TA/Qwen/Qwen3-235B-A22B-fp8-tput
Common Name: Qwen3 235B A22B FP8 Throughput
TogetherAI
Released on May 7 12:00 AMQwen3 235B model with 22B active parameters optimized for throughput, hosted on TogetherAI.
Specifications
Context
128K
Maximum Output
32.8K
Inputtext
Outputtext
Performance (7-day Average)
Collecting…
Collecting…
Collecting…
Pricing
Input$0.22/MTokens
Output$0.66/MTokens
Availability Trend (24h)
Performance Metrics (24h)
Similar Models
$0.17/$0.66/M
ctx128Kmax—avail—tps—
InOutCap
OpenAI's open-weight 120B model for production and high reasoning use cases, hosted on TogetherAI.
$0.20/$0.20/M
ctx128Kmax—avail—tps—
InOut
Meta's Llama 3.1 8B optimized for fast inference on TogetherAI.
$0.22/$0.22/M
ctx128Kmax—avail—tps—
InOut
Meta's Llama 2 7B chat model for conversational AI, hosted on TogetherAI.
$0.22/$0.22/M
ctx128Kmax—avail—tps—
InOut
Mistral AI's 7B instruction-tuned model v0.2 with improved performance, hosted on TogetherAI.