Jais 3 vs SiliconFlow

Jais 3

Jais 3 runs on the owner's hardware through OpenAI-compatible servers in vLLM and SGLang, with tool calls, three reasoning levels and a 512K context, from a 2.2 GB 0.9B model to a 758 GB 375B one. The weights download without sign-up under Apache-2.0, but every launch command trusts remote code, and no technical report or security contact is published.

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.

Jais 3

1. Start vLLM or SGLang with --reasoning-parser k2_horizon, and add --tool-call-parser k2_horizon (vLLM also --enable-auto-tool-choice) for tools, or tool calls come back as raw text
2. Pass reasoning_effort (high, medium or low) and tool_call_format inside chat_template_kwargs. Other values return a template error
3. Send each earlier assistant turn back with reasoning_content as a string, even an empty one. A missing or null thinking field makes the template raise an error
4. Send your own system message, or set default_system_prompt to an empty string. Without one the template inserts an identity prompt naming IFM, Inception42 and Cerebras
5. Budget at least 32,768 output tokens at high effort, which the cards recommend for every request

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