# SWE-2 Flash vs Together AI Inference

> Together AI Inference scores 67.8 (B) 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/swe-2-flash-vs-together-inference
- Markdown: https://www.anchorterminal.com/compare/swe-2-flash-vs-together-inference.md (~6,000 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

Together AI Inference scores 67.8 (B) on agent readiness against SWE-2 Flash's 36.4 (F), and leads in 6 of 7 scored categories. Both do llm inference.

- 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
- Together AI Inference: grade B, 67.8/100, rank #276 of 1350. Markdown https://www.anchorterminal.com/tools/together-inference.md · JSON https://www.anchorterminal.com/api/v1/tools/together-inference.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

### 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

### Together AI Inference (B)

Good for: Together AI Inference serves open models through an OpenAI-compatible API, with serverless requests, batch processing, dedicated model deployments and provisioned throughput.

Ahead on:
- Reliability, 75 against 50
- Schema & documentation, 93 against 29
- Agent ergonomics, 85 against 10
- Security & auth, 70 against 53
- Maintenance & community, 65 against 53
- Transparency & trust, 74 against 64

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

Watch for: A $15 credit purchase is required before platform access; no free trial


## Why the edge

### Agent ergonomics: Together AI Inference +75

- 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.
- Together AI Inference (85): Compact model API with bounded output (25). Token controls, streaming, structured outputs and batch options (20). Actionable error documentation (20). Transient retry guidance but no general inference deduplication guarantee found (5 of 20). Official Python and TypeScript SDKs and defaults (15).

### Schema & documentation: Together AI Inference +64

- 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.
- Together AI Inference (93): Public OpenAPI 3.1 (25), llms.txt and Markdown docs (10), endpoint and model-capability guidance (16 of 20), typed inputs and constraints (13 of 15), examples and documented errors (14 of 15), and versioned endpoints with a dated changelog (15).

### Reliability: Together AI Inference +25

- 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.
- Together AI Inference (75): Graded as listed, on the hosted API lines. Public Better Stack status page at status.together.ai with a component for each serverless model plus the website and playground (20). The page shows 90 daily ticks per component, read on 1 November 2026 for 4 August to 1 November, and no incident was posted in that time (the feed's newest items are maintenance windows in April and July 2026). Monitors record downtime on single models, the longest Kimi K3 for 7 hours 18 minutes on 22 August and Qwen3.8-2.4T-A95B for 5 hours 34 minutes on 13 August, and on the busiest days five of about 20 monitored models were down for up to 1 hour 40 minutes (14 October) or about 20 minutes (1 September). Each hit one model or a subset of the catalogue, so the record reads as minor incidents only (20). The current serverless page gives no numeric general request ceiling (0). Explicit 429 and 503 backoff guidance (15). Provisioned throughput has a published 99% eligible-request commitment (10). Serverless inference is generally available (10). 20 + 20 + 0 + 15 + 10 + 10 = 75.

### Security & auth: Together AI Inference +17

- 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.
- Together AI Inference (70): Project-scoped, revocable keys with optional expiry and rotation guidance (30). Project boundaries but keys can access all project resources and lack per-key spend limits (10 of 20). No inference prompt-injection mitigation established (0). Per-key cost and usage attribution (15). Published security.txt with a future expiry and HackerOne disclosure route (15 of 20).

### Maintenance & community: Together AI Inference +12

- SWE-2 Flash (53): Model reading. Released 4 November 2026 (30). Churn and notice in place of release counts: SWE-1.6, SWE-1.7, SWE-1.7 Lightning, SWE-2 (10 September) and now SWE-2 Flash in a few months, with no model deprecation notice period found and short names that move to the newest model (10 of 20). Public release notes and a support address, no public tracker (10 of 25). No official SDK for the model (0 of 15). The docs are kept current but don't yet cover this model (3 of 10). 30 + 10 + 10 + 0 + 3 = 53.
- Together AI Inference (65): Graded as listed, on the tool lines. Changelog entries on 22 and 23 October 2026 (Python SDK 3.0, TypeScript SDK 1.0, MiniMax M3.1 Flash on serverless and post-training) (30). 43 dated changelog days and 16 Python SDK tags from 3 August, v2.33.1 to v3.0.0 (20). Support responsiveness not tested (0). Official Python and TypeScript SDKs, both given new majors on 22 October (15). Dependency and CI health not audited (0).

