News
Eleven Labs AI Models " Pricing & Playground
4+ hour, 33+ min ago (291+ words) Run every Eleven Labs model through a single REST API on Wave Speed AI " 11 total (9 audio models, 2 other models). Transparent per-output pricing, one API key, no per-provider setup. Open any model below to see its live pricing, input schema, code…...
Pruna Ai AI Models " Pricing & Playground
4+ hour, 31+ min ago (317+ words) Run every Pruna Ai model through a single REST API on Wave Speed AI " 10 total (1 text-to-image, 1 image editing, 1 text-to-video, 1 image-to-video, 1 digital human, 1 upscalers, 2 lora models, 2 other models). Transparent per-output pricing, one API key, no per-provider setup. Open any model below…...
LLM API Pricing & Performance | Wave Speed AI
5+ day, 7+ hour ago (200+ words) Compare pricing, speed, and performance for GPT-5. 5, Claude Opus 4. 7, Gemini 3, Qwen 3, Deep Seek R1, Llama 4, Grok 4, and more. Unified Open AI-compatible API with no cold starts and transparent per-token pricing. GPT, Claude, Gemini, Qwen, Deep Seek, Llama, Grok, Mistral " all in…...
GPT-3. 5 Turbo | Open AI Fast & Affordable LLM API | Wave Speed AI
5+ day, 8+ hour ago (127+ words) 16, 385 context " $0. 50/M input tokens " $1. 50/M output tokens No upfront costs, pay only for what you use Use the following code examples to integrate with our API: GPT-3. 5 Turbo is Open AI's fastest model. It can understand and generate natural language…...
LLM Models - API Pricing & Comparison
5+ day, 22+ hour ago (200+ words) Compare pricing, speed, and performance for GPT-5. 5, Claude Opus 4. 7, Gemini 3, Qwen 3, Deep Seek R1, Llama 4, Grok 4, and more. Unified Open AI-compatible API with no cold starts and transparent per-token pricing. GPT, Claude, Gemini, Qwen, Deep Seek, Llama, Grok, Mistral " all in…...
GLM-5 | Z. ai Open-Source Flagship LLM API | Wave Speed AI
1+ week, 11+ hour ago (132+ words) GLM-5 | Z. ai Open-Source Flagship LLM API Wave Speed AI 80, 000 context " $0. 72/M input tokens " $2. 30/M output tokens GLM-5 is Z. ai's flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance…...
Hi Dream-O1-Image-Dev: The 8 B Pixel-Native Model That Beat 56 B FLUX. 2 - Wave Speed Blog
1+ week, 5+ day ago (737+ words) Hi Dream-O1-Image-Dev is an 8 B distilled image model that drops the VAE and the external text encoder, generates 2 K natively, and outscores models 7x its size on Gen Eval, DPG, and HPSv3. Two checkpoints shipped: the full Hi Dream-O1-Image (50 steps,…...
Microsoft Phi-4 | Microsoft 14 B Reasoning LLM API | Wave Speed AI
2+ week, 8+ hour ago (94+ words) 16, 384 context " $0. 07/M input tokens " $0. 14/M output tokens No upfront costs, pay only for what you use Use the following code examples to integrate with our API: Access Phi 4 through our unified API " Open AI-compatible, no cold starts, transparent pricing. Pricing…...
Qwen3 Coder | Alibaba Agentic Coding LLM API | Wave Speed AI
2+ week, 1+ day ago (140+ words) 262, 144 context " $0. 22/M input tokens " $1. 00/M output tokens Keine Vorabkosten, zahlen Sie nur, was Sie nutzen Verwenden Sie die folgenden Codebeispiele zur Integration mit unserer API: Qwen3-Coder-480 B-A35 B-Instruct is a Mixture-of-Experts (Mo E) code generation model developed by the Qwen team. It…...
Llama Guard 3 8b | Meta LLM API | Wave Speed AI
2+ week, 22+ hour ago (98+ words) 131, 072 context " $0. 02/M input tokens " $0. 06/M output tokens No upfront costs, pay only for what you use Use the following code examples to integrate with our API: Access Llama Guard 3 8b through our unified API " Open AI-compatible, no cold starts, transparent pricing....