DeepInfra: API key and base URL
Low-cost open-model inference. Bring your own key; nothing is billed by us.
What the harness already knows
| Provider id | deepinfra |
| Base URL | https://api.deepinfra.com/v1/openai |
| Protocol | OpenAI-compatible chat completions |
| API key | DEEPINFRA_API_KEY |
| Model discovery | Yes — the model list is asked of the endpoint rather than shipped. |
Connecting it
The endpoint above is built in, so there is nothing to configure. Put the key in the environment and the provider appears in the model picker:
export DEEPINFRA_API_KEY="..."Models on DeepInfra
The newest models DeepInfra serves that can call tools, from the models.dev snapshot OHarness ships. The harness also asks the endpoint for its live list, so a model released after this snapshot still appears in the picker.
| Model id | Context / output | $/M in / cached / out | Reasoning |
|---|---|---|---|
deepseek-ai/DeepSeek-V4.1-Flash | 1.05M / 384K | 0.2 / 0.006 / 0.6 | Yes |
Qwen/Qwen3.8-Flash | 1M / 131K | 0.113 / 0.0141 / 0.382 | No |
zai-org/GLM-5.3-Flash | 1.05M / 131K | 0.15 / 0.03 / 0.5 | Yes |
deepseek-ai/DeepSeek-V4-Flash-Vision-Exp | 1.05M / 384K | 0.44 / 0.014 / 1.32 | Yes |
Qwen/Qwen3.8-27B | 262K / 33K | 0.2 / 0.05 / 2.5 | Yes |
zai-org/GLM-5.3 | 1.05M / 131K | 1.2 / 0.2 / 4 | Yes |
Qwen/Qwen3.8-2.4T-A95B | 262K / 131K | 2 / 0.2 / 6 | Yes |
deepseek-ai/DeepSeek-V4-Pro-0813 | 1.05M / 384K | 1.3 / 0.1 / 2.6 | Yes |
Qwen/Qwen3.8-Max | 256K / 131K | 1.65 / 0.206 / 4.951 | No |
deepseek-ai/DeepSeek-V4-Flash-0731 | 1.05M / 384K | 0.06 / 0.015 / 0.18 | Yes |
List prices in USD per million tokens, read from models.dev on 2026-09-19. DeepInfra changes its prices and models; its own pricing page is the authority. Start a session on the newest:
oharness -m deepinfra/deepseek-ai/DeepSeek-V4.1-FlashPointing it somewhere else
A regional host, a gateway, or a server of your own. Overrides in ~/.oharness/config.json are field level, so changing the endpoint does not mean restating the rest of the provider — this is the whole block, shown holding the default so the shape is clear:
{
"providers": {
"deepinfra": {
"baseUrl": "https://api.deepinfra.com/v1/openai"
}
}
}What you get either way
The same agent loop, the same tools, the same MCP servers and the same permission rules, whichever provider is underneath — and switching between them mid-session converts nothing, because history is never stored in a vendor’s shape. What an agent harness is covers why that is the hard part, and the providers reference covers the catalogue itself.