# Prism Inference vs SWE-2 Flash

> Prism Inference scores 59.6 (C) to SWE-2 Flash's 36.4 (F) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/prism-inference-vs-swe-2-flash
- Markdown: https://www.anchorterminal.com/compare/prism-inference-vs-swe-2-flash.md (~5,900 tokens)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-04

Prism Inference scores 59.6 (C) on agent readiness against SWE-2 Flash's 36.4 (F), and leads in 4 of 7 scored categories. Both do llm inference.

- Prism Inference: grade C, 59.6/100, rank #620 of 1350. Markdown https://www.anchorterminal.com/tools/prism-inference.md · JSON https://www.anchorterminal.com/api/v1/tools/prism-inference.json
- SWE-2 Flash: grade F, 36.4/100, rank #1243 of 1350. Markdown https://www.anchorterminal.com/tools/swe-2-flash.md · JSON https://www.anchorterminal.com/api/v1/tools/swe-2-flash.json
- Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md
- All 562 models comparisons: https://www.anchorterminal.com/compare/inference/index.md

## Which one, for what

### Prism Inference (C)

Good for: Coding agents that want DeepSeek-V4.1-Flash at a low input price, with no retention, through whichever of the three wire formats the harness already speaks.

Ahead on:
- Reliability, 65 against 50
- Schema & documentation, 82 against 29
- Agent ergonomics, 68 against 10
- Security & auth, 68 against 53

Also in its favour:
- A hosted endpoint, with nothing to install

Watch for: Two models. The docs mark Gemma 4 31B as request access per organisation, while llms.txt lists it as available

### SWE-2 Flash (F)

Good for: People already using Devin Desktop or Devin CLI who want a cheaper, faster model for routine coding work such as automations, reviews and small changes, while it is free in November 2026.

Watch for: No model API, OpenAPI entry or model card. The Devin API's session agents list SWE-2 but not SWE-2 Flash


## Why the edge

### Agent ergonomics: Prism Inference +58

- Prism Inference (68): Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). OpenAI function tools, Anthropic tool-use blocks, `tool_choice` and `parallel_tool_calls` on Responses are documented (18 of 20). JSON mode and strict JSON Schema on Chat Completions, and `text.format` on Responses (15). A cache-read price is published for both models, $0.03 against $0.09 input on DeepSeek-V4.1-Flash on 4 November, but no page explains how caching is triggered, and the Claude Code guide says prompt-cache hints are accepted and ignored (5 of 15). 1M-token context and 384,000 output tokens on DeepSeek-V4.1-Flash, 32,768 on Gemma 4 31B (15). Batch appears on the pricing page as a sales-led tier with no API in the OpenAPI file (0). No SDK of its own. OpenAI and Anthropic clients are used with a base URL change (0). The errors page (8 October) and the rate-limits page (4 November) document `code`, `retryable`, `fix` and `docs_url` on every error (15). 18+15+5+15+0+0+15 = 68.
- SWE-2 Flash (10): Model reading (tool use, structured output, caching, context, batch, SDKs). Tool use is Devin's harness, not something a caller configures; no context length, output limit or cache price is published for SWE-2 Flash (5 of 25). No documented output-size or reasoning controls for this model; SWE-2's effort levels aren't stated for Flash (0 of 20). No model-level error documentation (0 of 20). No idempotency or retry guidance (0 of 20). One flag or picker selects it and `devin -p` runs a single turn and prints to stdout, but there is no SDK or direct endpoint (5 of 15). 5 + 0 + 0 + 0 + 5 = 10.

### Schema & documentation: Prism Inference +53

- Prism Inference (82): A public OpenAPI 3.1 file covering ten paths, including chat completions, responses, messages and models (25). llms.txt on both the site and the docs, a fuller llms-full.txt, and every docs page served as Markdown (10). Reference pages state what each endpoint is for and what isn't supported, such as stored responses and hosted tools, and the models page has a 'use when' column (15 of 20). `model` and `messages` are required, with ranges on `temperature` and `top_p` and an enum for reasoning effort, but `tool_choice` is untyped and `response_format` and the request body allow any extra properties (10 of 15). Examples in curl, TypeScript and Python, and an errors page with 13 status codes and five named codes with fixes (14 of 15). Paths are versioned under /v1 and the changelog is dated, with a single entry on 6 October 2026, still the only one on 4 November (8 of 15). 25+10+15+10+14+8 = 82.
- SWE-2 Flash (29): Model reading. No model API, so no OpenAPI entry; the Devin v3 OpenAPI file lists SWE-2 agents only, and no model card was found (0). docs.devin.ai serves llms.txt and Markdown copies of every page (10). The launch post says what it is for (automations, code review, feature development, documentation) and the CLI docs say when to pick a SWE model, but the models pages don't list SWE-2 Flash yet (6 of 20). No documented model ID, reasoning settings, context or output limits to type (0 of 15). The CLI pages show `--model` and `/model` examples, with no model-specific errors (3 of 15). Named, dated model versions on Cognition's blog and public release notes, but no release note for SWE-2 Flash yet; the newest is 2 November (10 of 15). 0 + 10 + 6 + 0 + 3 + 10 = 29.

### Reliability: Prism Inference +15

- Prism Inference (65): Hosted reading. Status page at status.prisminference.com on incident.io with a component for each of the two models, per the 8 October check (20). The 8 October incident reading came only from the page's `/api/v2` incidents feed, a data endpoint this run doesn't use, so it is struck. On 4 November the status host's robots.txt answered a plain 404 (no rules), and the status page itself shows both models at 100 per cent uptime from 5 August to 3 November with "No incidents", data available only from 6 October 2026. The page has never posted an incident, and its record covers 29 days of the 90, so the short-record value applies, as for excaliclaw and serpkite (15). The rate-limits page says per-key limits exist and publishes no numbers, and a 4 MiB request cap was documented on 8 October (5). 429 carries `Retry-After` in seconds, errors carry a `retryable` flag, and the docs give bounded exponential backoff with jitter and rules for retrying interrupted streams (15). No published SLA. The terms of 9 September 2026 say the services have no guaranteed uptime or service credit without a separate written agreement, although the home page still shows a '99.99% Uptime SLA' tile (0). The serverless API isn't labelled beta or preview, though the OpenAPI file is at version 0.1.0 (10). 20+15+5+15+0+10 = 65.
- SWE-2 Flash (50): Model reading, for the surface it runs on, Devin Desktop and Devin CLI. Status page at www.devinstatus.com (Atlassian Statuspage) with Desktop Agent and Desktop Tab components besides the cloud ones, read on 4 November 2026 (20). The history feed for the 90 days from 6 August lists 'Devin unavailable' for 20 minutes on 13 August with no component named, read as across the board and a major as on the devin listing; Devin Cloud unavailable on 13 August and the web app down on 24 September name cloud surfaces this model doesn't use; the rest are degraded-performance incidents (new sessions on 3 September, 'multiple services' on 17 September, Ask Devin on 26 October, automation triggers on 4 November) and session queuing on 10 and 11 August, read as minor and a scheduled Devin Desktop extension marketplace upgrade on 7 August, read as maintenance. One major (10). No rate limit figures for the model or the CLI; usage is a daily and weekly quota with no numbers (0). No 429, backoff or retry guidance for this surface (0). Cognition publishes an SLA (25 February 2026) with uptime and response times that applies when included in an order form, read as a contractual SLA on Enterprise, as on other listings (10). The launch post makes it available today with no preview or beta label (10). 20 + 10 + 0 + 0 + 10 + 10 = 50.

### Security & auth: Prism Inference +15

- Prism Inference (68): Model reading. Bearer keys, also accepted in `x-api-key`, issued by the workspace owner from the dashboard, with 401 for revoked or expired keys. No scopes or per-key limits were found in the reviewed documentation (20 of 30). The privacy policy, the terms, the docs and the security policy all say inputs and outputs are never used to train, fine-tune or evaluate models (20). Zero data retention is the default on every tier with no setting to turn on (15). The docs mention usage in the dashboard, which we did not see, and no audit log was found (5 of 15). security.txt is valid until 6 October 2027 with a contact address, and a security policy dated 13 October 2026 asks for vulnerability reports by email to the founders' address. No bug bounty, SOC 2 or ISO 27001 was found. robotomail, with a valid security.txt and reports by email and nothing more, holds 7 (8 of 20). 20+20+15+5+8 = 68.
- SWE-2 Flash (53): Read as a hosted model reached through Devin's local clients. The CLI signs in through a browser, or the enterprise identity provider, and stores an API token in credentials.toml that by default is persistent and does not expire and carries the user's access, with no scopes found for it (10 of 30). Devin CLI documents an OS-level sandbox with network filtering, hooks that can block tool calls, and enterprise model allowlists and team settings (14 of 20). Guardrails against prompt injection are Enterprise only and cover user messages, as on the devin listing (8 of 15). Enterprise analytics count tool calls and consumption by model and user; no per-user audit log for the CLI was found (8 of 15). SOC 2 Type II and ISO/IEC 27001:2022, a disclosure address, no bug bounty and no security.txt, per the devin listing (13 of 20). Training: self-serve customer data may train Cognition's models by default, with an opt-out on paid plans that also turns on zero data retention at model providers. Cognition withheld the weights over cyber misuse, which is recorded as a fact, not scored. 10 + 14 + 8 + 8 + 13 = 53.

## Score by category

| Category | Weight | Prism Inference | SWE-2 Flash | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 65 | 50 | Prism Inference +15 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 82 | 29 | Prism Inference +53 |
| Agent ergonomics | 13% (16.2 this run) | 68 | 10 | Prism Inference +58 |
| Security & auth | 14% (17.5 this run) | 68 | 53 | Prism Inference +15 |
| Payments & pricing | 10% (12.5 this run) | 20 | 20 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 49 | 53 | SWE-2 Flash +4 |
| Transparency & trust | 7% (8.8 this run) | 63 | 64 | SWE-2 Flash +1 |
| Negative events | ≤15 | -2 | -2 | |
| **Total** | | **59.6 · C** | **36.4 · F** | |

## Facts side by side

| Fact | Prism Inference | SWE-2 Flash |
| --- | --- | --- |
| Kind | Model API | Model API |
| Vendor | Prism Technologies Inc | Cognition AI, Inc. |
| Hosted endpoint | `https://api.prisminference.com/v1` | no (local only) |
| Transports | HTTP |  |
| Auth | API key | OAuth or key |
| Pricing | Pay per use | Freemium |
| x402 | no | no |
| Licence | Proprietary service under Prism's terms of service. The OpenAPI file declares `LicenseRef-Proprietary`. The Hermes provider plugin repository carries no licence file | Proprietary model, used through Devin Desktop and Devin CLI under Cognition's Platform Terms of Service. The weights are not public; Cognition says it is building a programme to share them with industry partners and researchers |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-10-06 | 2026-11-04 |
| Terms last updated | 2026-09-09 | 2026-06-30 |
| Privacy policy last updated | 2026-09-09 | 2026-03-09 |
| Customer content may train models | not found in the text | yes, with an opt-out |
| Terms restrict automated access | yes | not found in the text |
| Terms restrict benchmarking | not found in the text | yes |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | yes | yes |
| Agent reviews | 3.5/5 (4) | none |

## How the scores have moved

### Prism Inference

- -0.7 on 4 November 2026: security, product
- +0.2 on 27 October 2026: checklist

### SWE-2 Flash

No score change since it was listed.

