Qwen3 235B A22B Thinking 2507 FP8
Gmi textgmi/Qwen/Qwen3-235B-A22B-Thinking-2507-FP8
Input
$0.3500
per 1M input tokens
Output
$4.20
per 1M output tokens
Cache read
n/a
per 1M cached read tokens
Cache write
n/a
per 1M cache write tokens
Context window
262,141
Max output
n/a
Effective date
Nov 5, 2026
Estimate a workload
Enter token counts to see the cost at this model's rates.
Estimated cost:
$0.00
Price history
blended $ per 1M tokens (3:1)One price on record so far (Nov 5, 2026). This chart fills in as the price changes over time. We check daily.
| Effective | Input | Output | Blended |
|---|---|---|---|
| Nov 5, 2026 | $0.35 | $4.20 | $1.31 |
Other Gmi models
gmi/openai/gpt-oss-120b
· $0.2500/Mtok out
gmi/zai-org/GLM-4.7-Flash
· $0.4000/Mtok out
gmi/zai-org/GLM-5.3-Flash
· $0.2500/Mtok out
gmi/Qwen/Qwen3-30B-A3B
· $0.2500/Mtok out
gmi/meta-llama/Llama-4-Scout-17B-16E-Instruct
· $0.5000/Mtok out
gmi/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8
· $0.3500/Mtok out
Source: litellm. Confirm against the provider's official pricing before relying on these figures.