OpenWaya model registry
Choose with the full picture.
Compare model capability, context, managed availability, and localized input and output pricing before you integrate.
249 models available now11 provider integrationsContinuously monitoredOne compatible API
Search and compare
Model catalog
Registry data · updated Nov 3, 2026
21–40 of 174 modelsPrices shown in USD / 1M tokens
| Model | Capabilities | Context | Input | Output |
|---|---|---|---|---|
| Llama-4-Maverick-17B-128E-Instruct-FP8meta-llama/llama-4-maverick-17b-128e-instruct-fp8Meta | chatstreamingtext_generation | 1.048576M | $ 0.27 | $ 0.85 |
| MiniMax: MiniMax-01minimax/minimax-01MiniMax | chatstreamingtext_generation | 1.000192M | $ 0.20 | $ 1.10 |
| Mistral-Nemo-Instruct-2407mistralai/mistral-nemo-instruct-2407Mistral AI | chatstreamingtext_generation | 131K | $ 0.03 | $ 0.03 |
| NVIDIA-Nemotron-3.5-Super-VLnvidia/nvidia-nemotron-3.5-super-vlNVIDIA | chatstreamingtext_generation | 262K | $ 0.15 | $ 0.50 |
| Qwen2.5 72B Instructqwen/qwen2.5-72b-instructQwen | chatstreamingtext_generation | 33K | $ 1.20 | $ 1.20 |
| Claude Opus 4.7anthropic/claude-opus-4-7Anthropic | chatreasoningstreamingtext_generation | 1M | $ 5.00 | $ 25.00 |
| gemini-3-flashgoogle/gemini-3-flashGoogle | chatreasoningstreamingtext_generation | 256K | $ 0.33 | $ 1.95 |
| Inkling Smallthinking-machines/inkling-smallThinking Machines Lab | chatstreamingstructuredOutputstext_generationtoolCalling | 524K | $ 0.45 | $ 1.20 |
| Cohere: Command R7B (12-2024)cohere/command-r7b-12-2024Cohere | chatjsonModeseedstreamingstructuredOutputstext_generation | 128K | $ 0.04 | $ 0.15 |
| grok-4.5x-ai/grok-4.5xAI | chatjsonModereasoningseedstreamingstructuredOutputstext_generationtoolCalling | 500K | $ 2.60 | $ 7.80 |
| DeepSeek R1 Distill Qwen 14Bdeepseek-ai/deepseek-r1-distill-qwen-14bDeepSeek | chatstreamingtext_generation | 131K | $ 1.60 | $ 1.60 |
| GLM 4.7 FP8z-ai/glm-4.7Z.ai | chatstreamingtext_generation | 203K | $ 0.60 | $ 2.20 |
| gpt-5.6-terraopenai/gpt-5-6-terraOpenAI | chatstreamingtext_generation | 4K | $ 2.00 | $ 2.50 |
| Meta Llama 3.1 8B Instruct Turbometa-llama/meta-llama-3.1-8b-instruct-turboMeta | chatstreamingtext_generation | 131K | $ 0.18 | $ 0.18 |
| Mistral-Small-3.2-24B-Instruct-2506mistralai/mistral-small-3.2-24b-instruct-2506Mistral AI | chatstreamingtext_generation | 128K | $ 0.08 | $ 0.20 |
| Qwen2.5-VL (72B) Instructqwen/qwen2.5-vl-72b-instructQwen | chatstreamingtext_generation | 33K | $ 1.95 | $ 8.00 |
| Kimi-K2-Instructmoonshotai/kimi-k2-instructMoonshot AI | chatstreamingtext_generationtoolCalling | 131K | $ 0.57 | $ 2.30 |
| Claude Opus 4.8anthropic/claude-opus-4-8Anthropic | chatreasoningstreamingtext_generation | 1M | $ 5.00 | $ 25.00 |
| Minimax M1 80Kminimax/minimax-m1-80kMiniMax | chatstreamingtext_generationtoolCalling | 1M | $ 0.55 | $ 2.20 |
| gemini-3.1-progoogle/gemini-3.1-proGoogle | chatreasoningstreamingtext_generation | 1M | $ 3.15 | $ 14.16 |
Use any model
One request shape across the catalog.
Choose a model returned by GET /v1/models. OpenWaya then selects its best eligible serving route using availability, latency, throughput, cost, and policy evidence.
const response = await client.chat.completions.create({
model: "YOUR_MODEL_ID",
messages: [{ role: "user", content: "Hello" }],
});