OpenAI-compatible API

One AI Gateway for every model

One AI Gateway for every model — OpenAI-compatible endpoint.

Create free account Read API docs

OpenAI SDK readyChange only base URL + API key

SSE streamingReal-time token passthrough

Multi-model routingFast, balanced, or premium paths

Free tierNo credit card to start

curl https://router.web-annonces.net/v1/chat/completions \
  -H "Authorization: Bearer sk-sqr-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"auto/fast","messages":[{"role":"user","content":"Hello"}]}'

from openai import OpenAI

client = OpenAI(
    api_key="sk-sqr-...",
    base_url="https://router.web-annonces.net/v1",
)
r = client.chat.completions.create(
    model="auto/fast",
    messages=[{"role": "user", "content": "Hello"}],
)
print(r.choices[0].message.content)

const r = await fetch("https://router.web-annonces.net/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer sk-sqr-...",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "auto/fast",
    messages: [{ role: "user", content: "Hello" }],
  }),
});
const data = await r.json();

How it works

From signup to your first API call in three simple steps.

Sign up

Create a free account — no credit card required.

Create API key

Generate sk-sqr-... from your dashboard.

Connect your tool

Set base URL + key in Open WebUI, Cursor, LangChain, or any OpenAI SDK.

Features

Built for production teams

Everything you need to ship AI features without managing multiple provider integrations.

Unified endpoint

One OpenAI-compatible base URL for chat, streaming, and model routing.

Usage controls

Daily token caps, RPM limits, and concurrency guards per plan.

Privacy-first logs

We store metadata only — not your prompts or completion text.

Flexible billing

Start free, then upgrade weekly plans when Stripe checkout is enabled.

Pricing

Transparent weekly plans with clear limits. Scale when your traffic grows.

Pro

Models: 261

119.99 USD / week

19.99 USD / day

80,000,000 tokens / day
200 req / min
10 concurrent

Model reference pricing

List prices per 1M tokens for featured models. Your subscription plan controls daily quotas — not per-token billing.

bytez/dreamlike-anime-1.0

Dreamlike Anime 1.0 — Bytez Free open text-to-image (SD ≤~1B · under Free ≤7B)

IMAGE_GEN

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

bytez/dreamlike-photoreal-2.0

Dreamlike Photoreal 2.0 — Bytez Free open text-to-image (SD ≤~1B · under Free ≤7B)

IMAGE_GEN

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

bytez/openjourney

Openjourney — Bytez Free open text-to-image (SD ≤~1B · under Free ≤7B)

IMAGE_GEN

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

bytez/sd-turbo

SD Turbo — Bytez Free open text-to-image (SD ≤~1B · under Free ≤7B)

IMAGE_GEN

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

bytez/sd-v1-4

Stable Diffusion v1.4 — Bytez Free open text-to-image (SD ≤~1B · under Free ≤7B)

IMAGE_GEN

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

bytez/sd-v1-5

Stable Diffusion v1.5 — Bytez Free open text-to-image (SD ≤~1B · under Free ≤7B)

IMAGE_GEN

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

dahl/glm-5.2

GLM 5.2 — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

dahl/kimi-k2.6

Kimi K2.6 — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

dahl/minimax-m2.7

MiniMax M2.7 — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

swift/gemini-2.5-flash

Free · Gemini 2.5 Flash (AI Studio) · serial queue (1 concurrent)

Serial queue: only one Gemini request at a time across all clients; others wait.

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

swift/gemini-2.5-flash-lite

Free · Gemini 2.5 Flash-Lite (AI Studio) · serial queue (1 concurrent)

Serial queue: only one Gemini request at a time across all clients; others wait.

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

swift/gemini-2.5-pro

Free · Gemini 2.5 Pro (AI Studio) · serial queue (1 concurrent, low daily cap)

Serial queue: only one Gemini request at a time across all clients; others wait.

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

image

Gemini 2.5 Flash Image · needs Google Billing · serial queue (1 concurrent)

IMAGE_GEN

Queued Gemini image gen. SouqRouter price $0; Google AI Studio Billing/Prepay required (image Free Tier = Not available).

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

image-2

Gemini 3.1 Flash Image · needs Google Billing · serial queue (1 concurrent)

IMAGE_GEN

Queued quality Gemini image gen. SouqRouter price $0; Google Billing required for image models.

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

image-lite

Gemini 3.1 Flash Lite Image · needs Google Billing · serial queue (1 concurrent)

IMAGE_GEN

Queued volume Gemini image gen. SouqRouter price $0; Google Billing required for image models.

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/claude-opus-4.7

hallo/claude-opus-4.7 — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/claude-sonnet-4.6

hallo/claude-sonnet-4.6 — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/deepseek-v4-flash

hallo/-v4-flash — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/deepseek-v4-pro

hallo/-v4-pro — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/gemini-3-flash

hallo/gemini-3-flash — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/gemini-3-flash-agent

hallo/gemini-3-flash-agent — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/gemini-3.1-pro-low

hallo/gemini-3.1-pro-low — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/gemini-3.5-flash-extra-low

hallo/gemini-3.5-flash-extra-low — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/gemini-3.5-flash-low

hallo/gemini-3.5-flash-low — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/gemini-3.6-flash-low

hallo/gemini-3.6-flash-low — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/gemini-3.7-flash-low

hallo/gemini-3.7-flash-low — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/glm-5.2

hallo/glm-5.2 — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/gpt-5.4

hallo/gpt-5.4 — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/gpt-5.4-mini

hallo/gpt-5.4-mini — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/gpt-5.5

hallo/gpt-5.5 — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/gpt-5.6-luna

hallo/gpt-5.6-luna — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/gpt-5.6-sol

hallo/gpt-5.6-sol — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/gpt-5.6-sol-max

hallo/gpt-5.6-sol-max — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/gpt-5.6-terra

hallo/gpt-5.6-terra — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/kimi-k2.7-code

hallo/kimi-k2.7-code — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/qwen-3.7-max

hallo/qwen-3.7-max — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

hallorouter/qwen-3.7-plus

hallo/qwen-3.7-plus — HalloRouter chat · hallorouter · Economical · wallet billing (actual × multiplier)

