Minimax Minimax M2.5
OpenRouter chatMinimax Minimax M2.5 is an OpenRouter chat model.It supports a 196,608-token context windowwith up to 65,536 output tokens.Input is priced at $0.300/M tokens and output at $1.10/M tokens. Capabilities include function calling, reasoning, prompt caching. Route Minimax Minimax M2.5 via Future AGI's Agent Command Center for unified observability, caching, and 15 routing strategies including cost-optimized fallback.
Estimate Minimax Minimax M2.5 spend
Pick a workload, fine-tune the sliders, and see the monthly bill.
Estimate uses $0.3000/M input · $1.10/M output. Provider pricing changes. Production costs vary with retries, streaming overhead, and tool-call rounds.
Want this for free? Cache + route via Agent Command Center — first 100K requests and 100K cache hits free every month.
Pricing
Per-token rates, expressed in USD per 1M tokens. Verified May 12, 2026.
| Input | $0.300/M | |
| Output | $1.10/M | |
| Cached input | $0.150/M |
Limits
- Context window
- 196,608 tokens
- Max input
- 196,608 tokens
- Max output
- 65,536 tokens
- Modalities
- text
Capabilities
- Function calling ✓ supported
- Parallel tool calls — not advertised
- Vision input — not advertised
- Audio input — not advertised
- Audio output — not advertised
- PDF input — not advertised
- Streaming ✓ supported
- Structured output — not advertised
- Prompt caching ✓ supported
- Reasoning ✓ supported
Where it's strong
- +prompt caching — only 23% of chat models on Future AGI advertise this
Watch out for
- !strict structured output — no JSON-schema enforcement, expect retry loops
Benchmarks pending
We haven't logged public benchmark scores for Minimax Minimax M2.5 yet. Have one to contribute? Submit a source — citations help us prioritise.
Call Minimax Minimax M2.5 via Agent Command Center
One OpenAI-compatible endpoint. Routing, fallback, semantic caching, guardrails, and cost tracking come along for the ride. First 100K requests + 100K cache hits free every month.
agentcc / @agentcc/client). Per-call metadata — provider, cost, latency, cache hit, request id — is returned on x-agentcc-* response headers, so any HTTP client can read it.# Minimax Minimax M2.5 via the Agent Command Center Python SDK
# pip install agentcc
import os
from agentcc import AgentCC
client = AgentCC(
api_key=os.environ["AGENTCC_API_KEY"], # from app.futureagi.com → Settings → API Keys
base_url="https://gateway.futureagi.com/v1",
)
resp = client.chat.completions.create(
model="openrouter/minimax-minimax-m2-5",
messages=[{"role": "user", "content": "Hello, Minimax Minimax M2.5!"}],
)
print(resp.choices[0].message.content)
print(f"Tokens: {resp.usage.total_tokens}")
# Per-call gateway metadata is returned on x-agentcc-* response headers.
# When you need it programmatically, use .with_raw_response to get them:
raw = client.chat.completions.with_raw_response.create(
model="openrouter/minimax-minimax-m2-5",
messages=[{"role": "user", "content": "Same call, but I want the headers."}],
)
print("Provider:", raw.headers.get("x-agentcc-provider"))
print("Latency:", raw.headers.get("x-agentcc-latency-ms"), "ms")
print("Cost: ", raw.headers.get("x-agentcc-cost"), "USD")
print("Cache: ", raw.headers.get("x-agentcc-cache"))AGENTCC_API_KEY with a key fromapp.futureagi.com.Gateway docs ↗Same model on other providers
minimax-minimax-m2-5 is also available via 1 other route. Pricing, regions, and capabilities can differ — compare before routing production traffic.
| Provider | Input / 1M | Output / 1M | Verified |
|---|---|---|---|
| Amazon Bedrock | $0.300/M | $1.20/M | May 12, 2026 |
Compare with similar models
Minimax Minimax M2.5 doesn't have a public Arena ELO score yet, so we group by provider only — quality-tier comparisons need a benchmark.
- OpenAI GPT 4o (2024-05-13)OpenRouter · $5.00/M in · $15.00/M out · 128,000 ctx
- Google Gemini 3.1 Flash Lite previewOpenRouter · $0.250/M in · $1.50/M out · 1,048,576 ctx
- Google Gemini 3.1 Pro previewOpenRouter · $2.00/M in · $12.00/M out · 1,048,576 ctx
- Google Gemini 3 Flash previewOpenRouter · $0.500/M in · $3.00/M out · 1,048,576 ctx
FAQ
How much does Minimax Minimax M2.5 cost?
Input is priced at $0.300 per 1M tokens and output at $1.10 per 1M tokens (OpenRouter, last verified May 12, 2026).
What is the context window of Minimax Minimax M2.5?
Minimax Minimax M2.5 supports a 196,608-token context window with up to 65,536 output tokens.
Does Minimax Minimax M2.5 support function calling?
Yes — Minimax Minimax M2.5 supports function (tool) calling.
Is Minimax Minimax M2.5 good for production?
Minimax Minimax M2.5 is well-suited for prompt caching — only 23% of chat models on Future AGI advertise this. Consider alternatives if you need strict structured output — no JSON-schema enforcement, expect retry loops.
How can I route to Minimax Minimax M2.5 with fallback?
Use Agent Command Center: a single OpenAI-compatible endpoint that supports cost-optimized routing, latency-aware retries, model fallback, and shadow traffic. Configure once, swap models without app changes.
Useful links for Minimax Minimax M2.5
Official sources, independent benchmarks, and pricing aggregators — no random search-engine guesses.
Third-party evals — verify the marketing.
Cross-check our number against the rest of the ecosystem.