Compare

MiniMax M2.7 vs GPT-5.4 Mini

Pricing per million tokens, context window, capabilities — pulled from each provider's public docs. All 2 are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.

Search2/4
MiniMax M2.7
minimax/m2.7
GPT-5.4 Mini
openai/gpt-5.4-mini
Provider
MiniMax
OpenAI
Family
MiniMax M
GPT-5
Modality
text
text
Context window
128,000 tok
128,000 tok
Max output
4,096 tok
16,384 tok
Released
2026-05-22
2026-05-22
License
Open-weight
Proprietary
Input price
$0.300 /1M
$0.750 /1M
Output price
$1.20 /1M
$4.50 /1M
Cache read
$0.075 /1M
Tools
yes
Streaming
yes
yes
Vision
yes
JSON mode
yes
Reasoning
yes
Prompt caching
yes
Batch API
yes
Try it
Open in playground →
Open in playground →
MiniMax M2.7
minimax/m2.7
Full spec →

MiniMax's M2.7 language model with multilingual capabilities.

Strengths
  • General-purpose chat
  • Long context
  • Tool use
Use cases
ChatbotsContent generationAgentic workflows
GPT-5.4 Mini
openai/gpt-5.4-mini
Full spec →

GPT-5.4 mini is a smaller, faster, and more cost-efficient version of GPT-5.4 for lightweight tasks.

Strengths
  • Very cheap per token
  • Fast
  • Full tool + vision support
Use cases
Drafts + rewritesBulk batch jobsCost-sensitive production

Benchmarks

MiniMax M2.7
GPT-5.4 Mini
HumanEval
88.6
MMLU
84.5

Source: each provider's published benchmarks. Higher is better. Run an eval to compare on your own data.

Compare with another

Claude Sonnet 4.6 vs GPT-5.4 Mini
anthropic/claude-sonnet-4.6 · openai/gpt-5.4-mini
Claude Haiku 4.5 vs GPT-5.4 Mini
anthropic/claude-haiku-4.5 · openai/gpt-5.4-mini
GPT-5.4 Mini vs Gemini 3 Flash
openai/gpt-5.4-mini · google/gemini-3-flash
Claude Opus 4.8 vs GPT-5.4 Mini
anthropic/claude-opus-4.8 · openai/gpt-5.4-mini
Claude Opus 4.8 vs MiniMax M2.7
anthropic/claude-opus-4.8 · minimax/m2.7
Claude Sonnet 4.6 vs MiniMax M2.7
anthropic/claude-sonnet-4.6 · minimax/m2.7
Grok 4.20 Multi-Agent vs GPT-5.4 Mini
xai/grok-4.20-multi-agent-0309 · openai/gpt-5.4-mini
Grok 4.20 Multi-Agent vs MiniMax M2.7
xai/grok-4.20-multi-agent-0309 · minimax/m2.7
GPT-5.4 vs GPT-5.4 Mini
openai/gpt-5.4 · openai/gpt-5.4-mini
SWITCH BETWEEN THEM

One key, all 2, one line different.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.aigateway.sh/v1",
    api_key="sk-aig-...",
)

# MiniMax M2.7
client.chat.completions.create(
    model="minimax/m2.7",
    messages=[{"role":"user","content":"hello"}],
)

# GPT-5.4 Mini
client.chat.completions.create(
    model="openai/gpt-5.4-mini",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →