Jais 3 vs OpenRouter

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.

OpenRouter

Public OpenAPI document, llms.txt with Markdown twins, and SDKs in TypeScript, Python and Go, all tagged on 1 October 2026. No machine payment. USDC top-ups go to a prepaid balance.

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

OpenRouter

1. Set provider.data_collection: "deny" or provider.zdr: true when the prompt holds anything private
2. Pass a models list so a failed provider falls through to the next one
3. Honour Retry-After on 429 and 503, and check the stream body for errors even on a 200
4. Set max_price so a routed request can't land on an expensive provider
5. Free models allow 50 requests a day until $10 of credit has been bought. Check GET /api/v1/key for what's left