Skip to main content
Model catalogue

LLM model catalogue: prices, context windows and capabilities

Look up what a model costs, how much it can read and write, and what it can do. The table lists 486 models from 12 of the 14 providers the DVARA LLM Gateway connects to, with list prices in US dollars per million tokens.

Two providers are not listed. On Azure OpenAI, each model is a deployment you create and name yourself, and its price follows your Azure agreement. Ollama runs models on your own hardware, so there is no list price. Both work in the gateway like any other provider; see Connect model providers.

Showing 1–50 of 486 models

Models with list prices in US dollars per million tokens, context window, output limit and capabilities. Column headers sort the table.
Capabilities
DeepSeek R1 Distill Qwen 1.5Bdeepseek-r1-distill-qwen-1-5bAlibaba Qwen$0$0—33K16K
  • Tools
  • Reasoning
DeepSeek R1 Distill Qwen 14Bdeepseek-r1-distill-qwen-14bAlibaba Qwen$0.144$0.431—33K16K
  • Tools
  • Reasoning
DeepSeek R1 Distill Qwen 32Bdeepseek-r1-distill-qwen-32bAlibaba Qwen$0.287$0.861—33K16K
  • Tools
  • Reasoning
DeepSeek R1 Distill Qwen 7Bdeepseek-r1-distill-qwen-7bAlibaba Qwen$0.072$0.144—33K16K
  • Tools
  • Reasoning
QVQ Maxqvq-maxAlibaba Qwen$1.147$4.588—131K8K
  • Vision
  • Tools
  • Reasoning
Qwen Deep Researchqwen-deep-researchAlibaba Qwen$7.742$23.367—1M33K
  • Tools
Qwen Doc Turboqwen-doc-turboAlibaba Qwen$0.087$0.144—131K8K
  • Tools
Qwen Flashqwen-flashAlibaba Qwen$0.022$0.216—1M33K
  • Tools
  • Reasoning
Qwen Longqwen-longAlibaba Qwen$0.072$0.287—10M8K
  • Tools
Qwen Math Plusqwen-math-plusAlibaba Qwen$0.574$1.721—4K3K
  • Tools
Qwen Math Turboqwen-math-turboAlibaba Qwen$0.287$0.861—4K3K
  • Tools
Qwen Maxqwen-maxAlibaba Qwen$0.345$1.377—131K8K
  • Tools
Qwen Plusqwen-plusAlibaba Qwen$0.115$0.287$0.0121M33K
  • Tools
  • Reasoning
Qwen Plus Characterqwen-plus-characterAlibaba Qwen$0.115$0.287—33K4K
  • Tools
Qwen Turboqwen-turboAlibaba Qwen$0.044$0.087—1M16K
  • Tools
  • Reasoning
Qwen-MT Plusqwen-mt-plusAlibaba Qwen$0.259$0.775—16K8K
  • None listed
Qwen-MT Turboqwen-mt-turboAlibaba Qwen$0.101$0.28—16K8K
  • None listed
Qwen-Omni Turboqwen-omni-turboAlibaba Qwen$0.058$0.23—33K2K
  • Vision
  • Tools
Qwen-Omni Turbo Realtimeqwen-omni-turbo-realtimeAlibaba Qwen$0.23$0.918—33K2K
  • Vision
  • Tools
Qwen-VL Maxqwen-vl-maxAlibaba Qwen$0.23$0.574—131K8K
  • Vision
  • Tools
Qwen-VL OCRqwen-vl-ocrAlibaba Qwen$0.043$0.072—34K4K
  • Vision
Qwen-VL Plusqwen-vl-plusAlibaba Qwen$0.115$0.287—131K8K
  • Vision
  • Tools
Qwen2.5 14B Instructqwen2-5-14b-instructAlibaba Qwen$0.144$0.431—131K8K
  • Tools
Qwen2.5 32B Instructqwen2-5-32b-instructAlibaba Qwen$0.287$0.861—131K8K
  • Tools
Qwen2.5 72B Instructqwen2-5-72b-instructAlibaba Qwen$0.574$1.721—131K8K
  • Tools
Qwen2.5 7B Instructqwen2-5-7b-instructAlibaba Qwen$0.072$0.144—131K8K
  • Tools
Qwen2.5-Coder 32B Instructqwen2-5-coder-32b-instructAlibaba Qwen$0.287$0.861—131K8K
  • Tools
Qwen2.5-Coder 7B Instructqwen2-5-coder-7b-instructAlibaba Qwen$0.144$0.287—131K8K
  • Tools
Qwen2.5-Math 72B Instructqwen2-5-math-72b-instructAlibaba Qwen$0.574$1.721—4K3K
  • Tools
Qwen2.5-Math 7B Instructqwen2-5-math-7b-instructAlibaba Qwen$0.144$0.287—4K3K
  • Tools
Qwen2.5-Omni 7Bqwen2-5-omni-7bAlibaba Qwen$0.087$0.345—33K2K
  • Vision
  • Tools
