# Qwen3 14B

As of 14 September 2026, Qwen3 14B costs $0.120 per million input tokens and $0.240 per million output tokens on OpenRouter. Observed on OpenRouter's own published price list on 14 September 2026. This is OpenRouter's resale price, not the model vendor's list price.

Source: OpenRouter (reseller)
Canonical page: https://bertrande.com/en/ai/openrouter/qwen--qwen3-14b/
Machine formats: https://bertrande.com/en/ai/openrouter/qwen--qwen3-14b/data.json | https://bertrande.com/en/ai/openrouter/qwen--qwen3-14b/data.csv
License: CC-BY-4.0, reuse with attribution and a link.

## Parameters

| Parameter | Value | Unit | Observed | Source level | Proof (SHA-256) |
|---|---|---|---|---|---|
| Input price | $0.120 | USD per 1M tokens | 2026-09-14 | L1 | `4ec86d780634a903` |
| Output price | $0.240 | USD per 1M tokens | 2026-09-14 | L1 | `4ec86d780634a903` |
| Context window | 131 072 | tokens | 2026-09-15 | L1 | `08c6e27b7535b9dc` |
| Maximum output | 16 384 | tokens | 2026-09-14 | L1 | `4ec86d780634a903` |
| Agentic index (Artificial Analysis) | 0.900 | index 0-100 | 2026-09-15 | L4 | `48cc0be56adecc1b` |
| Coding index (Artificial Analysis) | 13.8 | index 0-100 | 2026-09-16 | L4 | `42ebb9d4b828cb12` |
| Intelligence index (Artificial Analysis) | 6.4 | index 0-100 | 2026-09-15 | L4 | `48cc0be56adecc1b` |
| Input modalities | text | list | 2026-09-18 | L1 | `62c152853524cc69` |
| Output modalities | text | list | 2026-09-18 | L1 | `62c152853524cc69` |
| Listed since | 2025-04-28 | date | 2026-09-18 | L1 | `62c152853524cc69` |
| Supported parameters | frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p | list | 2026-09-18 | L1 | `62c152853524cc69` |

## How this is verified

Every value above was read from the source URL shown on the canonical page, on the date given. We store a SHA-256 fingerprint of the source content at that moment, which is what lets us show later what the source said that day.

No value here was produced, estimated or completed by a language model. Where we have no verified figure, the row is absent rather than filled in.

Method: https://bertrande.com/en/methodology/
Report an error: https://bertrande.com/en/corrections/