OpenAI compatible API · Attested · Public status

MiniMax: MiniMax M3 vs mistral-medium-3.5-128b

MiniMax: MiniMax M3 has the lower published input-plus-output rate, more Credits provider routes and the lower measured p50 time to first token. Compare price, speed, context, and privacy.

Verify gateway

Onebase URL to migrate

100sof models and routes

0prompt or output logs. Always.

Compare routesProviders, price, context, and policy posture in one view.

Use auto when uptime mattersKeep a primary model and let fallback handle provider failures.

Same API shapeUse the OpenAI client and set the model you want.

Practical read

Monthly evidence

MiniMax: MiniMax M3 has the lower published input-plus-output rate, more Credits provider routes and the lower measured p50 time to first token.

$1.25545/1MMiniMax: MiniMax M3 cheapest route

$11.154158/1Mmistral-medium-3.5-128b cheapest route

901 msMiniMax: MiniMax M3 fastest measured p50 TTFT via together

2370 msmistral-medium-3.5-128b fastest measured p50 TTFT via scaleway

The price comparison adds each route's rate for one million input tokens and one million output tokens; your cost depends on your input/output mix. Prices and live route measurements can change. Use the monthly reports when you need a stable evidence window, then run a small task-specific eval before choosing a production default.

MiniMax: MiniMax M3mistral-medium-3.5-128b

Model idminimax/minimax-m3mistralai/mistral-medium-3.5-128b

Publisher MiniMax Mistral

AI IQ IQ 115#54 —

Context524,288 tokens0 tokens

Credits provider routes151

Cheapest route$1.25545/1M$11.154158/1M

Cached input$0.05275/1M to $0.2532/1MNot published

Privacy posturehas ZDR routeprovider posture varies

Fastest measured p50 TTFT901 ms via together2370 ms via scaleway

Highest measured throughput170 tok/s via atlas-cloudnot enough data

Recent route uptime range100.00%100.00%

Modes chat chat

MiniMax: MiniMax M3 routes

Overview15 Credits routes
PricingInput, cached input, and output rates
BenchmarksTrustedRouter and external sources
ProvidersAll serving providers

mistral-medium-3.5-128b routes

Overview1 Credits routes

Related comparisons

Browse every comparison

MiniMax: MiniMax M3 vs Z.ai: GLM 5.3 Flash49 combined provider routes
MiniMax: MiniMax M3 vs Z.ai: GLM 5.348 combined provider routes
MiniMax: MiniMax M3 vs Z.ai: GLM 5.247 combined provider routes
MiniMax: MiniMax M3 vs MoonshotAI: Kimi K344 combined provider routes
DeepSeek: DeepSeek V4 Flash 0731 vs MiniMax: MiniMax M342 combined provider routes
DeepSeek: DeepSeek V4.1 Flash vs MiniMax: MiniMax M339 combined provider routes
MiniMax: MiniMax M3 vs OpenAI: gpt-oss-120b38 combined provider routes
MiniMax: MiniMax M3 vs Qwen: Qwen3.8 27B33 combined provider routes

Production choice

Pick a default model. Keep fallback enabled.

TrustedRouter is useful when you know the model you want, but still need provider rollover, budget limits, usage records, and a prompt path you can verify.

OpenAI clientPython

client = OpenAI(
    base_url="https://api.trustedrouter.com/v1",
    api_key="sk-tr-v1-..."
)

response = client.chat.completions.create(
    model="minimax/minimax-m3",
    messages=messages,
)

Questions

Which should I use, MiniMax: MiniMax M3 or mistral-medium-3.5-128b?

MiniMax: MiniMax M3 has the lower published input-plus-output rate, more Credits provider routes and the lower measured p50 time to first token.

Is MiniMax: MiniMax M3 or mistral-medium-3.5-128b cheaper?

The current cheapest TrustedRouter route is $1.25545/1M for MiniMax: MiniMax M3 and $11.154158/1M for mistral-medium-3.5-128b. The comparison uses current catalog prices and updates as provider pricing changes.

Is MiniMax: MiniMax M3 or mistral-medium-3.5-128b faster?

Current measured p50 time to first token is 901 ms for MiniMax: MiniMax M3 and 2370 ms for mistral-medium-3.5-128b. These are routed probe measurements, not vendor-advertised speeds, and update as new samples arrive.

Can I test MiniMax: MiniMax M3 and mistral-medium-3.5-128b with the same API?

Yes. Use the same OpenAI-compatible TrustedRouter base URL and API key, then change only the model id between minimax/minimax-m3 and mistralai/mistral-medium-3.5-128b. This makes side-by-side evals possible without maintaining two provider integrations.