How do I use Tokyotech LLM models through the OpenRouter API?

OpenRouter serves 1 Tokyotech LLM model behind one OpenAI-compatible API. Create an OpenRouter API key, point your client at https://openrouter.ai/api/v1, and set the model to an ID such as tokyotech-llm/llama-3.1-swallow-8b-instruct-v0.3. The quickstart has request examples for every supported SDK.

Which Tokyotech LLM model has the largest context window?

Llama 3.1 Swallow 8B Instruct V0.3 has the largest context window of any Tokyotech LLM model on OpenRouter, accepting up to 16,384 tokens per request.

What is the newest Tokyotech LLM model on OpenRouter?

Llama 3.1 Swallow 8B Instruct V0.3 is the most recently added Tokyotech LLM model on OpenRouter, listed on April 7, 2025.

Tokyotech LLM

Access 1 Tokyotech LLM model through the OpenRouter unified API including Llama 3.1 Swallow 8B Instruct V0.3. Compare pricing, context windows, benchmarks, and capabilities between different Tokyotech LLM models.

Tokyotech LLM requests made on OpenRouter

Not enough data to display yet.

Swallow: Llama 3.1 Swallow 8B Instruct V0.3Llama 3.1 Swallow 8B Instruct V0.3
Llama 3.1 Swallow 8B is a large language model that was built by continual pre-training on the Meta Llama 3.1 8B. Llama 3.1 Swallow enhanced the Japanese language capabilities of the original Llama 3.1 while retaining the English language capabilities. Swallow used approximately 200 billion tokens that were sampled from a large Japanese web corpus (Swallow Corpus Version 2), Japanese and English Wikipedia articles, and mathematical and coding contents, etc (see the Training Datasets section of the base model) for continual pre-training. The instruction-tuned models (Instruct) were built by supervised fine-tuning (SFT) on the synthetic data specially built for Japanese.
by tokyotech-llmApr 7, 202516K context

Tokyotech LLM

Access 1 Tokyotech LLM model through the OpenRouter unified API including Llama 3.1 Swallow 8B Instruct V0.3. Compare pricing, context windows, benchmarks, and capabilities between different Tokyotech LLM models.

Tokyotech LLM requests made on OpenRouter

Not enough data to display yet.

Swallow: Llama 3.1 Swallow 8B Instruct V0.3Llama 3.1 Swallow 8B Instruct V0.3
Llama 3.1 Swallow 8B is a large language model that was built by continual pre-training on the Meta Llama 3.1 8B. Llama 3.1 Swallow enhanced the Japanese language capabilities of the original Llama 3.1 while retaining the English language capabilities. Swallow used approximately 200 billion tokens that were sampled from a large Japanese web corpus (Swallow Corpus Version 2), Japanese and English Wikipedia articles, and mathematical and coding contents, etc (see the Training Datasets section of the base model) for continual pre-training. The instruction-tuned models (Instruct) were built by supervised fine-tuning (SFT) on the synthetic data specially built for Japanese.
by tokyotech-llmApr 7, 202516K context

Tokyotech LLM

Not enough data to display yet.

Frequently asked questions

Tokyotech LLM

Not enough data to display yet.

Frequently asked questions