Fireworks AI
EfficientAUTO PROFILE

Phind-CodeLlama-34B (fw)

Code

Phind-CodeLlama-34B (fw) is a code-specialist variant tuned for completion, refactoring, and test generation across major programming languages. Available via Fireworks AI. 16,000-token context. Efficient pricing.

Phind-CodeLlama-34B (fw) is a efficient AI model from Fireworks AI. It costs $0.8000 per million input tokens and $0.8000 per million output tokens (blended $0.8000/M), with a 16,000-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.8000/M
per million input tokens
OUTPUT
$0.8000/M
per million output tokens
BLENDED 70/30
$0.8000/M
unchanged since 3 May
CONTEXT
16,000
tokens

Hand-maintained from Fireworks AI's published pricing; no check date on record.

What it is good at
  • Code completion across languages
  • Multi-file refactoring
  • Test generation
  • Debugging from stack traces
Typical use cases
  • Pair-programming copilots
  • Codebase refactors
  • Code review automation
  • Repo-scale agents

Benchmarks

vs. best public score
Scores inherited from CodeLlama 34B — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
HumanEval41.5%
Python function synthesis from docstrings. Source: Meta (self-reported), HumanEval, read 2026-11-10.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

More from Fireworks AI

See all 7 →

Frequently asked questions

How much does Phind-CodeLlama-34B (fw) cost?

Phind-CodeLlama-34B (fw) costs $0.8000 per million input tokens and $0.8000 per million output tokens, for a blended reference rate of $0.8000 per million tokens.

What is Phind-CodeLlama-34B (fw)'s context window?

Phind-CodeLlama-34B (fw) supports up to 16,000 tokens of context in a single request.

What is Phind-CodeLlama-34B (fw) best for?

Phind-CodeLlama-34B (fw) is well suited to Code completion across languages, Multi-file refactoring and Test generation.

Who makes Phind-CodeLlama-34B (fw)?

Phind-CodeLlama-34B (fw) is developed and served by Fireworks AI.

Terms used on this page