Qwen2.5-VL 72B Instructqwen2-5-vl-72b-instructAlibaba Qwen$2.294$6.881—131K8K
  • Vision
  • Tools
Qwen2.5-VL 7B Instructqwen2-5-vl-7b-instructAlibaba Qwen$0.287$0.717—131K8K
  • Vision
  • Tools
Qwen3 14Bqwen3-14bAlibaba Qwen$0.144$0.574—131K8K
  • Tools
  • Reasoning
Qwen3 235B-A22Bqwen3-235b-a22bAlibaba Qwen$0.287$1.147—131K16K
  • Tools
  • Reasoning
Qwen3 32Bqwen3-32bAlibaba Qwen$0.287$1.147—131K16K
  • Tools
  • Reasoning
Qwen3 8Bqwen3-8bAlibaba Qwen$0.072$0.287—131K8K
  • Tools
  • Reasoning
Qwen3 Coder Flashqwen3-coder-flashAlibaba Qwen$0.144$0.574—1M66K
  • Tools
Qwen3 Coder Plusqwen3-coder-plusAlibaba Qwen$0.574$2.296—1.05M66K
  • Tools
Qwen3 Maxqwen3-maxAlibaba Qwen$0.359$1.434—262K66K
  • Tools
  • Structured
  • Reasoning
Qwen3-ASR Flashqwen3-asr-flashAlibaba Qwen$0.032$0.032—53K4K
  • None listed
Qwen3-Coder 30B-A3B Instructqwen3-coder-30b-a3b-instructAlibaba Qwen$0.216$0.861—262K66K
  • Tools
Qwen3-Coder 480B-A35B Instructqwen3-coder-480b-a35b-instructAlibaba Qwen$0.861$3.441—262K66K
  • Tools
Qwen3-Next 80B-A3B (Thinking)qwen3-next-80b-a3b-thinkingAlibaba Qwen$0.144$1.434—131K33K
  • Tools
  • Reasoning
Qwen3-Next 80B-A3B Instructqwen3-next-80b-a3b-instructAlibaba Qwen$0.144$0.574—131K33K
  • Tools
Qwen3-Omni Flashqwen3-omni-flashAlibaba Qwen$0.058$0.23—66K16K
  • Vision
  • Tools
  • Reasoning
Qwen3-Omni Flash Realtimeqwen3-omni-flash-realtimeAlibaba Qwen$0.23$0.918—66K16K
  • Vision
  • Tools
Qwen3-VL 235B-A22Bqwen3-vl-235b-a22bAlibaba Qwen$0.2867$1.1468—131K33K
  • Vision
  • Tools
  • Reasoning
Qwen3-VL 30B-A3Bqwen3-vl-30b-a3bAlibaba Qwen$0.108$0.431—131K33K
  • Vision
  • Tools
  • Reasoning
Qwen3-VL Plusqwen3-vl-plusAlibaba Qwen$0.1434$1.4335—262K33K
  • Vision
  • Tools
  • Reasoning

How is this catalogue kept current?​

DVARA reviews every price weekly before it is published. Each check marks a model for a closer look: a cached-input price outside 10–50% of the input price, output cheaper than input, a zero price on a hosted model, a missing cache price where the provider bills caching, a context window smaller than the output limit, and a price more than 1% away from another published price list. A mark never hides a model. Each model page shows its marks.

How does DVARA use these prices?​

In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.

Each DVARA release packages a snapshot of this catalogue, so an install with no internet access has it. Flightdeck can also read your own copy of llm-models.json from a URL you choose. It refuses a copy that is damaged, much smaller than the packaged one, or fails a price check it does not flag, and keeps the last good copy. Read more about LLM cost attribution and budgets.

What do the columns mean?​

  • Input and output are the list prices per million tokens sent to and returned by the model.
  • Cached input is the price per million input tokens read from the provider's prompt cache.
  • Context is the most tokens the model accepts in one call, input and output together.
  • Max output is the most tokens the model returns in one call.
  • Vision means the model accepts images. Structured output means it can be held to a JSON schema.

Snapshot 16 October 2026. DVARA reviews every price weekly before it is published. Get the whole catalogue as llm-models.json. Prices are list prices in US dollars per million tokens; check your provider contract before you budget.