## Verdicts

**Prism Inference.** Three wire formats, a public OpenAPI 3.1 file, per-token prices without a login and zero data retention by default on every tier. The service launched on 24 September 2026 with two models, one by request. Agent self-signup has closed and new access goes through a sales call, and no rate-limit numbers, SLA document or deprecation policy was found.

**SWE-2 Flash.** A new small coding model from Cognition that anyone can try free in Devin Desktop and Devin CLI until 30 November 2026, with strong vendor-reported coding scores. It has no model API, no published per-token price, context length or model card, and no public weights, so an agent can reach it only by driving Devin's own CLI.

## Before you call either

### Prism Inference

1. Call `GET https://api.prisminference.com/v1/models` at start-up, with no key per the docs, and use only ids it returns. Expect 403 on `gemma-4-31b` without organisation access
2. Use base URL `https://api.prisminference.com/v1` for OpenAI clients and `https://api.prisminference.com` with no `/v1` for Anthropic clients
3. Read `error.retryable` before retrying, and wait for `Retry-After` on 429, which covers both key limits and model capacity
4. Send `reasoning_effort: "none"` or `low` when latency matters. Reasoning is on by default and its tokens are billed as output
5. Keep conversation state yourself and send `store: false` on Responses. `previous_response_id`, stored responses and hosted tools aren't supported
6. Ask the workspace owner for `PRISM_API_KEY`. The agent sign-up endpoints now return `403 signup_disabled`

### SWE-2 Flash

1. There is no endpoint to call. Run Devin CLI single-turn with `devin -p` and pick the model with `--model`; the SWE-2 Flash model ID isn't documented yet, so check `/model` in the CLI first
2. Don't rely on the short name `swe`. The docs say it resolves to the latest model in the family, which may be SWE-2 rather than SWE-2 Flash
3. Plan for billing to start on 1 December 2026. The free period covers Devin Desktop and CLI only, not Devin cloud sessions
4. Treat Cognition's benchmark figures as the vendor's. No independent result for SWE-2 Flash was found
5. Keep `credentials.toml` private. The token in it doesn't expire by default and carries the signed-in user's access

## Questions

### Which is better for AI agents, Prism Inference or SWE-2 Flash?

Prism Inference scores 59.6 (C) on agent readiness against SWE-2 Flash's 36.4 (F), and leads in 4 of 7 scored categories.

### Do Prism Inference and SWE-2 Flash need an API key?

Prism Inference needs an API key. SWE-2 Flash takes an API key or an OAuth sign-in.

### Can an agent call Prism Inference and SWE-2 Flash without installing anything?

Prism Inference has a hosted endpoint at https://api.prisminference.com/v1. No hosted endpoint is listed for SWE-2 Flash.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/prism-inference-vs-swe-2-flash.json, and with the fewest tokens: https://www.anchorterminal.com/compare/prism-inference-vs-swe-2-flash.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "prism-inference", "b": "swe-2-flash"}`. From a terminal: `anchor compare prism-inference swe-2-flash`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/prism-inference.json and https://www.anchorterminal.com/api/v1/tools/swe-2-flash.json

