Claude Fable 5$22.000/MClaude Opus 5$11.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.6 Sol$12.500/MGPT-5.6 Terra$5.000/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MClaude Fable 5$22.000/MClaude Opus 5$11.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.6 Sol$12.500/MGPT-5.6 Terra$5.000/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/M
Tokenando
BETA
Subscribe
← Back to Index·All Anyscale models
Anyscale
AnyscaleEfficient

CodeLlama 70B (Anyscale)

Code

Code-tuned Llama 2 at 70B. Largely superseded by Qwen2.5-Coder and DeepSeek-Coder, but still hosted for legacy code workflows.

CodeLlama 70B (Anyscale) is a efficient AI model from Anyscale. It costs $1.000 per million input tokens and $1.000 per million output tokens (blended $1.000/M), with a 16,000-token context window.

Profile inherited from upstream CodeLlama 70B ↗ — this is a hosted variant of the same open-weights model.

Released Jan 2024Modalities textOfficial model page ↗Provider pricing ↗API docs ↗Compare with another model →Estimate monthly cost →
INPUT
$1.000/M
per million input tokens
OUTPUT
$1.000/M
per million output tokens
BLENDED 70/30
$1.000/M
unchanged since 3 May
default reference rate · how it is calculated →
CONTEXT
16,000
tokens
What it is good at
  • Open weights
  • Code-tuned
  • Wide ecosystem
Typical use cases
  • Legacy code-completion backends

Benchmarks

vs. best public score
Scores inherited from CodeLlama 70B — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
HumanEval75%
Python function synthesis from docstrings.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

More from Anyscale

See all 4 →
Llama 3.1 70B (Anyscale)
Managed · 128,000 ctx
in $1.000/Mout $1.000/M
Mistral 7B (Anyscale)
Nano · 32,000 ctx
in $0.150/Mout $0.150/M
Mixtral 8x7B (Anyscale)
MoE · 32,000 ctx
in $0.500/Mout $0.500/M

Frequently asked questions

How much does CodeLlama 70B (Anyscale) cost?

CodeLlama 70B (Anyscale) costs $1.000 per million input tokens and $1.000 per million output tokens, for a blended reference rate of $1.000 per million tokens.

What is CodeLlama 70B (Anyscale)'s context window?

CodeLlama 70B (Anyscale) supports up to 16,000 tokens of context in a single request.

What is CodeLlama 70B (Anyscale) best for?

CodeLlama 70B (Anyscale) is well suited to Open weights, Code-tuned and Wide ecosystem.

Who makes CodeLlama 70B (Anyscale)?

CodeLlama 70B (Anyscale) is developed and served by Anyscale. It was released in Jan 2024.

Terms used on this page

Full glossary →
TokenInput tokensOutput tokensPrice per million tokensContext windowPrompt cachingBatch APIBlended cost