AIモデルインテリジェンス

プロバイダー · 2026-05-12

openrouter

標準モデル 24 件全 55 件(派生 / ファインチューン含む)
モデル入力 / 1M出力 / 1Mコンテキストプロバイダータグ
Hy3 preview$0.066$0.260256K1tools · reasoning · open-weights
Hermes 4 70B$0.130$0.400131K1tools · json · reasoning · open-weights
Trinity Large Thinking$0.220$0.850262K1tools · reasoning · open-weights
Intellect 3$0.200$1.10131K1tools · json · reasoning · open-weights
Hermes 4 405B$1.00$3.00131K1tools · reasoning · open-weights
Elephant (free)不明不明262K1tools · json · reasoning
FLUX.2 Flex不明不明67K1vision
FLUX.2 Klein 4B不明不明41K1vision · open-weights
FLUX.2 Max不明不明47K1vision
FLUX.2 Pro不明不明47K1vision
Free Models Router不明不明200K1tools · json · reasoning · vision
Hermes 3 405B Instruct (free)不明不明131K1reasoning · open-weights
Laguna M.1不明不明131K1tools · reasoning
Laguna XS.2不明不明131K1tools · reasoning · open-weights
LFM2.5-1.2B-Instruct (free)不明不明131K1open-weights
LFM2.5-1.2B-Thinking (free)不明不明131K1reasoning · open-weights
Owl Alpha不明不明1.05M1tools · json · reasoning
Pareto Code Router不明不明200K1tools · json · reasoning
Riverflow V2 Fast Preview不明不明8K1vision · open-weights
Riverflow V2 Max Preview不明不明8K1vision · open-weights
Riverflow V2 Standard Preview不明不明8K1vision · open-weights
Seedream 4.5不明不明4K1vision · open-weights
Trinity Large Preview不明不明131K1tools · json · open-weights
Uncensored (free)不明不明33K1json · open-weights
Gemma 2 9B派生$0.030$0.0908K1open-weights
GPT OSS 120B (exacto)派生$0.050$0.240131K1tools · json · reasoning · open-weights
Qwen: Qwen3.5-Flash派生$0.065$0.2601M1tools · json · reasoning · vision
DeepSeek-V3.1派生$0.200$0.800164K1tools · json · reasoning · open-weights
Qwen3 235B A22B Instruct 2507派生$0.150$0.850262K1tools · json · open-weights
DeepSeek V3.1 Terminus (exacto)派生$0.270$1.00131K1tools · json · reasoning · open-weights
Qwen3.6 27B派生$0.195$1.56262K1tools · json · vision · open-weights
Qwen3 Coder (exacto)派生$0.380$1.53131K1tools · json · open-weights
GLM 4.6 (exacto)派生$0.600$1.90200K1tools · json · reasoning · open-weights
Qwen3.5 Plus 2026-02-15派生$0.400$2.401M1tools · json · reasoning · vision
Kimi K2 Instruct 0905 (exacto)派生$0.600$2.50262K1tools · json · open-weights
Grok 4.20 Multi - Agent Beta派生$2.00$6.002M1reasoning · vision
Grok 4.20 Beta派生$2.00$6.002M1tools · reasoning · vision
DeepSeek V3 0324派生不明不明16K1json · open-weights
Gemma 3 12B (free)派生不明不明33K1vision · open-weights
Gemma 3 27B (free)派生不明不明131K1tools · vision · open-weights
Gemma 3 4B (free)派生不明不明33K1vision · open-weights
Gemma 3n 2B (free)派生不明不明8K1open-weights
Gemma 3n 4B (free)派生不明不明8K1open-weights
Gemma 4 26B A4B (free)派生不明不明262K1tools · json · reasoning · vision · open-weights
Gemma 4 31B (free)派生不明不明262K1tools · json · reasoning · vision · open-weights
GLM 4.5 Air (free)派生不明不明128K1reasoning · open-weights
gpt-oss-120b (free)派生不明不明131K1tools · reasoning · open-weights
gpt-oss-20b (free)派生不明不明131K1tools · reasoning · open-weights
MiniMax M2.5 (free)派生不明不明205K1tools · json · reasoning · open-weights
Nemotron 3 Nano 30B A3B (free)派生不明不明256K1tools · json · reasoning · open-weights
Nemotron 3 Nano Omni (free)派生不明不明256K1tools · json · reasoning · vision · open-weights
Nemotron 3 Super (free)派生不明不明262K1tools · reasoning · open-weights
Nemotron Nano 12B 2 VL (free)派生不明不明128K1tools · reasoning · vision · open-weights
Nemotron Nano 9B V2 (free)派生不明不明128K1tools · json · reasoning · open-weights
Qwen2.5 Coder 32B Instruct派生不明不明33K1json · open-weights

Frequently asked questions

How many AI models does openrouter offer?

We track 24 canonical openrouter models plus 31 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily from models.dev.

Which openrouter model is the cheapest?

Hy3 preview is currently the lowest-priced openrouter model, at $0.066 per 1M input tokens and $0.260 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.

Which openrouter model has the largest context window?

Owl Alpha leads at 1.05M tokens. This is the total of prompt + completion.

Which openrouter models support tool calling?

Multiple openrouter models support tool calling, with Hy3 preview being a popular pick. The capability column in the table above marks every model with openrouter tool-calling support.

Which openrouter models accept image input?

FLUX.2 Flex accepts image input. Other vision-capable openrouter models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.

What are the best alternatives to openrouter?

Depends on the use case. For raw cost savings, look at /pricing/cheapest-llm-api. For agent-oriented workloads, /best/best-ai-model-for-agents. For long-document workflows, /best/best-long-context-llm.

How fresh is this openrouter pricing data?

Daily. Our pipeline pulls models.dev each morning and rebuilds these pages on data change, so list-price moves and new model releases land within roughly 24 hours.

最終更新:

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.