Jais 3 vs Vercel AI Gateway

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.

Vercel AI Gateway

Token prices pass through with no markup, prompts are not stored by the gateway, and budgets, provider failover and per-request logs are built in. The free monthly credit needs a card on file, rate limits are not published as numbers, no SLA covers the API, and the contractual promise not to train on content applies to Enterprise subscriptions only.

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

Vercel AI Gateway

1. Read GET https://ai-gateway.vercel.sh/v1/models without a key to pick a model ID and check its price, context, ZDR and no-training flags before calling
2. Set zeroDataRetention or disallowPromptTraining to true in providerOptions.gateway on sensitive requests. Default routing ignores provider retention and training policies
3. Treat a 429 as retryable and honour retry-after when present. A 402 with quota_for_entity_exceeded is a spent budget, so do not retry it
4. On a Token Pass key, a 403 with no_providers_available means spent credit or a model outside the pass. Retry with a standard AI Gateway key, which bills credits
5. Set inferenceRegion when data residency matters. The default global may run inference outside the user's jurisdiction