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 DeepInfra models
DeepInfra
DeepInfraEfficient

Llama 3.3 70B (DI)

Serverless

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

Llama 3.3 70B (DI) is a efficient AI model from DeepInfra. It costs $0.230 per million input tokens and $0.400 per million output tokens (blended $0.281/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
$0.230/M
per million input tokens
OUTPUT
$0.400/M
per million output tokens
BLENDED 70/30
$0.281/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 DeepInfra
See all 11 →
Llama 3.1 405B (DI)
Serverless · 128K ctx
in $0.800/Mout $0.800/M
Llama 3.1 70B (DI)
Balanced · 128K ctx
in $0.350/Mout $0.400/M
Mistral 7B (DI)
Nano · 32K ctx
in $0.070/Mout $0.070/M
Mixtral 8x7B (DI)
MoE · 32K ctx
in $0.240/Mout $0.240/M
DeepSeek-R1 (DI)
Reasoning · 64K ctx
in $0.550/Mout $2.190/M
Qwen2.5-72B (DI)
Balanced · 128K ctx
in $0.350/Mout $0.400/M
Frequently asked questions

How much does Llama 3.3 70B (DI) cost?

Llama 3.3 70B (DI) costs $0.230 per million input tokens and $0.400 per million output tokens, for a blended reference rate of $0.281 per million tokens.

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

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

What is Llama 3.3 70B (DI) best for?

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

Who makes Llama 3.3 70B (DI)?

Llama 3.3 70B (DI) is developed and served by DeepInfra.