Skip to content
Alpha
  • Models
  • Rankings
  • Ori

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Ori
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Customers
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for qwen

Qwen2.5 Coder 32B Instruct

qwen/qwen-2.5-coder-32b-instruct

Model weights
Compare

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:

  • Significantly improvements in code generation, code reasoning and code fixing.
  • A more comprehensive foundation for real-world applications such as Code Agents. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies.

To read more about its evaluation results, check out Qwen 2.5 Coder's blogOpens in new tab.

Modalities
In / Out Price
$0.66 / $1per 1M
Context
33K
Released
Nov 11, 2024
Knowledge Cutoff
Jun 2024
Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Qwen2.5 Coder 32B Instruct (Artificial Analysis)
SourceBenchmarkScore
Artificial AnalysisQwen2.5 Coder Instruct 32B Intelligence Index6.7
Artificial AnalysisQwen2.5 Coder Instruct 32B GPQA Diamond41.7%
Artificial AnalysisQwen2.5 Coder Instruct 32B HLE3.5%
Artificial AnalysisQwen2.5 Coder Instruct 32B LiveCodeBench29.5%
Artificial AnalysisQwen2.5 Coder Instruct 32B MMLU-Pro63.5%
Artificial AnalysisQwen2.5 Coder Instruct 32B AIME12.0%
Artificial AnalysisQwen2.5 Coder Instruct 32B MATH-50076.7%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Not currently available through EU in-region routing. In-region routing docs

Explore more models

AI Model RankingsRanking
Latency / throughput
$0.66$1.001.74s31 tps
100.00%
Throughput
31tok/s

P50, best across providers

Latency
1.74s

P50, best provider

Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
99.87%

Availability over the last 3 days

Last 72 hours
Availability 99.87%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.56%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

1.
Favicon for https://jtg-systems.com/
JTG Swarm Council Engine
new
41Mtokens
2.
Favicon for https://predator-v3.local/
PredatorV3-5SeatCouncil
new
23.2Mtokens
3.
Favicon for https://aider.chat/
Aider
AI pair programming in your terminal
15.9Mtokens
4.
Favicon for https://dataxmind.com/
SACP-Gateway
new
13.2Mtokens
5.
Favicon for https://ethos.institute/
ETHOS Ensemble (Xiaomi MiMo-V2.6-Pro (Mathematical & Numerics Auditor))
new
9.78Mtokens

Frequently asked questions

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in code generation, code reasoning and code fixing. - A more comprehensive foundation for real-world applications such as Code Agents.

Qwen2.5 Coder 32B Instruct costs $0.66/M input tokens and $1.00/M output tokens.

Qwen2.5 Coder 32B Instruct has a 32,768 token context window. It supports up to 32,768 completion tokens.

No. Qwen2.5 Coder 32B Instruct does not accept tools, so function calling is unavailable. It supports response_format for JSON output, without JSON-schema enforcement.

Qwen3.8 Max Prime, Qwen3.8 Omni Flash, Qwen3.8 Max (0902) and 38 more are other text models from Qwen.

Qwen2.5 Coder 32B Instruct was released on November 11, 2024. Its knowledge cutoff is June 30, 2024.