Skip to contentx402 is live on Robinhood Chain: agents can now pay for any model, per call, in USDG →
OmniRail
← All models

Qwen · Language model

Qwen3 30B A3B Thinking 2507

qwen/qwen3-30b-a3b-thinking-2507
  • Language
Released Aug 28, 2025

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...

Specifications

Context window
81,920 tokens
Max output
32,768 tokens
Input
text
Output
text
Reasoning
always on
Tokenizer
Qwen3
Knowledge cutoff
2025-06-30

Supported parameters

Accepted by the model and forwarded as-is by the gateway.

  • frequency_penalty
  • max_tokens
  • presence_penalty
  • reasoning
  • response_format
  • seed
  • stop
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_p

Use it

POST /api/v1/chat/completions · MCP chat · full reference

curl https://omnirail.org/api/v1/chat/completions \
  -H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3-30b-a3b-thinking-2507","messages":[{"role":"user","content":"Hello"}],"max_tokens":300}'