DeepSeek API vs SiliconFlow

DeepSeek API

Accepts both OpenAI and Anthropic request formats. 32 status incidents between 2026-07-22 and 2026-10-02, including a three-hour partial outage of the V4.1 Flash API on 2026-09-14.

SiliconFlow

Per-token prices for every listed model are public, and one key reaches chat, embeddings, reranking, image, video and speech through OpenAI-style and Anthropic-style routes. No status page, SLA, security page or official SDK was found, release notes stop at 11 June 2026, and several model removals are dated the same day as their notice.

DeepSeek API

1. Send only data you'd be happy to publish
2. Schedule bulk work off-peak for half price. Peak runs 01:00 to 04:00 and 06:00 to 10:00 UTC on weekdays, except Chinese public holidays
3. Set max_tokens yourself. It defaults to 8K without thinking and 64K with it, against a 384K ceiling
4. For schema-checked tool arguments use base URL https://api.deepseek.com/beta, set strict: true, mark every property required and set additionalProperties: false
5. Keep a fallback provider and check the model field. 429 carries no Retry-After, and deepseek-v4-flash now answers as V4.1 Flash

SiliconFlow

1. Set the OpenAI client's base URL to https://api.siliconflow.com/v1, or the Anthropic client's to https://api.siliconflow.com/, and send the key as a Bearer token
2. Take model ids from the model pages or GET /v1/models, not from the OpenAPI enum or the function calling guide, which list removed models
3. Check the model field of each response. On 11 June 2026 traffic for GLM-5 and Kimi-K2.5 was routed to successor models
4. Use response_format of json_object only where the model page says JSON Mode is supported, and keep max_tokens about 10,000 below the context length
5. Set the Claude Code environment variables by hand. The automated route pipes a script from an Amazon S3 bucket into bash