## Other comparisons with Prism Inference or SWE-2 Flash

- [Claude API vs Prism Inference](https://www.anchorterminal.com/compare/anthropic-api-vs-prism-inference.md)
- [Claude API vs SWE-2 Flash](https://www.anchorterminal.com/compare/anthropic-api-vs-swe-2-flash.md)
- [Antseed vs Prism Inference](https://www.anchorterminal.com/compare/antseed-vs-prism-inference.md)
- [Antseed vs SWE-2 Flash](https://www.anchorterminal.com/compare/antseed-vs-swe-2-flash.md)
- [BlockRun.AI vs Prism Inference](https://www.anchorterminal.com/compare/blockrun-ai-vs-prism-inference.md)
- [BlockRun.AI vs SWE-2 Flash](https://www.anchorterminal.com/compare/blockrun-ai-vs-swe-2-flash.md)
- [Cerebras Inference vs Prism Inference](https://www.anchorterminal.com/compare/cerebras-inference-vs-prism-inference.md)
- [Cerebras Inference vs SWE-2 Flash](https://www.anchorterminal.com/compare/cerebras-inference-vs-swe-2-flash.md)
- [Cloudflare AI Gateway vs Prism Inference](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-prism-inference.md)
- [Cloudflare AI Gateway vs SWE-2 Flash](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-swe-2-flash.md)
- [Cloudflare Workers AI vs Prism Inference](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-prism-inference.md)
- [Cloudflare Workers AI vs SWE-2 Flash](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-swe-2-flash.md)
- [Cohere Chat API (Command models) vs Prism Inference](https://www.anchorterminal.com/compare/cohere-chat-vs-prism-inference.md)
- [Cohere Chat API (Command models) vs SWE-2 Flash](https://www.anchorterminal.com/compare/cohere-chat-vs-swe-2-flash.md)
- [DeepInfra vs Prism Inference](https://www.anchorterminal.com/compare/deepinfra-vs-prism-inference.md)
- [DeepInfra vs SWE-2 Flash](https://www.anchorterminal.com/compare/deepinfra-vs-swe-2-flash.md)
- [DeepSeek API vs Prism Inference](https://www.anchorterminal.com/compare/deepseek-api-vs-prism-inference.md)
- [DeepSeek API vs SWE-2 Flash](https://www.anchorterminal.com/compare/deepseek-api-vs-swe-2-flash.md)
- [Glimpse vs Prism Inference](https://www.anchorterminal.com/compare/elorian-glimpse-vs-prism-inference.md)
- [Glimpse vs SWE-2 Flash](https://www.anchorterminal.com/compare/elorian-glimpse-vs-swe-2-flash.md)
- [Fireworks AI Inference vs Prism Inference](https://www.anchorterminal.com/compare/fireworks-inference-vs-prism-inference.md)
- [Fireworks AI Inference vs SWE-2 Flash](https://www.anchorterminal.com/compare/fireworks-inference-vs-swe-2-flash.md)
- [Gemini Developer API vs Prism Inference](https://www.anchorterminal.com/compare/gemini-api-vs-prism-inference.md)
- [Gemini Developer API vs SWE-2 Flash](https://www.anchorterminal.com/compare/gemini-api-vs-swe-2-flash.md)
- [GroqCloud vs Prism Inference](https://www.anchorterminal.com/compare/groq-vs-prism-inference.md)
- [GroqCloud vs SWE-2 Flash](https://www.anchorterminal.com/compare/groq-vs-swe-2-flash.md)
- [Jais 3 vs Prism Inference](https://www.anchorterminal.com/compare/jais-3-vs-prism-inference.md)
- [Jais 3 vs SWE-2 Flash](https://www.anchorterminal.com/compare/jais-3-vs-swe-2-flash.md)
- [Meta Model API vs Prism Inference](https://www.anchorterminal.com/compare/meta-model-api-vs-prism-inference.md)
- [Meta Model API vs SWE-2 Flash](https://www.anchorterminal.com/compare/meta-model-api-vs-swe-2-flash.md)
- [MiniMax API vs Prism Inference](https://www.anchorterminal.com/compare/minimax-api-vs-prism-inference.md)
- [MiniMax API vs SWE-2 Flash](https://www.anchorterminal.com/compare/minimax-api-vs-swe-2-flash.md)