TEXT

Economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

huggingface/apertus-8b

Apertus 8B — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

huggingface/llama-3.1-8b-hf

Llama 3.1 8B — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

huggingface/olmo-3-7b

OLMo 3 7B — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

huggingface/phi-4

Phi-4 — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

huggingface/qwen2.5-coder-3b

Qwen2.5 Coder 3B — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

huggingface/qwen2.5-coder-7b

Qwen2.5 Coder 7B — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

huggingface/qwen3-4b

Qwen3 4B — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

huggingface/qwen3-4b-thinking Beta

Qwen3 4B Thinking — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

mistral/devstral Beta

Devstral — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

mistral/magistral-small Beta

Magistral Small — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

mistral/ministral-14b

Ministral 14B — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

mistral/ministral-3b

Ministral 3B — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

mistral/ministral-8b

Ministral 8B — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

mistral/mistral-large-api Beta

Mistral Large — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

mistral/mistral-nemo

Mistral Nemo — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

mistral/mistral-small

Mistral Small — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nararouter/hy3-c

HY3 — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nararouter/mistral-large

Mistral Large — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nararouter/mistral-medium

Mistral Medium 3.5 — Very economical

TEXT CODING REASONING VISION LIGHTWEIGHT EMBEDDING OCR TOOLS AGENTIC

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/deepseek-ai-deepseek-v4-flash-0731

ai/-v4-flash-0731 — NVIDIA Build free NIM chat · -ai · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/google-gemma-4-31b-it

google/gemma-4-31b-it — NVIDIA Build free NIM chat · google · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/meta-llama-3.1-70b-instruct

meta/llama-3.1-70b-instruct — NVIDIA Build free NIM chat · meta · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/meta-llama-3.1-8b-instruct

meta/llama-3.1-8b-instruct — NVIDIA Build free NIM chat · meta · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/meta-llama-3.2-1b-instruct

meta/llama-3.2-1b-instruct — NVIDIA Build free NIM chat · meta · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/meta-llama-3.2-3b-instruct

meta/llama-3.2-3b-instruct — NVIDIA Build free NIM chat · meta · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/meta-llama-3.3-70b-instruct

meta/llama-3.3-70b-instruct — NVIDIA Build free NIM chat · meta · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/minimaxai-minimax-m3

minimaxai/minimax-m3 — NVIDIA Build free NIM chat · minimaxai · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/mistralai-mistral-nemotron

mistralai/mistral-nemotron — NVIDIA Build free NIM chat · mistralai · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/nvidia-llama-3.1-nemotron-nano-8b-v1

nvidia/llama-3.1-nemotron-nano-8b-v1 — NVIDIA Build free NIM chat · nvidia · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/nvidia-llama-3.3-nemotron-super-49b-v1

nvidia/llama-3.3-nemotron-super-49b-v1 — NVIDIA Build free NIM chat · nvidia · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/nvidia-llama-3.3-nemotron-super-49b-v1.5

nvidia/llama-3.3-nemotron-super-49b-v1.5 — NVIDIA Build free NIM chat · nvidia · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/nvidia-nemotron-3-nano-30b-a3b

nvidia/nemotron-3-nano-30b-a3b — NVIDIA Build free NIM chat · nvidia · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/nvidia-nemotron-3-super-120b-a12b

nvidia/nemotron-3-super-120b-a12b — NVIDIA Build free NIM chat · nvidia · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/nvidia-nemotron-3-ultra-550b-a55b

nvidia/nemotron-3-ultra-550b-a55b — NVIDIA Build free NIM chat · nvidia · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/nvidia-nemotron-mini-4b-instruct

nvidia/nemotron-mini-4b-instruct — NVIDIA Build free NIM chat · nvidia · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/nvidia-nemotron-nano-12b-v2-vl

nvidia/nemotron-nano-12b-v2-vl — NVIDIA Build free NIM chat · nvidia · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/nvidia-nvidia-nemotron-nano-9b-v2

nvidia/nvidia-nemotron-nano-9b-v2 — NVIDIA Build free NIM chat · nvidia · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/openai-gpt-oss-120b

/gpt-oss-120b — NVIDIA Build free NIM chat · · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/openai-gpt-oss-20b

