LLM Pricing
← All models

deepseek-v3.2

OpenRouter · Chat model

deepseek-v3.2 is listed here as a chat model from OpenRouter. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.

Provider and model identifiers are kept in their original form for accuracy.

openrouter-openrouter-deepseek-deepseek-v3-2

Input
$0.2800 / 1M tokens
Output
$0.4000 / 1M tokens
Cached input
$0.0280 / 1M tokens
Context window
163.8K

Catalog generated: Jul 13, 2026

Compare this model Open a side-by-side table using this route and a close match from the current catalog. Estimate cost Use token counts, request volume, and cache assumptions to check a realistic monthly bill.

Quick read

Best for

Use this page when you need a fast view of cost, context size, and supported features before testing the model in your own workload.

Things to verify

Always check the provider page for discounts, cache pricing, region rules, and any model limits that may not appear in public metadata.

Pricing

Item Price
Input
$0.2800 / 1M tokens
Output
$0.4000 / 1M tokens
Cached input
$0.0280 / 1M tokens
Embedding
$0.2800 / 1M tokens

Limits

Context window
163.8K
Max input tokens
163.8K
Max output tokens
163.8K
Max tokens
163.8K
Explore benchmark family Review source-backed benchmark rows for the attached base model family. Check data sources See how pricing data is generated and what still needs provider verification. API vs subscription Learn when API pricing matters compared with ChatGPT, Claude Code, Cursor, or Copilot subscriptions. Cache and batch pricing Understand cached input, cache write, batch, priority, and flex pricing rows shown on this page.

Capabilities

Capability Supported
Vision -
Function calling Supported
Parallel function calling -
Tool choice Supported
Prompt caching Supported
Reasoning Supported
Response schema -
System messages -
Audio input -
Audio output -
Web search -
PDF input -
Video input -

Benchmarks

Most benchmark rows are attached to the base model family rather than this provider route. Open benchmark explorer

Benchmark Score Metric Scope Checked Source
MMLU 88.5 EM Base model: DeepSeek-V3 (DeepSeek-V3) 2026-05-31 Link
GPQA Diamond 59.1 Pass@1 Base model: DeepSeek-V3 (DeepSeek-V3) 2026-05-31 Link
LiveCodeBench 37.6 Pass@1 Base model: DeepSeek-V3 (DeepSeek-V3) 2026-05-31 Link
AIME 2024 39.2 Pass@1 Base model: DeepSeek-V3 (DeepSeek-V3) 2026-05-31 Link
MATH-500 90.2 EM Base model: DeepSeek-V3 (DeepSeek-V3) 2026-05-31 Link
Aider Polyglot 74.2% percent correct Base model: DeepSeek V3.2-Exp (deepseek/deepseek-reasoner) 2026-05-31 Link
MMLU-Pro 85.0 EM Base model: DeepSeek-V3.2-Exp (DeepSeek-V3.2-Exp) 2026-05-31 Link
GPQA Diamond 79.9 pass@1 Base model: DeepSeek-V3.2-Exp (DeepSeek-V3.2-Exp) 2026-05-31 Link
LiveCodeBench 74.1 pass@1 Base model: DeepSeek-V3.2-Exp (DeepSeek-V3.2-Exp) 2026-05-31 Link
AIME 2025 89.3 pass@1 Base model: DeepSeek-V3.2-Exp (DeepSeek-V3.2-Exp) 2026-05-31 Link
Aider Polyglot 74.5 accuracy Base model: DeepSeek-V3.2-Exp (DeepSeek-V3.2-Exp) 2026-05-31 Link
SWE-bench Verified 67.8 resolved Base model: DeepSeek-V3.2-Exp (DeepSeek-V3.2-Exp) 2026-05-31 Link
Terminal-Bench 37.7 score Base model: DeepSeek-V3.2-Exp (DeepSeek-V3.2-Exp) 2026-05-31 Link
Diamond 82.4 score Base model: DeepSeek-V3.2 (deepseek-ai/DeepSeek-V3.2) 2026-05-31 Link
Terminal-Bench 2.0 39.6 * score Base model: DeepSeek-V3.2 (deepseek-ai/DeepSeek-V3.2) 2026-05-31 Link
Apex Agents 7 * score Base model: DeepSeek-V3.2 (deepseek-ai/DeepSeek-V3.2) 2026-05-31 Link
SWE-bench Pro 15.56 score Base model: DeepSeek-V3.2 (deepseek-ai/DeepSeek-V3.2) 2026-05-31 Link
SWE-bench Verified 70 * resolved Base model: DeepSeek-V3.2 (deepseek-ai/DeepSeek-V3.2) 2026-05-31 Link

Sources

Source links
Pricing dataLiteLLM model cost map
Synced at2026-05-28
Catalog generated2026-07-13T14:21:55.110Z