LIVE Cheapest: GLM-4.7-Flash $0.000/Mtok in 153 models tracked Updated Jun 25, 2026
Jun 25, 2026
ModelPriceWatch$/Mtok
Pricing / Compare / gpt-oss-120B vs Gemma-4-31B-it-Pearl

gpt-oss-120B vs Gemma-4-31B-it-Pearl

Side-by-side API pricing comparison · Together vs Together

🏆 gpt-oss-120B is 52% cheaper on blended cost ($0.375 vs $0.570/Mtok)

gpt-oss-120B

by Together

Current budget Open weights
Input
$0.150/Mtok
Output
$0.600/Mtok
✓ Cheaper
Blended avg$0.375/Mtok
Context128K tokens
Modalitytext
Parameters120B
ReleasedJan 1, 2026
Full details →

Gemma-4-31B-it-Pearl

by Together

Current budget Open weights
Input
$0.280/Mtok
Output
$0.860/Mtok
Blended avg$0.570/Mtok
Context128K tokens
Modalitytext
Parameters31B
ReleasedJan 1, 2026
Full details →

Cost at scale — 1M tokens (50/50 input/output)

Volumegpt-oss-120BGemma-4-31B-it-PearlSavings
1M tokens $0.38 $0.57 $0.2 (35.1%)
10M tokens $3.75 $5.7 $1.95 (34.2%)
100M tokens $37.5 $57 $19.5 (34.2%)
1000M tokens $375 $570 $195 (34.2%)

Summary

gpt-oss-120B by Together costs $0.150/Mtok input and $0.600/Mtok output, with a 128K-token context window. It supports text input.

Gemma-4-31B-it-Pearl by Together costs $0.280/Mtok input and $0.860/Mtok output, with a 128K-token context window. It supports text input.

On a blended cost basis, gpt-oss-120B is 52% cheaper than Gemma-4-31B-it-Pearl.

Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.