Ambient
Inference provider
- Endpoints
- 15
- Models
- 15
Models served
15 shown
| Model | Creator | Type | In $/1M | Out $/1M | Context | Max output | Tools | Region |
|---|---|---|---|---|---|---|---|---|
| Ambient Small ambient/small | ambient | Chat | $0.001 | $0.001 | 101K | 101K | Region not stated | |
| DeepSeek V4 Flash deepseek/deepseek-v4-flash | DeepSeek | Chat | $0.14 | $0.28 | 1.05M | 1.05M | Region not stated | |
| DeepSeek V4 Flash Latest deepseek/deepseek-v4-flash-0731 | DeepSeek | Chat | $0.08 | $0.18 | 1.05M | 1.05M | Region not stated | |
| GLM-5.1 zai-org/GLM-5.1-FP8 | Z.ai (Zhipu AI) | Chat | $1.40 | $4.40 | 203K | 131K | Region not stated | |
| GLM-5.2 ambient/large | Z.ai (Zhipu AI) | Chat | $0.60 | $2.00 | 203K | 203K | Region not stated | |
| Kimi K2.6 moonshotai/kimi-k2.6 | Moonshot AI | Chat | $0.95 | $4.00 | 262K | 262K | Region not stated | |
| Kimi K2.7 Code HighSpeed moonshotai/kimi-k2.7-code | Moonshot AI | Chat | $0.69 | $3.49 | 262K | 262K | Region not stated | |
| MiMo-V2.5 xiaomi/mimo-v2.5 | Xiaomi | Chat | $0.405.19× median | $2.00 | 1.05M | 131K | Region not stated | |
| MiniMax-M3 minimax/minimax-m3 | MiniMax | Chat | $0.23 | $0.96 | 262K | 262K | Region not stated | |
| Qwen3 30B A3B Instruct 2507 qwen/qwen3-30b-a3b-instruct-2507 | Alibaba (Qwen) | Chat | $0.09 | $0.30 | 131K | 32.8K | Region not stated | |
| Qwen3.6 27B qwen/qwen3.6-27b | Alibaba (Qwen) | Chat | $0.32 | $3.20 | 32.8K | 8.2K | Region not stated | |
| Qwen3.6 35B-A3B qwen/qwen3.6-35b-a3b | Alibaba (Qwen) | Chat | $0.15 | $1.00 | 262K | 262K | Region not stated | |
| Qwen3.8-27B qwen/qwen3.8-27b | Alibaba (Qwen) | Chat | $0.32 | $3.20 | 32.8K | 8.2K | Region not stated | |
| qwen3.8-27b-4q unsloth/qwen3.8-27b-gguf | Unsloth | Chat | $0.001 | $0.001 | 101K | 101K | Region not stated | |
| Step 3.7 Flash stepfun/step-3.7-flash | StepFun | Chat | $0.19 | $1.14 | 262K | 262K | Region not stated |
One row per model and variant. Dated pins appear on the model page, not as separate rows. Prices are indicative; verify with the provider.