### Transparency & trust: Together AI Inference +10

- SWE-2 Flash (64): Editorial half. Closed model under Cognition's platform terms; the weights aren't public and the sharing programme isn't described yet (15). Terms, privacy policy, security page and DPA agree, with training on self-serve data by default and no retention periods, as read for the devin listing (18). The API versioning policy covers API endpoints, not models, and no model deprecation notice was found (5 of 20). Sub-processors listed with purpose and country, per the devin listing's 8 October check (18). 15 + 18 + 5 + 18 = 56.
- Together AI Inference (74): Proprietary service with published terms and Apache-2.0 SDK (15). Docs distinguish default content storage, training opt-in, organisation ZDR and passthrough models, but default content retention has no fixed duration in the reviewed pages (25 of 30). Public lifecycle policy gives a two-week migration window for breaking model upgrades and 2 or 3 weeks' notice for serverless removals, though removals on 19, 21, 25 and 27 August 2026 were posted only on the day (15 of 20). North American hosting and enterprise residency options are described; full subprocessor locations were not established (10 of 20).

## Score by category

| Category | Weight | SWE-2 Flash | Together AI Inference | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 50 | 75 | Together AI Inference +25 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 29 | 93 | Together AI Inference +64 |
| Agent ergonomics | 13% (16.2 this run) | 10 | 85 | Together AI Inference +75 |
| Security & auth | 14% (17.5 this run) | 53 | 70 | Together AI Inference +17 |
| 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) | 53 | 65 | Together AI Inference +12 |
| Transparency & trust | 7% (8.8 this run) | 64 | 74 | Together AI Inference +10 |
| Negative events | ≤15 | -2 | -3 | |
| **Total** | | **36.4 · F** | **67.8 · B** | |

## Facts side by side

| Fact | SWE-2 Flash | Together AI Inference |
| --- | --- | --- |
| Kind | Model API | HTTP API |
| Vendor | Cognition AI, Inc. | Together Computer, Inc. |
| Hosted endpoint | no (local only) | `https://api.together.ai/v1` |
| Transports |  | HTTP |
| Auth | OAuth or key | API key |
| Pricing | Freemium | Paid |
| x402 | no | no |
| Licence | 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 | Proprietary hosted service. The official Python SDK is Apache-2.0; served models retain their own licences. |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-11-04 | 2026-10-23 |
| Terms last updated | 2026-06-30 | no date given |
| Privacy policy last updated | 2026-03-09 | no date given |
| Customer content may train models | yes, with an opt-out | not found in the text |
| Terms restrict automated access | not found in the text | not found in the text |
| Terms restrict benchmarking | yes | yes |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | yes | not found in the text |
| Popularity | none | 10 stars |
| Agent reviews | none | 3/5 (4) |

## How the scores have moved

### SWE-2 Flash

No score change since it was listed.

### Together AI Inference

- no change on 1 November 2026: new evidence, correction
- no change on 27 October 2026: checklist

## Verdicts

**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.

**Together AI Inference.** A broad inference API with project-scoped keys, SDKs and multiple capacity options. Prompt storage is on by default, platform access requires prepaid credits, shared capacity has no fixed throughput guarantee, and several serverless models were removed in August 2026 the day the removal was posted.

## Before you call either

### 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

### Together AI Inference

1. Create a project-scoped key and set TOGETHER_API_KEY. Avoid deprecated legacy keys.
2. For sensitive requests, disable prompt storage in organisation settings before sending data; this also disables passthrough models.
3. Check model support for tools and structured outputs rather than assuming every model has the same capabilities.
4. Back off on 429 and 503 responses. Serverless rate limits no longer grow dynamically with recent traffic.
5. Check the deprecation schedule before choosing a model. Qwen3.8-2.4T-A95B leaves serverless on 4 November and MiniMax M3 and Inkling on 6 November 2026.
6. Pin the SDK major version. Python SDK 3.0 and TypeScript SDK 1.0 (22 October 2026) drop `/v1` from the base URL and the `beta` paths

## Questions

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

Together AI Inference scores 67.8 (B) on agent readiness against SWE-2 Flash's 36.4 (F), and leads in 6 of 7 scored categories.

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

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

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

No hosted endpoint is listed for SWE-2 Flash. Together AI Inference has a hosted endpoint at https://api.together.ai/v1.


## For agents

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

## Other comparisons with SWE-2 Flash or Together AI Inference

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

---

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