Back to Models
Science Tokyo
japan-qwen3-swallow-8b
Qwen3 Swallow 8B
Japan: Qwen3 Swallow 8B (AWQ-INT4) - Science Tokyo's Japanese-tuned Qwen3 8B, hosted and run in Japan
32,768 tokens
Input: $0.0351/M
Output: $0.1721/M
Specifications
Modalities
Input
text
Output
text
Max Output Tokens
8,192Data policy
- Prompt retention
- Unknown: we could not confirm
- Training
- Not used for training
"Unknown" does not mean "safe". It means we could not confirm it.
Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.
Code Examples
curl https://api.fastmetal.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "japan-qwen3-swallow-8b",
"messages": [{"role": "user", "content": "Hello!"}]
}'Frequently asked questions
- How much does the Qwen3 Swallow 8B API cost?
- On FastMetal, Qwen3 Swallow 8B is billed per token: $0.0351 per 1M input tokens and $0.1721 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
- Can I call Qwen3 Swallow 8B with the OpenAI SDK?
- Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "japan-qwen3-swallow-8b" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
- What is the context window of Qwen3 Swallow 8B?
- 32,768 tokens, shared between the prompt and the response.
- What do I need to try Qwen3 Swallow 8B?
- Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.
Try Qwen3 Swallow 8B right now
Qwen3 Swallow 8B is available on FastMetal through one API key. Start in the browser, or call it from the OpenAI SDK.