Claude Fable 5$22.000/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-5.5$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/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/MClaude Fable 5$22.000/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-5.5$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/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/M
BETA
Subscribe
← Back to Index·All Cerebras models
Cerebras
CerebrasEfficient

Llama-3.3-70B (Cerebras)

Ultra-Fast

The most-deployed open-weights chat model in 2025 — strong reasoning at 70B with broad inference-provider support.

Llama-3.3-70B (Cerebras) is a efficient AI model from Cerebras. It costs $0.590 per million input tokens and $0.990 per million output tokens (blended $0.710/M), with a 128K-token context window.

Profile inherited from upstream Llama 3.3 70B ↗ — this is a hosted variant of the same open-weights model.

Modalities textOfficial model page ↗Provider pricing ↗API docs ↗Compare with another model →Estimate monthly cost →
INPUT
$0.590/M
per million input tokens
OUTPUT
$0.990/M
per million output tokens
BLENDED 70/30
$0.710/M
default reference rate · how it's calculated →
CONTEXT
128K
128,000 tokens
What it's good at
  • Strong open chat baseline
  • Cheap on Groq/Cerebras
  • 128K context
  • Wide ecosystem
Typical use cases
  • Self-hosted production chat
  • Cost benchmarking
  • RAG
Benchmarks
vs. best public score
Scores inherited from Llama 3.3 70B — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
MMLU86%
Multitask academic knowledge across 57 subjects.
GPQA Diamond50%
Graduate-level science questions, "Google-proof".
MATH77%
High-school competition math problems.
HumanEval80%
Python function synthesis from docstrings.
LMArena Elo1257 Elo
Crowd-sourced head-to-head preference Elo rating.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources — treat as directional rather than authoritative.
More from Cerebras
See all 4 →
Llama-3.1-405B (Cerebras)
Fast Large · 128K ctx
in $0.990/Mout $0.990/M
Llama-3.1-8B (Cerebras)
Ultra-Fast Nano · 128K ctx
in $0.100/Mout $0.100/M
DeepSeek-R1 (Cerebras)
Fast Reasoning · 64K ctx
in $0.550/Mout $0.990/M
Frequently asked questions

How much does Llama-3.3-70B (Cerebras) cost?

Llama-3.3-70B (Cerebras) costs $0.590 per million input tokens and $0.990 per million output tokens, for a blended reference rate of $0.710 per million tokens.

What is Llama-3.3-70B (Cerebras)'s context window?

Llama-3.3-70B (Cerebras) supports up to 128K tokens of context (128,000 tokens).

What is Llama-3.3-70B (Cerebras) best for?

Llama-3.3-70B (Cerebras) is well suited to Strong open chat baseline, Cheap on Groq/Cerebras and 128K context.

Who makes Llama-3.3-70B (Cerebras)?

Llama-3.3-70B (Cerebras) is developed and served by Cerebras.