Minimax M3

Minimax M3 on Zumik: live pricing, context, and caching, routable by id or alias through one OpenAI-compatible endpoint.

$0.30
Input / 1M tokens
$1.20
Output / 1M tokens
$0.06
Cache read · −80%
512K
Context window

At a glance.

ProviderFireworks AI
Familyminimax_m3_vl
Released2026-06
LicenseOpen weights
Context window512K tokens
Max output512K tokens
Parameters428B
Modalitiestext
Tool callingYes
Reasoning modeYes
Cachingautomatic
Batch discountNo batch tier

What reuse looks like here.

Not yet profiled

Pricing, context, and capabilities for Minimax M3 are live, but it is outside the flagship set Zumik benchmarks in depth, so measured reuse, capture, and warm TTFT are not shown yet. Run a workload estimate or route it by id to start collecting traces.

Reuse economics

What you actually pay once caching works.

At a typical 55% prefix reuse, a million input tokens on Minimax M3 effectively costs $0.17 instead of $0.30 - blending to roughly $0.43 with a 25% output share. There is no batch tier, so cost control here leans on caching and routing.

Estimate it for your workload
Best for
text

Route it directly by id, or let an alias pick it when it wins under policy.

Same OpenAI client, this model.

python
from openai import OpenAI

client = OpenAI(base_url="https://api.zumik.ai/v1", api_key="zk_live_...")

r = client.responses.create(
    model="minimax-m3",
    input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached)   # confirm reuse

Minimax M3, answered.

How much does Minimax M3 cost?

Minimax M3 is $0.30 per million input tokens and $1.20 per million output tokens through Zumik. Cache reads are $0.06 per million, a 80% discount on input.

What is Minimax M3's context window?

Minimax M3 supports a 512K-token context window with up to 512K output tokens.

Run Minimax M3 with reuse measured.

Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.