Models and pricing
| Model ID | Input / 1M tokens | Output / 1M tokens | Cache read / 1M tokens | Cache write / 1M tokens |
|---|---|---|---|---|
| decision-models/baseten-elephant-9b-latest | $0.035 | — | — | — |
| decision-models/baseten-joey-2b-latest | $0.01 | — | — | — |
| decision-models/baseten-mammoth-27b-latest | $0.1 | — | — | — |
| deepseek-ai/DeepSeek-V4-Flash-0731 | $0.13 | $0.26 | $0.028 | — |
| deepseek-ai/DeepSeek-V4-Pro-0813 | $1.32 | $3.96 | $0.132 | — |
| deepseek-ai/DeepSeek-V4.1-Flash | $0.3 | $1.2 | $0.007 | — |
| deepseek-ai/DeepSeek-V4.1-Flash-1017 | $0.3 | $1.2 | $0.007 | — |
| deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast | $0.6 | $2.4 | $0.014 | — |
| deepseek-ai/DeepSeek-V4.1-Flash-Fast | $0.6 | $2.4 | $0.014 | — |
| meta-models/muse-spark-open | $1.25 | $4.25 | $0.15 | — |
| moonshotai/Kimi-K3 | $3 | $15 | $0.3 | — |
| nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.6 | $2.4 | $0.12 | — |
| nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B | $0.2 | $0.5 | $0.04 | — |
| openai/gpt-oss-120b | $0.1 | $0.5 | $0.1 | — |
| reflection/Beam-1.0 | $0.4 | $1.2 | $0.04 | — |
| zai-org/GLM-5.2 | $1.4 | $4.4 | $0.14 | — |
| zai-org/GLM-5.2-Fast | $2.1 | $6.6 | $0.21 | — |
| zai-org/GLM-5.3 | $1.4 | $4.4 | $0.14 | — |
| zai-org/GLM-5.3-Fast | $2.1 | $6.6 | $0.21 | — |
| zai-org/GLM-5.3-Flash | $0.15 | $0.5 | $0.03 | — |
curl --request GET \
--url 'https://api.narev.ai/v1/prices?provider_id=baseten&model_id=decision-models%2Fbaseten-elephant-9b-latest'
{
"model_id": "decision-models/baseten-elephant-9b-latest",
"provider_id": "baseten",
"pricing": {
"prompt": 3.5e-8,
"completion": 0,
"discount": 0,
"request": 0,
"web_search": 0,
"input_cache_read": 0,
"input_cache_write": 0,
"image": 0,
"image_output": 0,
"audio": 0,
"audio_output": 0,
"input_audio_cache": 0,
"internal_reasoning": 0
}
}
Provider details
| Property | Value |
|---|---|
| Headquarters | US |
| API base URL | https://inference.baseten.co/v1 |
| SDK package | @ai-sdk/openai-compatible |
| Environment variables | [“BASETEN_API_KEY”] |
Data policies
| Policy | Value |
|---|---|
| Uses data for training | No |
| Retains prompts | No |
| Can publish data | No |