Qwen3 235B A22B Thinking 2507 (FP8) API
Pricing & Specs
Qwen (Alibaba) · $0.65 input / $3 output per 1M tokens · 262.144K context window
No longer offered on OpenMark
Qwen3 235B A22B Thinking 2507 (FP8) API is no longer offered on OpenMark (deprecated or superseded upstream). Its specs are kept here for reference — if you're still running it in production, it's worth benchmarking current alternatives: newer models are often cheaper AND better on the same task.
Qwen3 235B A22B Thinking 2507 (FP8) API API Pricing
| Tokens | Price |
|---|---|
| Input | $0.65 / 1M tokens |
| Output | $3 / 1M tokens |
50% discount available for batch API requests. Batch API pricing is available via Together at 50%; cache pricing is not published.
What that means in practice
Qwen3 235B A22B Thinking 2507 (FP8) API Specs
| Spec | Value |
|---|---|
| Context window | 262.144K tokens |
| Input modalities | text |
| Output modalities | text |
| Latency (measured by OpenMark) | ~3.3s median response |
| Reasoning model | Yes |
| Tool / function calling | Yes |
| JSON mode | Yes |
| Streaming | Yes |
| Prompt caching | No |
| Batch API | Yes |
Capabilities
Notes
Scheduled for deprecation on Together AI: March 06, 2026.
FAQ
How much does Qwen3 235B A22B Thinking 2507 (FP8) API cost?
Qwen3 235B A22B Thinking 2507 (FP8) API costs $0.65 per 1M input tokens and $3 per 1M output tokens.
What is Qwen3 235B A22B Thinking 2507 (FP8) API's context window?
Qwen3 235B A22B Thinking 2507 (FP8) API has a 262.144K-token context window.
Can I test Qwen3 235B A22B Thinking 2507 (FP8) API on my own task?
Qwen3 235B A22B Thinking 2507 (FP8) API is no longer offered on OpenMark, but you can benchmark its current alternatives from Qwen (Alibaba) and other providers on your own task — free tier available.
Still using Qwen3 235B A22B Thinking 2507 (FP8) API?
It's been superseded. Benchmark its current alternatives on your actual
workload — you'll likely find something cheaper AND better. Free tier available.