15 models · OpenAI- & Anthropic-compatible
Models & API pricing
Run any of these on Ambient's verified inference through a drop-in OpenAI- and Anthropic-compatible API. Prices are per million tokens.
Sort
| Model | Input | Output | Context | Capabilities |
|---|---|---|---|---|
Kimi K2.7 Code (INT4)Featured moonshotai/kimi-k2.7-code | $0.72 / M | $3.49 / M | 256K | VisionReasoningToolsStructured |
GLM 5.2 (FP8)Featured ambient/large | $1.40 / M | $4.40 / M | 198K | ReasoningToolsStructured |
gpt-oss-20b openai/gpt-oss-20b | $0.03 / M | $0.14 / M | 128K | ReasoningToolsStructured |
Nemotron 3 Nano 30B A3B (FP4) nvidia/nemotron-3-nano-30b-a3b | $0.05 / M | $0.20 / M | 256K | ReasoningTools |
Qwen3 Coder 30B A3B Instruct qwen/qwen3-coder-30b-a3b-instruct | $0.07 / M | $0.27 / M | 156K | ToolsStructured |
Qwen3 Next 80B A3B Instruct qwen/qwen3-next-80b-a3b-instruct | $0.09 / M | $1.10 / M | 256K | ToolsStructured |
Gemma 4 26B A4B google/gemma-4-26b-a4b-it | $0.10 / M | $0.30 / M | 256K | VisionReasoningToolsStructured |
GLM 4.5 Air z-ai/glm-4.5-air | $0.13 / M | $0.85 / M | 128K | ReasoningToolsStructured |
Qwen3.5 35B A3B qwen/qwen3.5-35b-a3b | $0.14 / M | $1.00 / M | 256K | VisionReasoningToolsStructured |
gpt-oss-120b openai/gpt-oss-120b | $0.15 / M | $0.60 / M | 128K | ReasoningToolsStructured |
Qwen3.6 35B A3B qwen/qwen3.6-35b-a3b | $0.15 / M | $1.00 / M | 256K | VisionReasoningToolsStructured |
Gemma 4 31B google/gemma-4-31b-it | $0.20 / M | $0.80 / M | 64K | VisionReasoningToolsStructured |
Qwen3.6 27B qwen/qwen3.6-27b | $0.32 / M | $3.20 / M | 256K | VisionReasoningToolsStructured |
Kimi K2.5 moonshotai/kimi-k2.5 | $0.40 / M | $1.98 / M | 256K | VisionReasoningToolsStructured |
Kimi K2.6 (INT4) moonshotai/kimi-k2.6 | $0.55 / M | $3.20 / M | 256K | VisionReasoningToolsStructured |
Ready to integrate?
Get an API key and start building. Pay per token, no upfront setup.
See pricing & sign up