LLM · sync
budget-chat
One endpoint, every free model: GLM, Nemotron, MiniMax, Gemma, Ling, Laguna.
Model picker
Try this agent
Sign in to invoke this agent. New accounts get 100 credits.
About
budget-chat is the catch-all for the free tier. Instead of one listing per vendor, it exposes a single endpoint over every zero-cost model orqis has vetted, so you switch models by changing one string.
**Managed-mode allowlist** (all free on OpenRouter): • `z-ai/glm-5.2:free` — GLM 5.2, 256K context • `nvidia/nemotron-3-super-120b-a12b:free` (default) — Nemotron 3 Super 120B • `nvidia/nemotron-3.5-lightning:free` — Nemotron 3.5 Lightning, 1M context • `minimax/minimax-m2.7:free` — MiniMax M2.7 • `google/gemma-4-31b-it:free` — Gemma 4 31B • `inclusionai/ling-3.0-flash-fin:free` — Ling 3.0 Flash • `poolside/laguna-s-2.1:free` — Laguna S 2.1 • `cohere/north-mini-code:free` — North Mini Code
`GET /v1/agents/budget-chat` returns the live allowlist, so you don't have to hard-code this.
**Modes:** • **Managed** — `OPENROUTER_API_KEY` set on the host; 1 credit per call; allowlisted models only (anything else gets a 400 naming the allowlist). • **BYO key** — pass your own OpenRouter `apiKey`; 1-credit routing fee; any model id accepted, paid models included. • **Mock** — canned echo, refunded to 0 credits.
Response includes `usage.costUsd`, which reads $0 on free models. Managed mode caps `maxTokens` at 2048 — free models share a per-account rate limit. Non-streaming.
Models & weights
7 of 8 models this agent routes to publish their weights. Pass a model slug to pick one, or omit it for the default.
- 192K ctxWeightsMiniMax M2.7Default
minimax/minimax-m2.7:free - 256K ctxWeightsLaguna S 2.1
poolside/laguna-s-2.1:free - 256K ctxWeightsGLM 5.2
z-ai/glm-5.2:free - 256K ctxWeightsGemma 4 31B
google/gemma-4-31b-it:free - 256K ctxAPI-onlyLing 3.0 Flash
inclusionai/ling-3.0-flash-fin:free - 256K ctxWeightsNorth Mini Code
cohere/north-mini-code:free - 1M ctxWeightsNemotron 3.5 Lightning
nvidia/nemotron-3.5-lightning:free - 256K ctxWeightsNemotron 3 Super 120B
nvidia/nemotron-3-super-120b-a12b:free
Weights links come from OpenRouter's model metadata, not from a hand-maintained list, so they track the live roster.
{
"type": "object",
"required": [
"messages"
],
"properties": {
"messages": {
"type": "array",
"minItems": 1,
"maxItems": 64,
"items": {
"type": "object",
"required": [
"role",
"content"
],
"properties": {
"role": {
"type": "string",
"enum": [
"user",
"assistant",
"system"
]
},
"content": {
"type": "string",
"maxLength": 100000
}
}
}
},
"model": {
"type": "string",
"default": "nvidia/nemotron-3-super-120b-a12b:free",
"description": "OpenRouter slug (vendor/model). Managed mode: must be on the budget allowlist. BYO mode: any."
},
"maxTokens": {
"type": "integer",
"minimum": 1,
"maximum": 8192,
"default": 1024
},
"temperature": {
"type": "number",
"minimum": 0,
"maximum": 2,
"default": 1
},
"apiKey": {
"type": "string",
"description": "BYO OpenRouter key. When set, routing fee is 1 credit and the allowlist is lifted."
}
}
}These are descriptive previews. Schema-validated invocation lands in Sprint 6 with an interactive "Try it" panel.
Reviews (0)
No reviews yet — be the first to share your experience.
Used this agent? Leave a review.
Sign in to share your experience.