Currently listed through these providers:
Model details
MiniMax-M2.7-highspeed
MiniMax-M2.7-highspeed is presented by a third-party guide as the faster hosted variant of the base MiniMax-M2.7 model, sharing the same March 18, 2026 release lineage. The variant sits inside MiniMax's main, non-legacy catalog alongside the base M2.7 entry, while the frontier role in the M-series has moved to MiniMax-M3. Independent Runware inventory also surfaces the model under the MiniMax family as a text-to-text endpoint, reinforcing that the highspeed identifier is a recognized member of the MiniMax lineup rather than a separate architecture.
In practical terms, the highspeed designation is positioned for throughput-sensitive deployments of the M2.7 family, particularly software engineering and agent-style workflows where faster token generation can shorten iteration cycles on tool-use and document tasks. Keeping the same underlying behavior as M2.7 while prioritizing speed makes it a fit for teams already standardized on the M2.7 tool-use profile who want to trade some frontier capability for lower response times on routine agent steps.
Quick Info
Powered by- Provider
- DevPass (LLM Gateway)
- Model key
- minimax-m2.7-highspeed
- Release date
- Mar 18, 2026
- Last updated
- Mar 18, 2026
- Input modalities
- Output modalities
- Capabilities
Cost
- Input token cost
- $0.60
- Output token cost
- $2.40
Limits
- Output tokens
- 131,072 tokens
- Context window
- 204,800 tokens
Transparent token rates
Compare MiniMax-M2.7-highspeed pricing
Rates are shown per one million tokens. Combined means one million input plus one million output tokens.
Latest news about MiniMax-M2.7-highspeed
No articles yet. Fetch the latest news to show it here.
Videos about MiniMax-M2.7-highspeed
More models around MiniMax-M2.7-highspeed
This exact model name is also listed by 10 other providers.