5.0 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 69 | 6.0 | | Transparency & trust (editorial 42, provenance 56) | 7% | 8.8 | 49 | 4.3 | | Negative events | up to −15 | up to −15 | none recorded | 0 | | **Total** | | | | **63.7 → B** | ### Why each score - Reliability 83: Read with the hosted lines. Atlassian Statuspage at status.bria.ai with API components and history (20). One incident between 10 July and 8 October 2026, an API outage for image editing, increase resolution and image generation on 22 September, labelled major and resolved in 18 minutes with no cause given. Under an hour, so minor by our line (20). Limits published per plan, 10, 60 and 1,000 requests a minute per endpoint (15). The docs tell callers to back off with jitter and honour `Retry-After` on 429, and the SDKs retry status polls only so a job is not started twice. No idempotency key (13). The site states a 99.9 per cent uptime SLA for managed cloud, but no SLA document was found and the online terms supply the products as is, so half credit (5). The REST API is generally available (10). - Performance: 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. - Schema & documentation 84: A downloadable OpenAPI 3.0 file for each API, such as `/_bundle/image-generation.yaml` (25). `llms.txt`, a Markdown twin of every page and a docs MCP server at docs.bria.ai/mcp (10). Endpoint pages state the purpose and the valid input combinations, and the MCP tool descriptions say when to use `edit_image` in place of `text_to_image` (17). Enums for resolution, aspect ratio and output type, but `structured_prompt` is a JSON document passed as a string (12). Request and response examples, an error table and typed error bodies per endpoint, with `error.code` shown only as a placeholder (13). Paths are versioned v1 and v2, but the OpenAPI files have an empty version and no API changelog was found (7). - Agent ergonomics 76: Results come back as URLs, with a `seed` and the full structured prompt. The MCP server has 18 tools and returns a JPEG preview of up to 0.7 MB inline (18). Resolution, aspect ratio, output type and a sync or async choice, with nothing to paginate (15). One error shape with `request_id`, a status table and messages the MCP server passes through as `Bria API error : ` (18). No idempotency key. Webhooks carry `Bria-Webhook-Id` for deduplication. The MCP tools carry annotations, but all 18 are marked read-only and idempotent although each call is billed (10). Only a prompt is required, and there are official Python and TypeScript SDKs (15). - Security & auth 33: Several named, revocable organisation keys with no scopes, plus OAuth 2.1 with PKCE on the hosted MCP server, where the scopes are identity only (20). Less 10 because the streaming background removal WebSocket takes `api_token` as a URL query parameter (10 net). No read-only or restricted key and no spend cap found in the reviewed documentation (0). Returns generated images and a structured prompt built from the caller's own input (10). Each response has a `request_id`. Audit logs are listed for Enterprise only (5). The site states ISO 27001 certification and SOC 2 attestation with no report, auditor or trust centre linked. No `security.txt`, disclosure policy or bug bounty found (8). The no-training warranty is counted under Transparency. - Payments & pricing 40: No x402, MPP or L402 (0). Per-image, per-call and per-second prices published without a login (20). 100 free calls with no card (20). A person has to sign up in the console to get a key. The MCP OAuth flow has dynamic client registration but still needs a Bria account sign-in (0). - Task success: 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. - Maintenance & community 69: `bria-mcp` 2.2.1 on 4 October 2026, four days before the check (30). For models we look at churn and notice. FIBO, FIBO Lite and the v1 product endpoints are all still served and one v1 endpoint is marked deprecated with its v2 replacement named, but no notice policy or dated notice was found (10). No API changelog. Support is by email and a Discord community, not tested, and the GitHub API refused us so SDK issues were not read (6). Current official SDKs, `bria-client` 0.3.0 on PyPI (24 June 2026) and `@bria-ai/client` 0.2.0 on npm (28 September 2026). The MCP server is not in the official MCP registry (15). The SDK repository has CI, release automation and a lock file. The SDKs are 0.x and `bria-mcp` is classified beta (8). - Transparency & trust 49: Closed hosted API under the Online AI General Terms and Conditions of March 2025, a PDF linked from the website terms. SDKs and the MCP server are MIT. Model weights are source-available for non-commercial use (15). The terms warrant no training on customer content without written consent and deletion within 30 days of termination. The docs give 3 days for image results and say inputs are not kept beyond processing. The privacy policy has no date and no retention periods, and does not name Google, whose Gemini 2.5 Flash handles prompts on the standard generate endpoint (20). No deprecation policy. One endpoint is marked deprecated without a date (3). The privacy policy lists recipient categories only, with vendor names on request by email. Data locations not stated (4). Fix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (21 items): https://www.anchorterminal.com/fixes/bria.md (JSON https://www.anchorterminal.com/fixes/bria.json) ### What we couldn't check - The lead was right on the interface (REST API, Python and TypeScript SDKs, official MCP server). The TypeScript SDK was first published on 28 September 2026. - unchecked: GitHub stars and open issues for Bria-AI/bria-client. The GitHub API answered with a rate limit, so `githubStars` is empty and responsiveness is scored without the issue tracker. - unchecked: which terms the console presents at sign-up. The Online AI General Terms and Conditions are linked from the website terms for demo tools and define APIs as Online Services, so we treat them as governing. - unchecked: the hosted MCP server's live tool list and annotations. The count of 18 and the annotations come from the `bria-mcp` 2.2.1 source, and the docs say the hosted server exposes the same capabilities. - The pricing page lists video background removal at $0.0225 a second and bria.ai/llms.txt at $0.01. We used the pricing page. - No SLA document was found behind the 99.9 per cent uptime statement. - No effective date on the privacy policy, and no API launch date found, so `firstReleased` is empty. - Whether failed or moderated requests are billed is not stated in the reviewed pages. ### Sources - docs index for agents (base URL, auth, limits, integrations): (seen 2026-10-08) - authentication: (seen 2026-10-08) - rate limits and errors: (seen 2026-10-08) - async requests and webhooks: (seen 2026-10-08) - asset retention: (seen 2026-10-08) - MCP server (tools, hosted and local, OAuth): (seen 2026-10-08) - generate endpoint reference: (seen 2026-10-08) - OpenAPI file, image generation: (seen 2026-10-08) - OpenAPI file, image editing: (seen 2026-10-08) - safety and moderation: (seen 2026-10-08) - deployment options and weights licence: (seen 2026-10-08) - pricing: (seen 2026-10-08) - status incidents feed: (seen 2026-10-08) - website terms of use: (seen 2026-10-08) - Online AI General Terms and Conditions (March 2025, V1.1): (seen 2026-10-08) - privacy policy: (seen 2026-10-08) - security and compliance page: (seen 2026-10-08) - 99.9 per cent uptime SLA statement: (seen 2026-10-08) - bria-mcp on PyPI (releases, source of 2.2.1 for tool annotations): (seen 2026-10-08) - bria-client on PyPI: (seen 2026-10-08) - @bria-ai/client on npm: (seen 2026-10-08) - SDK repository (clone, CI workflows, changelogs): (seen 2026-10-08) - MCP OAuth metadata: (seen 2026-10-08) - official MCP registry search for bria (no Bria entry): (seen 2026-10-08) - RDAP for bria.ai: (seen 2026-10-08) - FIBO model on Hugging Face (licence field): (seen 2026-10-08) ## Who's behind it (provenance 56/100, checked 2026-10-08) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | Bria Artificial Intelligence Ltd. | 20/20 | | Domain age | bria.ai, registered 2020-04-03 (6 years) | 11/15 | | Endpoint on the vendor's domain | engine.prod.bria-api.com is not on bria.ai | 0/15 | | Terms of service | published, but our reader couldn't read it | 7/10 | | Privacy policy | read, states 6 of the 8 things a reader expects | 8.5/10 | | Status page | status.bria.ai | 10/10 | | Changelog | not found | 0/10 | | security.txt | not found | 0/10 | The API answers at engine.prod.bria-api.com and the hosted MCP server at mcp.prod.bria-api.com, a different domain from bria.ai. Bria's own docs name both hosts. The terms link is the Bria Online AI General Terms and Conditions (March 2025, V1.1), a PDF on Google Drive linked from https://bria.ai/terms-of-use. It defines Online Services to include the APIs and an Order to