Fireworks AI · none caching
Snorkel Mistral PairRM DPO
Snorkel Mistral PairRM DPO on Zumik: live pricing, context, and caching, routable by id or alias through one OpenAI-compatible endpoint.
Specifications
At a glance.
| Provider | Fireworks AI |
| Family | mistral |
| Released | — |
| License | Open weights |
| Context window | 33K tokens |
| Max output | — |
| Parameters | 7B |
| Modalities | text |
| Tool calling | No |
| Reasoning mode | No |
| Caching | none |
| Batch discount | No batch tier |
Measured by Zumik
What reuse looks like here.
Pricing, context, and capabilities for Snorkel Mistral PairRM DPO are live, but it is outside the flagship set Zumik benchmarks in depth, so measured reuse, capture, and warm TTFT are not shown yet. Run a workload estimate or route it by id to start collecting traces.
Call it
Same OpenAI client, this model.
from openai import OpenAI
client = OpenAI(base_url="https://api.zumik.ai/v1", api_key="zk_live_...")
r = client.responses.create(
model="snorkel-mistral-7b-pairrm-dpo",
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reuseFrequently asked
Snorkel Mistral PairRM DPO, answered.
How much does Snorkel Mistral PairRM DPO cost?
Snorkel Mistral PairRM DPO is an open-weights model routed through Fireworks AI. It is priced on the host's serverless size tier rather than a single published per-token list price, so it shows "—" here until profiled.
What is Snorkel Mistral PairRM DPO's context window?
Snorkel Mistral PairRM DPO supports a 33K-token context window.
Does Snorkel Mistral PairRM DPO support prompt caching?
Yes. Fireworks AI uses Automatic prompt caching (serverless and dedicated) caching. In the Zumik corpus, Snorkel Mistral PairRM DPO shows a median cache capture of 76% on agent workloads.
Run Snorkel Mistral PairRM DPO with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.