Fireworks AI · none caching
Code Llama 70B Instruct
Code Llama 70B Instruct 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 | llama |
| Released | — |
| License | Open weights |
| Context window | 4K tokens |
| Max output | — |
| Parameters | 69B |
| 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 Code Llama 70B Instruct 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="code-llama-70b-instruct",
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reuseFrequently asked
Code Llama 70B Instruct, answered.
How much does Code Llama 70B Instruct cost?
Code Llama 70B Instruct 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 Code Llama 70B Instruct's context window?
Code Llama 70B Instruct supports a 4K-token context window.
Does Code Llama 70B Instruct support prompt caching?
Yes. Fireworks AI uses Automatic prompt caching (serverless and dedicated) caching. In the Zumik corpus, Code Llama 70B Instruct shows a median cache capture of 76% on agent workloads.
Run Code Llama 70B Instruct with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.