/gpt-oss-20b — NVIDIA Build free NIM chat · · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/poolside-laguna-xs-2.1

poolside/laguna-xs-2.1 — NVIDIA Build free NIM chat · poolside · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/stepfun-ai-step-3.7-flash

stepfun-ai/step-3.7-flash — NVIDIA Build free NIM chat · stepfun-ai · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/thinkingmachines-inkling

thinkingmachines/inkling — NVIDIA Build free NIM chat · thinkingmachines · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/writer-palmyra-creative-122b

writer/palmyra-creative-122b — NVIDIA Build free NIM chat · writer · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/writer-palmyra-fin-70b-32k

writer/palmyra-fin-70b-32k — NVIDIA Build free NIM chat · writer · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/writer-palmyra-med-70b

writer/palmyra-med-70b — NVIDIA Build free NIM chat · writer · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/writer-palmyra-med-70b-32k

writer/palmyra-med-70b-32k — NVIDIA Build free NIM chat · writer · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/z-ai-glm-5.2

z-ai/glm-5.2 — NVIDIA Build free NIM chat · z-ai · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nimb/zyphra-zamba2-7b-instruct

zyphra/zamba2-7b-instruct — NVIDIA Build free NIM chat · zyphra · Free · Free Endpoint tier · ~40 RPM

TEXT

Free

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nvidia/flux

Trial · NVIDIA NIM – FLUX.1 Dev

IMAGE_GEN

Higher quality FLUX.1 Dev via NVIDIA NIM.

trial

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nvidia/image

Trial · NVIDIA NIM – FLUX.1 Schnell (default covers)

IMAGE_GEN

Fast high-quality covers via NVIDIA cloud GenAI. Free Trial limited on build.nvidia.com.

trial

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nvidia/qwen

Trial · NVIDIA NIM – Qwen-Image

IMAGE_GEN

Multilingual text rendering in images via Qwen-Image.

trial

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

nvidia/sd35

Trial · NVIDIA NIM – Stable Diffusion 3.5 Large

IMAGE_GEN

SD 3.5 Large text-to-image via NVIDIA NIM.

trial

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

openrouter/auto

Free Auto — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

openrouter/laguna-xs

Laguna XS — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

openrouter/nemotron-3-nano

Nemotron 3 Nano — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

openrouter/nemotron-3-omni

Nemotron 3 Omni — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

openrouter/nemotron-3-super

Nemotron 3 Super — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

openrouter/nemotron-3-ultra

Nemotron 3 Ultra — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

openrouter/nemotron-nano-9b

Nemotron Nano 9B — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

openrouter/north-mini-code

North Mini Code — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

runware/flux

Budget · remapped to FLUX.2 klein 4B (Schnell disabled)

IMAGE_GEN

Was FLUX.1 Schnell; now klein 4B so every cover stays ≤ ~$0.0006 @ ≤1024.

budget

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

runware/image

Budget · Runware – FLUX.2 klein 4B (default covers)

IMAGE_GEN

Ultra-cheap stable covers (~$0.0006/img @ ≤1024). Best default for high volume.

budget

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

runware/twinflow

Budget · Runware – TwinFlow Z-Image-Turbo

IMAGE_GEN

Same upstream as z-turbo · display alias (~$0.0006/img @ ≤1024 · 4 steps).

budget

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

runware/z-turbo

Budget · Runware – Z-Image-Turbo

IMAGE_GEN

Photorealistic budget alternative (~$0.0006/img @ ≤1024 · 4 steps).

budget

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

siliconflow/deepseek-r1-7b

R1 Distill 7B — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

siliconflow/qwen3-8b

Qwen3 8B — Very economical

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

tf/deepseek-v4-flash

V4-Flash — TokenFaucet free (daily claim wallet) ·

TEXT

Chat via TokenFaucet daily claim wallet (modelType=free)

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

tf/gpt-5.6-terra

gpt-5.6-terra — TokenFaucet free (daily claim wallet) ·

TEXT

Chat via TokenFaucet daily claim wallet (modelType=free)

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

tf/mimo-v2.5

mimo-v2.5 — TokenFaucet free (daily claim wallet) · mimo

TEXT

Chat via TokenFaucet daily claim wallet (modelType=free)

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

tf/mimo-v2.5-pro

mimo-v2.5-pro — TokenFaucet free (daily claim wallet) · mimo

TEXT

Chat via TokenFaucet daily claim wallet (modelType=free)

Very economical

Input: $0.00 per 1M tokens
Output: $0.00 per 1M tokens

llm7/codestral-latest Paid

codestral-latest — LLM7 free (turbo) · Very economical · list $0.01/$0.02 per 1M · Free token caps ~40 RPM / 1M TPD

TEXT

Very economical

Input: $0.01 per 1M tokens
Output: $0.02 per 1M tokens

openrouter/ling-2.6-flash Paid

Ling 2.6 Flash (inclusionAI) — Paid · ~104B MoE / 7.4B active · 262K context

Economical

Input: $0.01 per 1M tokens
Output: $0.03 per 1M tokens

openrouter/mistral-nemo Paid

Mistral Nemo (12B · Mistral + NVIDIA) — Paid · multilingual · tools · 131K context

Economical

Input: $0.02 per 1M tokens
Output: $0.03 per 1M tokens

llm7/mistral-nemo-instruct-2407 Paid

mistral-Nemo-Instruct-2407 — LLM7 free (turbo) · Very economical · list $0.03/$0.03 per 1M · Free token caps ~40 RPM / 1M TPD

TEXT

Very economical

Input: $0.03 per 1M tokens
Output: $0.03 per 1M tokens

openrouter/llama-3.1-8b-instruct Paid

Llama 3.1 8B Instruct (Meta) — Paid · fast instruct · 131K context

Economical

Input: $0.02 per 1M tokens
Output: $0.04 per 1M tokens

bluesminds/openai/gpt-o3-mini-2025-01-31 Paid

GPT o3 mini (2025-01-31) — BluesMinds (chat) · default group

TEXT

Very economical

Input: $0.06 per 1M tokens
Output: $0.0072 per 1M tokens

llm7/minimax-m2.7 Paid

minimax-m2.7 — LLM7 free (turbo) · Very economical · list $0.03/$0.05 per 1M · Free token caps ~40 RPM / 1M TPD

TEXT

Very economical

Input: $0.03 per 1M tokens
Output: $0.05 per 1M tokens

bluesminds/baai/bge-m3 Paid

BGE M3 — BluesMinds (embeddings) · default group

EMBEDDING

Economical

Input: $0.08 per 1M tokens
Output: $0.0032 per 1M tokens

bluesminds/snowflake/arctic-embed-m-v1.5 Paid

Arctic Embed M v1.5 — BluesMinds (embeddings) · default group

EMBEDDING

Economical

Input: $0.08 per 1M tokens
Output: $0.0032 per 1M tokens

openrouter/ling-3.0-flash Paid

Ling 3.0 Flash (inclusionAI) — Paid · 124B MoE / ~5.1B active · agentic · 262K context

Economical

Input: $0.02 per 1M tokens
Output: $0.06 per 1M tokens

bluesminds/google/gemma-2-2b Paid

Gemma 2 2B — BluesMinds (chat) · default group

TEXT

Economical

Input: $0.08 per 1M tokens
Output: $0.0064 per 1M tokens

bluesminds/google/gemma-2b Paid

Gemma 2B — BluesMinds (chat) · default group

TEXT

Economical

Input: $0.08 per 1M tokens
Output: $0.0064 per 1M tokens

bluesminds/google/recurrentgemma-2b Paid

RecurrentGemma 2B — BluesMinds (chat) · default group

TEXT

Economical

Input: $0.08 per 1M tokens
Output: $0.0064 per 1M tokens

bluesminds/ibm/granite-3.0-2b-instruct Paid

Granite 3.0 2B Instruct — BluesMinds (chat) · default group

TEXT

Economical

Input: $0.08 per 1M tokens
Output: $0.0064 per 1M tokens

bluesminds/meta/llama-3.2-1b Paid

Llama 3.2 1B — BluesMinds (chat) · default group

TEXT

Economical

Input: $0.08 per 1M tokens
Output: $0.0064 per 1M tokens

bluesminds/nvidia/embed-qa-4 Paid

Embed QA 4 — BluesMinds (embeddings) · default group

EMBEDDING

Economical

Input: $0.08 per 1M tokens
Output: $0.0064 per 1M tokens

bluesminds/nvidia/llama-3.2-1b-instruct Paid

Llama 3.2 1B Instruct — BluesMinds (chat) · default group

TEXT

Economical

Input: $0.08 per 1M tokens
Output: $0.0064 per 1M tokens

bluesminds/nvidia/llama-3.2-3b Paid

Llama 3.2 3B — BluesMinds (chat) · default group

TEXT

Economical

Input: $0.08 per 1M tokens
Output: $0.0064 per 1M tokens

bluesminds/nvidia/llama-3.2-3b-instruct Paid

Llama 3.2 3B Instruct — BluesMinds (chat) · default group

TEXT

Economical

Input: $0.08 per 1M tokens
Output: $0.0064 per 1M tokens

bluesminds/nvidia/llama-nemotron-3-8b Paid Beta

Llama Nemotron 3 8B — BluesMinds (chat) · VIP group

TEXT

Economical

Input: $0.08 per 1M tokens
Output: $0.0064 per 1M tokens

bluesminds/nvidia/llama-nemotron-3-8b-reward Paid

Llama Nemotron 3 8B Reward — BluesMinds (chat) · default group

TEXT

Economical

Input: $0.08 per 1M tokens
Output: $0.0064 per 1M tokens

bluesminds/nvidia/nv-embed-v2 Paid

NV Embed v2 — BluesMinds (embeddings) · default group

EMBEDDING

Economical

Input: $0.08 per 1M tokens
Output: $0.0064 per 1M tokens

bluesminds/nvidia/nvclip Paid

NVClip — BluesMinds (chat) · default group

TEXT VISION

Economical

Input: $0.08 per 1M tokens
Output: $0.0064 per 1M tokens

openrouter/l3-lunaris-8b Paid

Llama 3 8B Lunaris (Sao10K) — Paid · generalist / roleplay · 8K context

Economical

Input: $0.04 per 1M tokens
Output: $0.05 per 1M tokens

llm7/gpt-oss-20b Paid

gpt-oss:20b — LLM7 free (turbo) · Very economical · list $0.04/$0.06 per 1M · Free token caps ~40 RPM / 1M TPD

TEXT

Very economical

Input: $0.04 per 1M tokens
Output: $0.06 per 1M tokens

llm7/gemma4-31b Paid

gemma4:31b — LLM7 free (turbo) · Very economical · list $0.03/$0.08 per 1M · Free token caps ~40 RPM / 1M TPD

TEXT

Very economical

Input: $0.03 per 1M tokens
Output: $0.08 per 1M tokens

openrouter/mythomax-l2-13b Paid

MythoMax 13B (Gryphe) — Paid · Llama 2 fine-tune · roleplay · 8K context

Economical

Input: $0.06 per 1M tokens
Output: $0.06 per 1M tokens

openrouter/nex-n2-mini Paid

Nex-N2-Mini (Nex AGI) — Paid · agentic MoE · text+image · coding/tools · 262K context

Economical

Input: $0.03 per 1M tokens
Output: $0.10 per 1M tokens

openrouter/granite-4.0-h-micro Paid

Granite 4.0 H Micro (IBM) — Paid · 3B · long-context tool calling · 131K context

Economical

Input: $0.02 per 1M tokens
Output: $0.11 per 1M tokens

groq/llama-3.1-8b Paid

Llama 3.1 8B — Groq free tier · Very economical · list $0.05/$0.08 per 1M · free caps ~30 RPM / 14400 RPD / 6000 TPM / 500000 TPD

TEXT

Very economical

Input: $0.05 per 1M tokens
Output: $0.08 per 1M tokens

openrouter/mistral-small-24b-instruct-2501 Paid

Mistral Small 3 (24B) — Paid · low-latency instruct · 33K context

Economical

Input: $0.05 per 1M tokens
Output: $0.08 per 1M tokens

bluesminds/google/gemma-3-27b-it Paid

Gemma 3 27B IT — BluesMinds (chat) · default group

TEXT

Medium cost

Input: $0.12 per 1M tokens
Output: $0.01 per 1M tokens

bluesminds/google/gemma-3-4b-it Paid

Gemma 3 4B IT — BluesMinds (chat) · default group

TEXT

Medium cost

Input: $0.12 per 1M tokens
Output: $0.01 per 1M tokens

bluesminds/meta/llama-3.2-3b-instruct Paid

Llama 3.2 3B Instruct — BluesMinds (chat) · default group

TEXT

Medium cost

Input: $0.12 per 1M tokens
Output: $0.01 per 1M tokens

openrouter/gemma-3-4b-it Paid

Gemma 3 4B IT (Google) — Paid · multimodal · tools · 131K context

Economical

Input: $0.05 per 1M tokens
Output: $0.10 per 1M tokens

openrouter/granite-4.1-8b Paid

Granite 4.1 8B (IBM) — Paid · tools / RAG / code · multilingual · 131K context

Economical

Input: $0.05 per 1M tokens
Output: $0.10 per 1M tokens

openrouter/solar-pro4 Paid

Solar Pro 4 (Upstage) — Paid · long-horizon / agentic · docs & coding · 524K context

Economical

Input: $0.03 per 1M tokens
Output: $0.12 per 1M tokens

openrouter/gpt-oss-20b-paid Paid

GPT-OSS 20B () — Paid · 21B MoE / ~3.6B active · tools & structured · 131K context

Economical

Input: $0.03 per 1M tokens
Output: $0.13 per 1M tokens

openrouter/qwen3.7-flash Paid

Qwen3.7 Flash (Alibaba) — Paid · vision-language · multimodal agents · 1M context

Economical

Input: $0.03 per 1M tokens
Output: $0.13 per 1M tokens

openrouter/nova-micro-v1 Paid

Nova Micro 1.0 (Amazon) — Paid · low-latency text · summarization/chat · 128K context

Economical

Input: $0.04 per 1M tokens
Output: $0.14 per 1M tokens

openrouter/gemma-3n-e4b-it Paid

Gemma 3n E4B IT (Google) — Paid · multimodal · efficient · 33K context

Economical

Input: $0.06 per 1M tokens
Output: $0.12 per 1M tokens

openrouter/laguna-xs-2.1 Paid

Laguna XS 2.1 (Poolside) — Paid · coding agent · tools · 262K context

Economical

Input: $0.06 per 1M tokens
Output: $0.12 per 1M tokens

bluesminds/adept/fuyu-8b Paid

Fuyu 8B — BluesMinds (chat) · default group

TEXT VISION

Highest cost

Input: $0.16 per 1M tokens
Output: $0.03 per 1M tokens

bluesminds/aisingapore/sea-lion-7b-instruct Paid

SEA-LION 7B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.16 per 1M tokens
Output: $0.03 per 1M tokens

bluesminds/google/codegemma-2b-instruct Paid

CodeGemma 2B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.16 per 1M tokens
Output: $0.03 per 1M tokens

bluesminds/google/codegemma-7b-instruct Paid

CodeGemma 7B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.16 per 1M tokens
Output: $0.03 per 1M tokens

bluesminds/ibm/granite-3.0-8b-instruct Paid

Granite 3.0 8B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.16 per 1M tokens
Output: $0.03 per 1M tokens

bluesminds/ibm/granite-8b-code-instruct Paid

Granite 8B Code Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.16 per 1M tokens
Output: $0.03 per 1M tokens

bluesminds/nvidia/nemotron-mini-4b-instruct Paid

Nemotron Mini 4B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.16 per 1M tokens
Output: $0.03 per 1M tokens

bluesminds/nvidia/nv-embedqa-e5-v5 Paid

NV EmbedQA E5 v5 — BluesMinds (embeddings) · default group

EMBEDDING

Highest cost

Input: $0.16 per 1M tokens
Output: $0.03 per 1M tokens

bluesminds/nvidia/nv-embedqa-mistral-7b-v2 Paid

NV EmbedQA Mistral 7B v2 — BluesMinds (embeddings) · default group

EMBEDDING

Highest cost

Input: $0.16 per 1M tokens
Output: $0.03 per 1M tokens

bluesminds/nvidia/riva-translation-en-es Paid

Riva Translation EN→ES — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.16 per 1M tokens
Output: $0.03 per 1M tokens

bluesminds/nvidia/riva-translation-en-fr Paid

Riva Translation EN→FR — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.16 per 1M tokens
Output: $0.03 per 1M tokens

bluesminds/zyphra/zamba2-7b-instruct Paid

Zamba2 7B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.16 per 1M tokens
Output: $0.03 per 1M tokens

openrouter/command-r7b-12-2024 Paid

Command R7B 12-2024 (Cohere) — Paid · RAG / tools / agents · 128K context

Economical

Input: $0.04 per 1M tokens
Output: $0.15 per 1M tokens

openrouter/ministral-3b-2512 Paid

Ministral 3 3B 2512 (Mistral) — Paid · tiny + vision · 131K context

Economical

Input: $0.10 per 1M tokens
Output: $0.10 per 1M tokens

openrouter/reka-edge Paid

Reka Edge (Reka) — Paid · 7B multimodal · vision/video · tools · 16K context

Economical

Input: $0.10 per 1M tokens
Output: $0.10 per 1M tokens

openrouter/phi-4 Paid

Phi 4 (Microsoft) — Paid · 14B · reasoning · English-focused · 16K context

Economical

Input: $0.07 per 1M tokens
Output: $0.14 per 1M tokens

bluesminds/google/deplot Paid Beta

DePlot — BluesMinds (chat) · VIP group

TEXT VISION

Highest cost

Input: $0.20 per 1M tokens
Output: $0.02 per 1M tokens

bluesminds/microsoft/kosmos-2 Paid

Kosmos 2 — BluesMinds (chat) · default group

TEXT VISION

Highest cost

Input: $0.20 per 1M tokens
Output: $0.02 per 1M tokens

bluesminds/microsoft/phi-3-mini-128k-instruct Paid

Phi-3 Mini 128K Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $0.02 per 1M tokens

bluesminds/microsoft/phi-3-mini-4k-instruct Paid

Phi-3 Mini 4K Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $0.02 per 1M tokens

bluesminds/microsoft/phi-4-mini-instruct Paid

Phi-4 Mini Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $0.02 per 1M tokens

bluesminds/microsoft/phi-4-multimodal-instruct Paid

Phi-4 Multimodal Instruct — BluesMinds (chat) · default group

TEXT VISION

Highest cost

Input: $0.20 per 1M tokens
Output: $0.02 per 1M tokens

bluesminds/bigcode/starcoder2-15b-instruct Paid

StarCoder2 15B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $0.04 per 1M tokens

bluesminds/google/gemma-3-12b-it Paid

Gemma 3 12B IT — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $0.04 per 1M tokens

bluesminds/meta/llama-3.1-8b-instruct Paid

Llama 3.1 8B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $0.04 per 1M tokens

bluesminds/nv-mistralai/mistral-nemo-12b-instruct Paid Beta

Mistral Nemo 12B Instruct (NV) — BluesMinds (chat) · VIP group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $0.04 per 1M tokens

bluesminds/nvidia/ai-synthetic-gen-llm-8b Paid

AI Synthetic Gen LLM 8B — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $0.04 per 1M tokens

bluesminds/nvidia/cosmos-reason1-7b Paid

Cosmos Reason1 7B — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $0.04 per 1M tokens

bluesminds/nvidia/gliner-pii Paid

GLiNER PII — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $0.04 per 1M tokens

bluesminds/nvidia/llama-3.1-nemotron-70b-instruct Paid

Llama 3.1 Nemotron 70B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $0.04 per 1M tokens

bluesminds/nvidia/llama-3.1-nemotron-nano-8b-v1 Paid

Llama 3.1 Nemotron Nano 8B v1 — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $0.04 per 1M tokens

bluesminds/nvidia/llama-3.1-swiftkv-8b-instruct Paid

Llama 3.1 SwiftKV 8B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $0.04 per 1M tokens

bluesminds/nvidia/nemoretrieval-embedding-1 Paid

NeMo Retrieval Embedding 1 — BluesMinds (embeddings) · default group

EMBEDDING

Highest cost

Input: $0.20 per 1M tokens
Output: $0.04 per 1M tokens

bluesminds/nvidia/nemotron-3-8b-chat Paid

Nemotron 3 8B Chat — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $0.04 per 1M tokens

bluesminds/nvidia/nemotron-4-340b-reward Paid

Nemotron 4 340B Reward — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $0.04 per 1M tokens

bluesminds/nvidia/nemotron-70b-instruct Paid

Nemotron 70B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $0.04 per 1M tokens

bluesminds/nvidia/vila-1.5-8b Paid

VILA 1.5 8B — BluesMinds (chat) · default group

TEXT VISION

Highest cost

Input: $0.20 per 1M tokens
Output: $0.04 per 1M tokens

bluesminds/sarvamai/sarvam-mistral-7b-instruct Paid

Sarvam Mistral 7B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $0.04 per 1M tokens

openrouter/qwen3.5-9b Paid

Qwen3.5-9B (Alibaba) — Paid · multimodal · reasoning/coding · 262K context

Economical

Input: $0.10 per 1M tokens
Output: $0.15 per 1M tokens

bluesminds/mistralai/mistral-7b-instruct-v0.3 Paid

Mistral 7B Instruct v0.3 — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $0.06 per 1M tokens

bluesminds/mistralai/mistral-nemo-12b-instruct Paid

Mistral Nemo 12B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $0.06 per 1M tokens

bluesminds/meta/llama-3.2-1b-instruct Paid

Llama 3.2 1B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.24 per 1M tokens
Output: $0.06 per 1M tokens

bluesminds/gpt-oss-20b Paid Beta

GPT-OSS 20B — BluesMinds (chat) · VIP group

TEXT

Medium cost

Input: $0.10 per 1M tokens
Output: $0.20 per 1M tokens

openrouter/ministral-8b-2512 Paid

Ministral 3 8B 2512 (Mistral) — Paid · balanced + vision · 262K context

Economical

Input: $0.15 per 1M tokens
Output: $0.15 per 1M tokens

bluesminds/nv-mistralai/mistral-large-2-instruct Paid

Mistral Large 2 Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.28 per 1M tokens
Output: $0.08 per 1M tokens

groq/gpt-oss-20b-fast Paid

GPT-OSS 20B Fast — Groq free tier · Economical · list $0.075/$0.3 per 1M · free caps ~30 RPM / 1000 RPD / 8000 TPM / 200000 TPD

TEXT

Economical

Input: $0.08 per 1M tokens
Output: $0.30 per 1M tokens

groq/gpt-oss-safeguard-20b Paid Beta

GPT-OSS Safeguard 20B — Groq free tier · Economical · list $0.075/$0.3 per 1M · free caps ~30 RPM / 1000 RPD / 8000 TPM / 200000 TPD

TEXT

Economical

Input: $0.08 per 1M tokens
Output: $0.30 per 1M tokens

bluesminds/mimo-v2.5 Paid

MiMo v2.5 — BluesMinds (chat) · default group

TEXT

Medium cost

Input: $0.10 per 1M tokens
Output: $0.28 per 1M tokens

bluesminds/hy3 Paid

HY3 — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $0.20 per 1M tokens

bluesminds/kimi-k2.5 Paid

Kimi K2.5 — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.28 per 1M tokens
Output: $0.15 per 1M tokens

bluesminds/moonshotai/kimi-k1.5 Paid

Kimi K1.5 — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.28 per 1M tokens
Output: $0.15 per 1M tokens

bluesminds/openai/gpt-4o-mini Paid

GPT-4o Mini — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.30 per 1M tokens
Output: $0.18 per 1M tokens

bluesminds/z-ai/glm-4.7 Paid

GLM 4.7 — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.40 per 1M tokens
Output: $0.08 per 1M tokens

bluesminds/bytedance/seed-oss-36b-instruct Paid

Seed OSS 36B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.40 per 1M tokens
Output: $0.16 per 1M tokens

bluesminds/google/gemma-4-31b-it Paid

Gemma 4 31B IT — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.40 per 1M tokens
Output: $0.16 per 1M tokens

bluesminds/meta/llama-guard-3-8b Paid

Llama Guard 3 8B — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.40 per 1M tokens
Output: $0.16 per 1M tokens

bluesminds/nvidia/ising-calculator-8b Paid

Ising Calculator 8B — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.40 per 1M tokens
Output: $0.16 per 1M tokens

bluesminds/nvidia/nemotron-4-340b-instruct Paid

Nemotron 4 340B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.40 per 1M tokens
Output: $0.16 per 1M tokens

bluesminds/nvidia/neva-22b Paid

NeVA 22B — BluesMinds (chat) · default group

TEXT VISION

Highest cost

Input: $0.40 per 1M tokens
Output: $0.16 per 1M tokens

bluesminds/stepfun-ai/step-1-128k Paid

Step-1 128K — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.40 per 1M tokens
Output: $0.16 per 1M tokens

bluesminds/upstage/solar-10.7b-instruct Paid

Solar 10.7B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.40 per 1M tokens
Output: $0.16 per 1M tokens

bluesminds/mistralai/ministral-8b-instruct Paid

Ministral 8B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.40 per 1M tokens
Output: $0.24 per 1M tokens

bluesminds/mistralai/mixtral-8x22b-instruct-v0.1 Paid

Mixtral 8x22B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.40 per 1M tokens
Output: $0.24 per 1M tokens

groq/gpt-oss-120b-fast Paid

GPT-OSS 120B Fast — Groq free tier · Economical · list $0.15/$0.6 per 1M · free caps ~30 RPM / 1000 RPD / 8000 TPM / 200000 TPD

TEXT

Economical

Input: $0.15 per 1M tokens
Output: $0.60 per 1M tokens

bluesminds/z-ai/glm-5 Paid

GLM 5 — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.60 per 1M tokens
Output: $0.18 per 1M tokens

bluesminds/z-ai/glm-5.1 Paid

GLM 5.1 — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.60 per 1M tokens
Output: $0.18 per 1M tokens

mistral/codestral Paid

Codestral — Very economical

TEXT CODING REASONING VISION LIGHTWEIGHT EMBEDDING OCR TOOLS AGENTIC

Economical

Input: $0.30 per 1M tokens
Output: $0.50 per 1M tokens

bluesminds/minimaxai/minimax-m1 Paid

MiniMax M1 — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.40 per 1M tokens
Output: $0.44 per 1M tokens

bluesminds/mistralai/codestral-2501 Paid

Codestral 2501 — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.60 per 1M tokens
Output: $0.54 per 1M tokens

bluesminds/qwen2.5 Paid

Qwen2.5 — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.20 per 1M tokens
Output: $1.00 per 1M tokens

groq/llama-3.3-70b-fast Paid

Llama 3.3 70B Fast — Groq free tier · Medium cost · list $0.59/$0.79 per 1M · free caps ~30 RPM / 1000 RPD / 12000 TPM / 100000 TPD

TEXT

Medium cost

Input: $0.59 per 1M tokens
Output: $0.79 per 1M tokens

bluesminds/ibm/granite-34b-code-instruct Paid

Granite 34B Code Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.80 per 1M tokens
Output: $0.64 per 1M tokens

bluesminds/meta/llama-3.3-70b-instruct Paid

Llama 3.3 70B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.80 per 1M tokens
Output: $0.64 per 1M tokens

bluesminds/meta/llama-4-maverick-17b-128e-instruct Paid

Llama 4 Maverick 17B — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.80 per 1M tokens
Output: $0.64 per 1M tokens

bluesminds/nvidia/llama-3.1-70b-instruct Paid

Llama 3.1 70B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.80 per 1M tokens
Output: $0.64 per 1M tokens

bluesminds/nvidia/llama-3.1-8b-instruct Paid

Llama 3.1 8B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.80 per 1M tokens
Output: $0.64 per 1M tokens

bluesminds/nvidia/llama-3.3-70b-instruct Paid

Llama 3.3 70B Instruct (NV) — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.80 per 1M tokens
Output: $0.64 per 1M tokens

bluesminds/nvidia/llama3-chatqa-1-8b-v1 Paid

Llama3 ChatQA 1 8B v1 — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.80 per 1M tokens
Output: $0.64 per 1M tokens

mistral/mistral-medium-api Paid

Mistral Medium — Very economical

TEXT IMAGE_GEN

Medium cost

Input: $0.71 per 1M tokens
Output: $0.90 per 1M tokens

bluesminds/mistralai/mistral-large-2411 Paid

Mistral Large 2411 — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.80 per 1M tokens
Output: $0.96 per 1M tokens

bluesminds/mistralai/mistral-small-2503 Paid

Mistral Small 2503 — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.80 per 1M tokens
Output: $0.96 per 1M tokens

bluesminds/qwen/qwen3-next-80b-a3b-instruct Paid

Qwen3 Next 80B A3B Instruct — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.80 per 1M tokens
Output: $1.28 per 1M tokens

hcnsec/auto Paid

Auto Router — HCNSEC (chat) · Very economical

TEXT REASONING TOOLS

Very economical

Input: $1.21 per 1M tokens
Output: $1.21 per 1M tokens

groq/qwen3.6-27b Paid Beta

Qwen3.6 27B — Groq free tier · Medium cost · list $0.6/$3 per 1M · free caps ~30 RPM / 1000 RPD / 8000 TPM / 200000 TPD

TEXT

Medium cost

Input: $0.60 per 1M tokens
Output: $3.00 per 1M tokens

bluesminds/openai/gpt-5-mini Paid

GPT-5 Mini — BluesMinds (chat) · default group

TEXT

Highest cost

Input: $0.50 per 1M tokens
Output: $4.00 per 1M tokens

hcnsec/qwen3.6-27b Paid

Qwen3.6 27B — HCNSEC (chat) · Economical

TEXT REASONING TOOLS

Economical

Input: $2.52 per 1M tokens
Output: $2.52 per 1M tokens

hcnsec/sensenova-u1-fast Paid

SenseNova U1 Fast — HCNSEC (chat) · Economical

TEXT

Economical

Input: $2.52 per 1M tokens
Output: $2.52 per 1M tokens

hcnsec/step-3.5-flash Paid

Step 3.5 Flash — HCNSEC (chat) · Economical

TEXT REASONING TOOLS

Economical

Input: $3.02 per 1M tokens
Output: $3.02 per 1M tokens

hcnsec/stepaudio-2.5-chat Paid

StepAudio 2.5 Chat — HCNSEC (chat) · Economical

TEXT

Economical

Input: $3.02 per 1M tokens
Output: $3.02 per 1M tokens

hcnsec/stepaudio-2.5-tts Paid

StepAudio 2.5 TTS — HCNSEC (chat) · Economical

Economical

Input: $3.02 per 1M tokens
Output: $3.02 per 1M tokens

hcnsec/sensenova-6.7-flash Paid

SenseNova 6.7 Flash — HCNSEC (chat) · Medium cost

TEXT

Medium cost

Input: $4.03 per 1M tokens
Output: $4.03 per 1M tokens

hcnsec/step-3.5-flash-2603 Paid

Step 3.5 Flash 2603 — HCNSEC (chat) · Medium cost

TEXT REASONING TOOLS

Medium cost

Input: $5.03 per 1M tokens
Output: $5.03 per 1M tokens

hcnsec/step-image-edit-2 Paid

HCNSEC · Step Image Edit 2 (explicit upstream id)

IMAGE_GEN

Same as hcnsec/image.

paid

Input: $22.15 per 1M tokens
Output: $22.15 per 1M tokens

Prices are informational reference rates. Actual usage is metered against your plan token quota.

FAQ

Quick answers before you integrate.

Is it compatible with the OpenAI SDK?

Yes. Change only base_url and your sk-sqr-... API key.

What are the rate limits?

Free plan: 200 requests / min, 80,000,000 tokens / day. See your dashboard for usage.

Does streaming work?

Yes. Send "stream": true for Server-Sent Events (SSE) passthrough.

Can I cancel a stream?

Close the client connection. Upstream billing may still apply per provider policy.

What data do you retain?

We log request metadata (tokens, model, latency) — not prompt or completion text.