minimax-m3Fireworks AI
- api
- chat
- hosting
- US
- model lab
- MiniMax
- weights
- open
- added
- May 2026
- model id
- fireworks/minimax-m3
capabilities 3/8
3 providers serve minimax-m3. This page is one of them. Compare all endpoints
- input
- $0.30
- output
- $1.20
- cache write
- -
- cache read
- $0.06
worked cost
| volume | cost |
|---|---|
| 100K in + 10K out | $0.0420 |
| 1M in + 100K out | $0.42 |
| 10M in + 1M out | $4.20 |
Requesty charges what the upstream provider charges, with no markup and no per-request fee. Prompt caching and smart routing cut the effective cost further on repeated context. Gateway pricing
- median ttft
- 1.03s
- median tok/s
- 232.0
- blended /1M
- $0.15
- cache hit
- 80.6%
- answered
- 99.80%
Weekly aggregates from production traffic routed through Requesty to this endpoint. A metric with no qualifying sample is left out rather than filled in. Compare against the other providers
| eval | Score as a share of 100 | /100 |
|---|---|---|
| GPQA Diamond | 92.9 | |
| τ²-Bench | 88.9 | |
| Coding Index | 58.6 | |
| SciCode | 47.1 | |
| Terminal-Bench Hard | 42.4 | |
| Humanity's Last Exam | 39.0 | |
| Intelligence Index | 29.6 | |
| 7 evals | mean | 56.9 |
Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2026-06-01.
- retention
- none
- trains on prompts
- no
- hosted in
- US
Terms are the provider's, not Requesty's: routing a request here puts it under them. Fireworks Privacy Policy
Need every request to stay in one jurisdiction? EU hosting routes only through EU-hosted providers.
fireworks/minimax-m3this id pins the fireworks ai deployment, with no routing and no failover. the managed id on the canonical page routes across all 3 providers instead
from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create( model="fireworks/minimax-m3", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ],) print(response.choices[0].message.content)
Change the base url to https://router.requesty.ai/v1, use your Requesty key, set the model to the id above. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog. Browse all models
MiniMax-M3 is a native multimodal model with 512K context running ~428B parameters and ~23B activated parameters. It brings native multimodality, enabling deeper semantic fusion across text, image, and video. M3 also introduces MiniMax Sparse Attention (MSA) to improve long context efficiency, achieving frontier-level performance across long-horizon agentic benchmarks, excelling in both coding and cowork.
questions 6
How much does minimax-m3 cost?
What is the context window of minimax-m3?
How does minimax-m3 perform on benchmarks?
What can minimax-m3 do?
How do I use minimax-m3 with the OpenAI SDK?
Can I run minimax-m3 through Requesty?
more from fireworks ai 8
| endpoint | ctx | in /M |
|---|---|---|
| deepseek-v4.1-flash | 1.0M | $0.22 |
| deepseek-v4-flash-vision-exp | 1.0M | $0.22 |
| glm-5.3-flash | 1.0M | $0.15 |
| glm-5.3 | 1.0M | $1.40 |
| nemotron-lightning-3.5-30b-a3b | 262K | $0.05 |
| deepseek-v4-pro-0813 | 1M | $1.32 |
| muse-glimmer-30b | 131K | $0.35 |
| qwen3.8-max | 1M | $2.00 |
call minimax-m3 through one endpoint
One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover when a provider degrades, and prompt caching built in. Methodology