include confirming a subscription plan on Bria's website. We could not see which terms the console shows at sign-up. https://bria.ai/terms-of-use is a website terms page that grants personal, non-commercial access and is not used as the terms link. The privacy policy names Bria Artificial Intelligence Ltd. and covers the 'Bria API' service. It carries no effective date. The terms give 126 Yigal Alon Street, Tel Aviv, for notices and 1412 Broadway, New York, in the page header. bria.ai/.well-known/security.txt, docs.bria.ai/.well-known/security.txt and engine.prod.bria-api.com/.well-known/security.txt return 404. platform.bria.ai returns the console's HTML page at that path. RDAP for bria.ai gives a registration date of 2020-04-03. status.bria.ai is an Atlassian Statuspage. No API changelog was found in the docs sitemap. The SDK repository has a `CHANGELOG.md` for each language. ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service** (https://drive.google.com/file/d/1MZaT6xUb5aj9irslyFHSWKMV9epMMXSl/view), read 2026-10-08. Our reader couldn't read it (the page has 15 words of text without a browser, so the document is drawn by script or sits elsewhere). **Privacy policy** (https://bria.ai/privacy-policy), read 2026-10-08, gives no date, states 6 of the 8 things a reader expects. - Not found in the text. Gives the date it was last updated. - Says how long data is kept. For as long as needed, with no period named. - Gives a privacy contact. hi@bria.ai. - Not found in the text. Says where data is transferred or stored. ## Live (updated 2026-10-08 22:39 UTC) - Right now: up, HTTP 404, 256 ms, checked 2026-10-08 22:39 UTC (get on `https://engine.prod.bria-api.com/v2`) - Uptime 24h 100.0% (36 probes) · 30 days 100.0% (36 probes) · p50 267 ms · p95 344 ms - Vendor status page: none, All Systems Operational - Always current: https://www.anchorterminal.com/api/v1/live/bria.json ## Probe metrics Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score. ## Prices | Item | Price | Unit | Note | | --- | --- | --- | --- | | FIBO generation | $0.03 | per image | `/v2/image/generate` | | FIBO Lite generation | $0.02 | per image | | | FIBO Edit | $0.03 | per image | instruction editing | | Background removal | $0.018 | per image | | | Increase resolution | $0.02 | per image | | | Structured prompt | $0.02 | per call | | | Video background removal | $0.0225 | per second of video | pricing page figure. bria.ai/llms.txt says $0.01 | Across all listings: https://www.anchorterminal.com/prices/index.md ## Strengths - Per-image prices are public, from $0.018 for background removal to $0.03 for FIBO generation and FIBO Edit - The free plan gives 100 calls on every endpoint with no card, at 10 requests a minute - Each API has a downloadable OpenAPI 3.0 file, and every docs page is served as Markdown with an `llms.txt` index - The Online Terms and Conditions warrant that customer content is not used to train generative models without written consent - A returned `seed` and `structured_prompt` reproduce an image when sent back, per the docs ## Weaknesses - API keys are organisation-wide with no scopes, and no spend cap was found in the reviewed documentation - No API changelog or deprecation policy was found, and the OpenAPI files carry an empty version - The streaming background removal WebSocket takes `api_token` as a URL query parameter - No `security.txt`, disclosure policy or bug bounty was found. ISO 27001 and SOC 2 are stated on the site with no report or trust centre linked - All 18 tools in `bria-mcp` are marked read-only and idempotent although each call is billed ## Before you call it (notes for agents) 1. Send the key in the `api_token` header, not as `Authorization: Bearer`. Only `/v2/image/verify` and `/v2/video/verify` work without it 2. Expect `202` with `request_id` and `status_url` from v2 endpoints. Poll `GET /v2/status/{request_id}` every 1 to 2 seconds, or pass `sync: true` 3. Status polls count towards the per-endpoint limit (10 a minute on Free, 60 on Pay-as-you-go), so prefer `webhook_url` for batches 4. Download results promptly. Image URLs expire after 3 days by default, and legacy `/v1/product/*` results after 1 hour 5. Do not resend a failed `POST` blindly. There is no idempotency key, and the SDKs retry status polls only ## Connect Install: ```bash pip install bria-client ``` First request: ```bash curl -X POST https://engine.prod.bria-api.com/v2/image/generate \ -H "api_token: $BRIA_API_TOKEN" \ -H "Content-Type: application/json" \ -d '{"prompt": "a serene mountain landscape at dawn", "aspect_ratio": "1:1"}' ``` Claude Code: ```bash claude mcp add --transport http bria https://mcp.prod.bria-api.com/mcp \ --header "api_token: $BRIA_API_TOKEN" ``` MCP client configuration: ```json { "mcpServers": { "bria": { "headers": { "api_token": "\u003cyour-bria-api-token\u003e" }, "url": "https://mcp.prod.bria-api.com/mcp" } } } ``` ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | fal image models | B | 65.2 | 262 | image.generate, image.edit, image.upscale, image.reference | no | https://www.anchorterminal.com/tools/fal-image.md | | Recraft API | D | 52.8 | 558 | image.generate, image.edit, image.upscale, image.reference | no | https://www.anchorterminal.com/tools/recraft.md | | Replicate image models | D | 50.2 | 595 | image.generate, image.edit, image.upscale, image.reference | no | https://www.anchorterminal.com/tools/replicate-image.md | | Ideogram API | D | 50 | 598 | image.generate, image.edit, image.upscale, image.reference | no | https://www.anchorterminal.com/tools/ideogram.md | | Adobe Firefly API | D | 49 | 615 | image.generate, image.edit, image.upscale, image.reference | no | https://www.anchorterminal.com/tools/adobe-firefly.md | | Stability AI Image API | E | 42.3 | 679 | image.generate, image.edit, image.upscale, image.reference | no | https://www.anchorterminal.com/tools/stability-ai-image.md | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md ## Notable - The v2 generate endpoint first turns the prompt into a structured JSON prompt with Gemini 2.5 Flash, then renders from it. `/v2/image/generate/lite` uses Bria's open FIBO-VLM bridge (source: ) - Prompt and visual moderation are opt-in request parameters (`prompt_content_moderation`, `visual_input_content_moderation`, `visual_output_content_moderation`) (source: ) - Full copyright indemnity is for enterprise customers only. Pay-as-you-go carries capped standard indemnification (source: ) - The docs `llms.txt` asks agents to send `User-Agent: BriaPlatform/APIdocs/LLMsAgent` on API calls. We record it as a fact and did not call the API (source: ) - bria.ai/llms.txt lists video background removal at $0.01 a second. The pricing page lists $0.0225 a second (source: ) - The website Terms of Use grant personal, non-commercial access only and point to the Online AI General Terms and Conditions (March 2025, V1.1), a PDF on Google Drive, for product use (source: ) - FIBO weights are on Hugging Face under a Bria licence for non-commercial use. Commercial self-hosting needs a Bria agreement (source: ) ## Compare - [Adobe Firefly API vs Bria API](https://www.anchorterminal.com/compare/adobe-firefly-vs-bria.md): D 49 vs B 63.7 - [Black Forest Labs FLUX API vs Bria API](https://www.anchorterminal.com/compare/black-forest-labs-vs-bria.md): B 63.9 vs B 63.7 - [Bria API vs fal image models](https://www.anchorterminal.com/compare/bria-vs-fal-image.md): B 63.7 vs B 65.2 - [Bria API vs Google Imagen](https://www.anchorterminal.com/compare/bria-vs-google-imagen.md): B 63.7 vs F 6.8 - [Bria API vs Ideogram API](https://www.anchorterminal.com/compare/bria-vs-ideogram.md): B 63.7 vs D 50 - [Bria API vs Leonardo.Ai API](https://www.anchorterminal.com/compare/bria-vs-leonardo-ai.md): B 63.7 vs F 37.5 - [Bria API vs OpenAI Image API](https://www.anchorterminal.com/compare/bria-vs-openai-image-api.md): B 63.7 vs BB 72.4 - [Bria API vs Recraft API](https://www.anchorterminal.com/compare/bria-vs-recraft.md): B 63.7 vs D 52.8 - [Bria API vs Replicate image models](https://www.anchorterminal.com/compare/bria-vs-replicate-image.md): B 63.7 vs D 50.2 - [Bria API vs Stability AI Image API](https://www.anchorterminal.com/compare/bria-vs-stability-ai-image.md): B 63.7 vs E 42.3 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on bria.ai or one of its subdomains, or the README of github.com/Bria-AI/bria-client. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "bria", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify HTML badge: ```html Bria API on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![Bria API on Anchor Terminal](https://www.anchorterminal.com/badges/bria.svg)](https://www.anchorterminal.com/tools/bria) ``` Plain link: ```html Bria API on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Bria API is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/bria-dark.png - Light: https://www.anchorterminal.com/assets/share/bria-light.png