minimax/minimax-m3
- context · $0.2400 / M input tokens · $0.9600 / M output tokens
MiniMax M3 is a MiniMax model route on OurToken for developers who need hosted API access for coding, agent workflows, long-context tasks, multimodal evaluation, and production assistants.
Pricing
Pay-per-use
No upfront costs, pay only for what you use
API Usage
API Access Guide
Code examples
Use the OurToken API endpoint for this model. The examples below use direct HTTP requests and the recommended endpoint for the model family.
curl https://api.ourtoken.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "minimax-m3",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"max_tokens": 256
}'Chat Completions API Reference
Create a chat response with the OpenAI Chat Completions-compatible endpoint. Use https://api.ourtoken.ai/v1 as the SDK Base URL and POST /chat/completions as the endpoint.
Authorization
| Content-Type | application/json |
| Authorization | Bearer YOUR_API_KEY |
Request Body
| Field | Type | Required | Description |
|---|---|---|---|
| model | string | Required | Model ID to call. |
| messages | array<object> | Required | Conversation messages sent to the model. |
| max_tokens | integer | Optional | Maximum number of output tokens. |
| temperature | number | Optional | Sampling temperature. |
| top_p | number | Optional | Nucleus sampling parameter. |
| stream | boolean | Optional | Whether to return a streaming response. |
| stream_options | object | Optional | Additional options for streaming responses. |
| tools | array<object> | Optional | Tools available to the model. |
| tool_choice | string | object | Optional | Controls how the model selects tools. |
| response_format | object | Optional | Controls structured output, such as JSON object responses. |
Response Body
| Field | Type | Required | Description |
|---|---|---|---|
| id | string | Required | Unique chat completion identifier. |
| object | "chat.completion" | Required | Object type returned by the Chat Completions API. |
| created | integer | Required | Unix timestamp when the response was created. |
| model | string | Required | Model that produced the response. |
| choices | array<object> | Required | Candidate responses returned by the model. |
| choices[].message.role | string | Required | Role of the returned chat message. |
| choices[].message.content | string | Optional | Text content in the returned chat message. |
| choices[].finish_reason | string | Optional | Reason generation stopped. |
| usage | object | Optional | Token usage information for the chat completion. |
| usage.prompt_tokens | integer | Optional | Input token count. |
| usage.completion_tokens | integer | Optional | Output token count. |
| usage.total_tokens | integer | Optional | Total token count. |
| usage.prompt_tokens_details | object | Optional | Breakdown of input token usage. |
| usage.prompt_tokens_details.cached_tokens | integer | Optional | Tokens served from cache. |
Model Introduction
MiniMax minimax-m3
MiniMax M3 is a MiniMax model route on OurToken for developers who need hosted API access for coding, agent workflows, long-context tasks, multimodal evaluation, and production assistants.
MiniMax M3 gives teams a MiniMax route for application work where long context, coding workflows, multimodal prompts, and predictable API pricing matter. Use MiniMax M3 API when you want to test MiniMax workflows through the OurToken unified API while keeping model IDs, usage logs, cache costs, and price review in one dashboard.
Why It Looks Great
- 40% of the official MiniMax M3 reference price for input, output, and cache read tokens.
- OpenAI-compatible API setup through the same OurToken endpoint used by other supported models.
- Cache write is listed as $0, while standard input, output, and cache read tokens remain paid categories.
- Useful for evaluating coding agents, long-context tasks, tool-use experiments, and multimodal workflows without separate provider-specific integration.
- Dashboard logs and usage visibility help teams review request cost after launch.
Key Features
- Model ID: minimax-m3
- Input price: $0.2400 per 1M tokens on OurToken
- Output price: $0.9600 per 1M tokens on OurToken
- Cache read price: $0.0480 per 1M tokens on OurToken
- Cache write price: $0 per 1M tokens on OurToken
- Provider: MiniMax
Specifications
MiniMax M3 API Features
Use MiniMax M3 API for unified MiniMax API access, transparent MiniMax M3 pricing, cache visibility, multimodal evaluation, and production agent workflows.
Unified Access
Call MiniMax M3 API through OurToken's unified endpoint while keeping model access, API key management, and usage history in one place. Use minimax-m3 as the model ID and reuse OpenAI-compatible request patterns for coding agents, chat systems, and long-context workflows.
Pricing Clarity
Review MiniMax M3 pricing before rollout. OurToken lists $0.2400 input and $0.9600 output per 1M tokens, so teams can estimate MiniMax M3 price for coding, multimodal prompts, and high-volume assistant workloads.
Cache Costs
Separate cache behavior from normal prompt spend with explicit cache pricing. MiniMax M3 API cache read is listed at $0.0480 per 1M tokens on OurToken, while cache write is $0, which is the MiniMax M3 free case users should understand clearly.
Agent Workflows
Use MiniMax M3 model evaluation for coding agents, tool-use experiments, and multi-step automation. Competitor material highlights agentic capability and OpenCode-style workflows, but teams should validate Opencode MiniMax M3 behavior with their own prompts and acceptance criteria.
Multimodal Context
Evaluate long-context and multimodal tasks such as document review, repository analysis, visual inputs, video-grounded prompts, and multi-turn collaboration. Competitor material describes 1M context and native multimodality, which should be tested in your own production-like workload.
Deployment Choices
Compare hosted API access with searches such as MiniMax M3 HuggingFace and MiniMax M3 Ollama. OurToken focuses on managed API keys, usage logs, pricing visibility, and simple integration rather than local model hosting.
How to Use MiniMax M3 API on OurToken
Create an API key, copy minimax-m3, compare MiniMax M3 pricing, call the unified endpoint, and monitor real usage.
Create API Key
Create an OurToken API key from the dashboard and store it in a secure server-side environment variable. This gives your backend access to MiniMax M3 API while keeping credentials out of client code, notebooks, and public repositories.
01Copy Model ID
Use minimax-m3 as the model value in your request body. Keeping the exact MiniMax M3 model ID in configuration helps developers avoid naming mistakes when comparing MiniMax API routes across local tests, staging traffic, and production deployments.
02Call Endpoint
Send requests to the OurToken unified API endpoint with your API key, model ID, and prompt payload. Existing OpenAI-compatible chat request patterns can usually be reused after changing the base URL, credential, and model value.
03Compare Pricing
Compare MiniMax M3 API pricing before rollout: OurToken lists $0.2400 input, $0.9600 output, and $0.0480 cache read per 1M tokens. Cache write is $0, which is the MiniMax M3 free token category to separate from paid input and output.
04Test Workflows
Run representative coding, agent, long-context, image, and video-input prompts before scaling. If you are evaluating Opencode MiniMax M3 workflows, compare tool behavior, response quality, latency, and token usage against your production acceptance criteria.
05Monitor Cost
After launch, review history logs for request count, input tokens, output tokens, cache read tokens, and spend. Real usage data helps teams compare MiniMax M3 price against actual traffic instead of relying only on benchmark pages or provider listings.
06MiniMax M3 API FAQ
Answers about MiniMax M3 API pricing, MiniMax API access, free cache-write usage, model setup, OpenCode workflows, and deployment comparisons.
