Neuralwatt
A hosted service with its own key and prices. This page lists the addresses it answers, the facts its documentation states, and the setup of each harness.
Addresses and facts
- OpenAI Chat Completions:
https://api.neuralwatt.com/v1models.dev, read
- Authentication
- Authorization: Bearer, with the key in
NEURALWATT_API_KEYmodels.dev, read - Structured output
- Unknown
- Tool calling
- 29 of 29 listed models The share of this provider's models that models.dev records with tool calling. models.dev, read
- Rate limits
- Unknown
- Prices
- Unknown
- Data retention
- Unknown
- Documentation
- Read the page models.dev, read
- Output limits Baltor recorded
- Unknown
Harness setup
Replace deepseek-v4-flash with the model you want.
OpenCode
Put this in opencode.json in your project folder:
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"neuralwatt": {
"npm": "@ai-sdk/openai-compatible",
"name": "Neuralwatt",
"options": {
"baseURL": "https://api.neuralwatt.com/v1",
"apiKey": "{env:NEURALWATT_API_KEY}"
},
"models": {
"deepseek-v4-flash": {
"name": "deepseek-v4-flash"
}
}
}
}
}- OpenCode reads any OpenAI-compatible address through the @ai-sdk/openai-compatible package, and an address that speaks the Responses API through @ai-sdk/openai.
From OpenCode documentation, read .
Pi
Put this in ~/.pi/agent/models.json:
{
"providers": {
"neuralwatt": {
"baseUrl": "https://api.neuralwatt.com/v1",
"api": "openai-completions",
"apiKey": "$NEURALWATT_API_KEY",
"models": [
{
"id": "deepseek-v4-flash"
}
]
}
}
}- The apiKey field can name an environment variable as $NAME.
From Pi documentation, read .
Codex
Codex speaks only the Responses API, and Neuralwatt documents no Responses address. A gateway that offers one can sit in between.
- Codex speaks the Responses API only: responses is the one supported wire API of a custom provider. Ollama and LM Studio are built in and start with --oss.
From Codex documentation, read .
Claude Code
Claude Code sends Anthropic Messages requests, and Neuralwatt documents no such address. A gateway that translates to that API can sit in between.
- Claude Code sends Anthropic Messages requests to ANTHROPIC_BASE_URL. Anthropic says it does not support routing Claude Code to models other than Claude through any gateway, so some features may not work with another model.
From Claude Code documentation, read .
Models it lists
Prices in US dollars per million tokens, input and output, as models.dev, read records them.
| Model | Input | Output | Context | As of |
|---|---|---|---|---|
DeepSeek V4 Flash deepseek-v4-flash | 0.140 USD | 0.280 USD | 1,048,560 | older than 30 days |
DeepSeek V4 Flash Flex deepseek-v4-flash-flex | 0.091 USD | 0.182 USD | 1,048,560 | older than 30 days |
DeepSeek V4 Flash (Speed) deepseek-v4-flash-speed | 0.140 USD | 0.280 USD | 1,048,560 | older than 30 days |
DeepSeek V4 Pro deepseek-v4-pro | 1.00 USD | 3.00 USD | 1,048,560 | older than 30 days |
DeepSeek V4.1 Flash deepseek-v4.1-flash | 0.150 USD | 0.600 USD | 1,048,560 | |
DeepSeek V4.1 Flash Flex deepseek-v4.1-flash-flex | 0.098 USD | 0.390 USD | 1,048,560 | |
Gemma 4 31B gemma-4-31b | 0.144 USD | 0.420 USD | 262,128 | older than 30 days |
GLM 5.2 glm-5.2 | 1.45 USD | 4.50 USD | 1,048,560 | older than 30 days |
GLM 5.2 Fast glm-5.2-fast | 1.45 USD | 4.50 USD | 1,048,560 | older than 30 days |
GLM 5.2 Flex glm-5.2-flex | 0.943 USD | 2.92 USD | 1,048,560 | older than 30 days |
GLM 5.2 Short glm-5.2-short | 1.45 USD | 4.50 USD | 199,984 | older than 30 days |
GLM 5.2 Short Fast glm-5.2-short-fast | 1.45 USD | 4.50 USD | 199,984 | older than 30 days |
GLM 5.2 Short Fast Flex glm-5.2-short-fast-flex | 0.943 USD | 2.92 USD | 199,984 | older than 30 days |
GLM 5.2 Short Flex glm-5.2-short-flex | 0.943 USD | 2.92 USD | 199,984 | older than 30 days |
GLM 5.3 glm-5.3 | 1.45 USD | 4.50 USD | 1,048,560 | older than 30 days |
GLM-5.3 Flash glm-5.3-flash | 0.150 USD | 0.500 USD | 1,048,560 | |
GLM-5.3 Flash Flex glm-5.3-flash-flex | 0.098 USD | 0.325 USD | 1,048,560 | |
GLM 5.3 Flex glm-5.3-flex | 0.943 USD | 2.92 USD | 1,048,560 | older than 30 days |
Kimi K2.7 Code kimi-k2.7-code | 0.950 USD | 4.00 USD | 262,128 | older than 30 days |
Kimi K2.7 Code Fast kimi-k2.7-code-fast | 0.950 USD | 4.00 USD | 262,128 | older than 30 days |
Kimi K2.7 Code Flex kimi-k2.7-code-flex | 0.618 USD | 2.60 USD | 262,128 | older than 30 days |
Kimi K3 kimi-k3 | 3.00 USD | 15.00 USD | 1,048,560 | older than 30 days |
Kimi K3 Fast kimi-k3-fast | 3.00 USD | 15.00 USD | 1,048,560 | older than 30 days |
Kimi K3 Flex kimi-k3-flex | 1.95 USD | 9.75 USD | 1,048,560 | older than 30 days |
Qwen3.8 27B qwen-3.8-27b | 0.450 USD | 3.20 USD | 262,128 | older than 30 days |
Qwen3.8 27B Flex qwen-3.8-27b-flex | 0.292 USD | 2.08 USD | 262,128 | older than 30 days |
Qwen3.6 35B qwen3.6-35b | 0.290 USD | 1.15 USD | 131,056 | older than 30 days |
Qwen3.6 35B Fast qwen3.6-35b-fast | 0.290 USD | 1.15 USD | 131,056 | older than 30 days |
Qwen3.6 35B Flex qwen3.6-35b-flex | 0.189 USD | 0.748 USD | 131,056 | older than 30 days |
Sources of this page
- models.dev/api.json, read
Paid links
No link in this directory is a paid link or an ad, and no listing is paid for. The order and the contents of every list come from the sources named on this page.