Fireworks AI · none caching
Phind CodeLlama 34B v2
Phind CodeLlama 34B v2 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 | 16K tokens |
| Max output | — |
| Parameters | 34B |
| 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 Phind CodeLlama 34B v2 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="phind-code-llama-34b-v2",
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reuseFrequently asked
Phind CodeLlama 34B v2, answered.
How much does Phind CodeLlama 34B v2 cost?
Phind CodeLlama 34B v2 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 Phind CodeLlama 34B v2's context window?
Phind CodeLlama 34B v2 supports a 16K-token context window.
Does Phind CodeLlama 34B v2 support prompt caching?
Yes. Fireworks AI uses Automatic prompt caching (serverless and dedicated) caching. In the Zumik corpus, Phind CodeLlama 34B v2 shows a median cache capture of 75% on agent workloads.
Run Phind CodeLlama 34B v2 with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.