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 Groq models
Groq
GroqEfficient

Qwen2.5-Coder-32B (Groq)

Fast Code

Best open-weights code model in its class. A strong Codestral / GPT-4 alternative for self-hosted IDE backends.

Qwen2.5-Coder-32B (Groq) is a efficient AI model from Groq. It costs $0.790 per million input tokens and $0.790 per million output tokens (blended $0.790/M), with a 128K-token context window.

Profile inherited from upstream Qwen2.5-Coder-32B ↗ — 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
$0.790/M
per million input tokens
OUTPUT
$0.790/M
per million output tokens
BLENDED 70/30
$0.790/M
default reference rate · how it's calculated →
CONTEXT
128K
128,000 tokens
What it's good at
  • Best open-weights code at 32B
  • 128K context
  • Permissive license
Typical use cases
  • Self-hosted IDE backends
  • Code review bots
Benchmarks
vs. best public score
Scores inherited from Qwen2.5-Coder-32B — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
MMLU75%
Multitask academic knowledge across 57 subjects.
HumanEval92%
Python function synthesis from docstrings.
LMArena Elo1235 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 Groq
See all 11 →
Llama 3.3 70B (Groq)
Ultra-Fast · 128K ctx
in $0.590/Mout $0.790/M
Llama 3.1 405B (Groq)
Fast Large · 128K ctx
in $2.990/Mout $2.990/M
Llama 3.1 70B (Groq)
Fast · 128K ctx
in $0.590/Mout $0.790/M
Llama 3.1 8B (Groq)
Fast Nano · 128K ctx
in $0.050/Mout $0.080/M
Llama 3.2 11B Vision (Groq)
Fast Vision · 128K ctx
in $0.180/Mout $0.180/M
Llama 3.2 3B (Groq)
Fast Micro · 128K ctx
in $0.060/Mout $0.060/M
Frequently asked questions

How much does Qwen2.5-Coder-32B (Groq) cost?

Qwen2.5-Coder-32B (Groq) costs $0.790 per million input tokens and $0.790 per million output tokens, for a blended reference rate of $0.790 per million tokens.

What is Qwen2.5-Coder-32B (Groq)'s context window?

Qwen2.5-Coder-32B (Groq) supports up to 128K tokens of context (128,000 tokens).

What is Qwen2.5-Coder-32B (Groq) best for?

Qwen2.5-Coder-32B (Groq) is well suited to Best open-weights code at 32B, 128K context and Permissive license.

Who makes Qwen2.5-Coder-32B (Groq)?

Qwen2.5-Coder-32B (Groq) is developed and served by Groq.