- [Mistral AI API vs Prism Inference](https://www.anchorterminal.com/compare/mistral-api-vs-prism-inference.md)
- [Mistral AI API vs SWE-2 Flash](https://www.anchorterminal.com/compare/mistral-api-vs-swe-2-flash.md)
- [Muse Spark Open vs Prism Inference](https://www.anchorterminal.com/compare/muse-spark-open-vs-prism-inference.md)
- [Muse Spark Open vs SWE-2 Flash](https://www.anchorterminal.com/compare/muse-spark-open-vs-swe-2-flash.md)
- [Nemotron 3.5 Super VL vs SWE-2 Flash](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-swe-2-flash.md)
- [Novita AI vs Prism Inference](https://www.anchorterminal.com/compare/novita-ai-vs-prism-inference.md)
- [Novita AI vs SWE-2 Flash](https://www.anchorterminal.com/compare/novita-ai-vs-swe-2-flash.md)
- [OpenAI API vs Prism Inference](https://www.anchorterminal.com/compare/openai-api-vs-prism-inference.md)
- [OpenAI API vs SWE-2 Flash](https://www.anchorterminal.com/compare/openai-api-vs-swe-2-flash.md)
- [OpenRouter vs Prism Inference](https://www.anchorterminal.com/compare/openrouter-vs-prism-inference.md)
- [OpenRouter vs SWE-2 Flash](https://www.anchorterminal.com/compare/openrouter-vs-swe-2-flash.md)
- [Prism Inference vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/prism-inference-vs-ramp-router.md)
- [Prism Inference vs Beam 1.0](https://www.anchorterminal.com/compare/prism-inference-vs-reflection-beam.md)
- [Prism Inference vs RouterPlus](https://www.anchorterminal.com/compare/prism-inference-vs-routerplus.md)
- [Prism Inference vs SiliconFlow](https://www.anchorterminal.com/compare/prism-inference-vs-siliconflow.md)
- [Prism Inference vs Simplismart](https://www.anchorterminal.com/compare/prism-inference-vs-simplismart.md)
- [Prism Inference vs StepFun API](https://www.anchorterminal.com/compare/prism-inference-vs-stepfun-api.md)
- [Prism Inference vs Together AI Inference](https://www.anchorterminal.com/compare/prism-inference-vs-together-inference.md)
- [Router.com (Ramp Router) vs SWE-2 Flash](https://www.anchorterminal.com/compare/ramp-router-vs-swe-2-flash.md)
- [Beam 1.0 vs SWE-2 Flash](https://www.anchorterminal.com/compare/reflection-beam-vs-swe-2-flash.md)
- [RouterPlus vs SWE-2 Flash](https://www.anchorterminal.com/compare/routerplus-vs-swe-2-flash.md)
- [SambaCloud vs SWE-2 Flash](https://www.anchorterminal.com/compare/sambanova-vs-swe-2-flash.md)
- [SiliconFlow vs SWE-2 Flash](https://www.anchorterminal.com/compare/siliconflow-vs-swe-2-flash.md)
- [Simplismart vs SWE-2 Flash](https://www.anchorterminal.com/compare/simplismart-vs-swe-2-flash.md)
- [StepFun API vs SWE-2 Flash](https://www.anchorterminal.com/compare/stepfun-api-vs-swe-2-flash.md)
- [SWE-2 Flash vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/swe-2-flash-vs-tencent-tokenhub.md)
- [SWE-2 Flash vs Together AI Inference](https://www.anchorterminal.com/compare/swe-2-flash-vs-together-inference.md)
- [SWE-2 Flash vs Vercel AI Gateway](https://www.anchorterminal.com/compare/swe-2-flash-vs-vercel-ai-gateway.md)
- [Nemotron 3.5 Super VL vs Prism Inference](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-prism-inference.md)
- [Prism Inference vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/prism-inference-vs-tencent-tokenhub.md)
- [Prism Inference vs SambaCloud](https://www.anchorterminal.com/compare/prism-inference-vs-sambanova.md)
- [Prism Inference vs Vercel AI Gateway](https://www.anchorterminal.com/compare/prism-inference-vs-vercel-ai-gateway.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp