Models available on velqa.dev — Prices in dirhams (MAD)
All the models below are reachable through velqa.dev's OpenAI-compatible API (https://api.velqa.dev/v1/chat/completions) and Anthropic-compatible API (https://api.velqa.dev/v1/messages). Recharge Boost prices are indicative, from the 2026-07 sizing (see your dashboard for current prices).
Model table
| Model ID | Source provider | Use case | Type | Indicative price (MAD/M input tokens) | Indicative price (MAD/M output tokens) |
|---|---|---|---|---|---|
glm-4.7-flash | Zhipu AI | Fast chat, everyday tasks — the most responsive | Fast/Chat | ~0.7 MAD | ~4.7 MAD |
deepseek-v4-flash | DeepSeek | Cheap high-volume, light code review | Fast/Chat | ~1.1 MAD | ~2.1 MAD |
hy3 | Tencent | Generalist and agentic, excellent perf/price ratio | Chat/Agentic | ~1.7 MAD | ~6.8 MAD |
glm-4.7 | Zhipu AI | Chat, agentic coding, good in FR / AR | Chat/Coding | ~4.7 MAD | ~21 MAD |
minimax-m3 | MiniMax | Agentic reasoning, best perf/price ratio | Coding | ~3.5 MAD | ~14 MAD |
mimo-v2.5 | Xiaomi | Omnimodal generalist (text, image, video, audio) | Chat/Agentic | ~4.7 MAD | ~24 MAD |
kimi-k2.6 | Moonshot AI | Coding agent, long sessions, reasoning | Coding | ~9 MAD | ~41 MAD |
glm-5.2 | Zhipu AI | Long autonomous tasks, 1M context | Coding | ~11 MAD | ~35 MAD |
deepseek-v4-pro | DeepSeek | Flagship heavy reasoning, 1M context | Premium | ~15 MAD | ~31 MAD |
qwen3.7-max | Alibaba | Premium reasoning, 1M context | Premium | ~15 MAD | ~44 MAD |
bge-m3 | BAAI | Multilingual embeddings FR / AR — RAG, semantic search | Embeddings | ~0.12 MAD | — |
qwen3-embedding-8b | Alibaba | High-quality embeddings — top multilingual MTEB, up to 4096 dims | Embeddings | ~0.12 MAD | — |
qwen3-reranker-8b | Alibaba | Multilingual reranking (FR / AR) — complements embeddings for RAG | Rerank | ~0.6 MAD | — |
whisper-large-v3 | OpenAI (via DeepInfra) | Multilingual audio transcription (FR / AR / darija), max 10 min | Audio (STT) | ~0.10 MAD / min | — |
kokoro-tts | hexgrad (via DeepInfra) | Text-to-speech, 8 languages | Audio (TTS) | ~20 MAD / M chars | — |
flux-2-klein-4b | Black Forest Labs (via DeepInfra) | Text-to-image generation, max 4/request, 1024×1024 max | Image | ~0.30 MAD / image | — |
Prices are converted at the current exchange rate and displayed as rounded dirhams in the dashboard. The applied rate is updated daily.
Availability per plan
| Model | Starter (99 MAD) | Dev (199 MAD) | Pro (399 MAD) | Recharge Boost |
|---|---|---|---|---|
glm-4.7-flash | Yes | Yes | Yes | Yes |
deepseek-v4-flash | Yes | Yes | Yes | Yes |
hy3 | Yes | Yes | Yes | Yes |
glm-4.7 | Yes | Yes | Yes | Yes |
minimax-m3 | No | Yes | Yes | Yes |
mimo-v2.5 | No | Yes | Yes | Yes |
kimi-k2.6 | No | Yes | Yes | Yes |
glm-5.2 | No | Yes | Yes | Yes |
deepseek-v4-pro | No | No | Yes | Yes |
qwen3.7-max | No | No | Yes | Yes |
bge-m3 | Yes | Yes | Yes | Yes |
qwen3-embedding-8b | Yes | Yes | Yes | Yes |
qwen3-reranker-8b | Yes | Yes | Yes | Yes |
whisper-large-v3 | No | No | No | Yes |
kokoro-tts | No | No | No | Yes |
flux-2-klein-4b | No | No | No | Yes |
Notes
- Model identifiers (
model_id) are stable — these are the ones to use in your tool configs. - The Starter plan is designed for students and exploration; advanced coding models require the Dev plan at minimum.
- Recharge Boost mode (pay-as-you-go) gives access to every model from a prepaid credit balance, with no subscription.
- MAD/M token prices will be updated whenever the source providers change their pricing. Follow @velqa_dev for announcements.