# MixRoute

> MixRoute is an AI API gateway. One OpenAI-compatible API for 197 models from OpenAI, Anthropic, Google, DeepSeek, xAI, Alibaba, