Pricing, context window, capabilities, and release date — pulled from each provider's public docs. Both are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.
Both models stream in parallel through your own AIgateway key. Tokens, latency, and cost update as they arrive.
| Openhermes-2.5-Mistral-7b-Awq hf/thebloke/openhermes-2.5-mistral-7b-awq | Voxtral Mini Transcribe Realtime mistral/voxtral-mini-transcribe-realtime-26-02 | |
|---|---|---|
| Provider | Hugging Face | Mistral |
| Family | Mistral | Mistral |
| Modality | text | audio-stt |
| Context window | 4,096 tok | — |
| Max output | 4,096 tok | — |
| Released | 2023-11-02 | 2026-02-01 |
| Input price | $0.050 /1M | $0.0080 /min |
| Output price | $0.100 /1M | — |
| Cache read | — | — |
| Tools | — | — |
| Streaming | yes | — |
| Vision | — | — |
| JSON mode | — | — |
| Reasoning | — | — |
| Prompt caching | — | — |
OpenHermes 2.5 Mistral 7B is a state of the art Mistral Fine-tune, a continuation of OpenHermes 2 model, which trained on additional code datasets.
Voxtral Mini Transcribe Realtime (Feb 2026) — streaming ASR.
# pip install aigateway-py openai
# aigateway-py: sub-accounts, evals, replays, jobs, webhook verify.
# openai SDK: chat/embeddings/images/audio — drop-in compat per our SDK's own guidance.
from openai import OpenAI
client = OpenAI(
base_url="https://api.aigateway.sh/v1",
api_key="sk-aig-...",
)
# Try Openhermes-2.5-Mistral-7b-Awq
client.chat.completions.create(
model="hf/thebloke/openhermes-2.5-mistral-7b-awq",
messages=[{"role":"user","content":"hello"}],
)
# Try Voxtral Mini Transcribe Realtime — same client, same key
client.chat.completions.create(
model="mistral/voxtral-mini-transcribe-realtime-26-02",
messages=[{"role":"user","content":"hello"}],
)