API providers, route pricing, availability, and recent reliability signals.
Latency, throughput, and reliability signals from recent traffic.
Effective prices over the last 30 days, with current provider list prices for context.
Daily gateway activity over the last 30 days, with current UTC-day pace projection.
Public apps observed in gateway usage for this model.
Uptime trend for this model over the last 24 hours.
Start calling this model with endpoint-specific examples.
Key dates, capabilities, and model metadata.
Commercial plans and bundled access that currently include this model.
MiniMax: MiniMax M2.7
API providers, route pricing, availability, and recent reliability signals.
Latency, throughput, and reliability signals from recent traffic.
Weighted provider pricing over the last 30 days, with recent route pricing history below.
Public apps observed in gateway usage for this model.
Uptime trend for this model over the last 24 hours.
Start calling this model with endpoint-specific examples.
Key dates, capabilities, and model metadata.
Commercial plans and bundled access that currently include this model.
Choose a supported endpoint, pick a main language, then select the example style you want to copy.
Supported API reference routes for this model.
import Phaseo from '@phaseo/sdk';
const client = new Phaseo({
apiKey: process.env.PHASEO_API_KEY,
});
const response = await client.generateResponse({
"model": "minimax/minimax-m2.7",
"input": "Give me one fun fact about cURL."
});
const outputText = response.output
?.flatMap((item) => item.content ?? [])
.find((item) => item.type === "output_text")
?.text;
console.log(outputText ?? response);Parameters
Aggregated across active providers for the responses route.
Routing will select a compatible provider when a parameter narrows availability, so this list stays model-facing instead of provider-facing.
| Parameter | Description |
|---|---|
temperature | Controls how random token selection can be. |
top_p | Applies nucleus sampling by limiting candidates to a probability mass threshold. |
max_tokens | Caps output length on endpoints and providers that use the max_tokens field name. |
tool_choice | Controls which tool, if any, the model should call. |
tools | Defines callable tools or functions the model can invoke. |
response_format | Requests plain text, JSON, or schema-constrained output formats. |
top_k | Restricts sampling to the top-k candidate tokens on providers that expose it. |
frequency_penalty | Discourages repeated tokens in proportion to how often they already appeared. |
presence_penalty | Encourages the model to explore new wording or topics after they first appear. |
stop | Defines one or more sequences that terminate generation early. |
structured_outputs | Capability signal for reliable schema-constrained output workflows. |
reasoning | Provider-specific reasoning configuration for reasoning-capable APIs. |
18 Mar 2026·4 months ago
18 Mar 2026·4 months ago
Not listed
Not listed
Parameters
Not listed
License
Not listed
Training Tokens
Not listed
Input
Output
6 plans available
Token volume and request traffic for this model over time.
Weighted by routed usage over the last 30 days; provider list prices are shown until usage is available.
Weighted input price
--
Per 1M tokens
Weighted output price
--
Per 1M tokens
 AtlasCloud | $0.3 | $1.2 | -- | |
 DeepInfra | $0.25 | $1 | -- | |
 Fireworks | $0.3 | $1.2 | -- | |
 GMICloud | $0.3 | $1.2 | -- | |
| MiniMax | $0.3 | $1.2 | -- | |
| MiniMax Lightning priority | $0.6 | $2.4 | -- | |
 NovitaAI | $0.3 | $1.2 | -- | |
 Together | $0.3 | $1.2 | -- | |
 Venice | $0.375 | $1.5 | -- |
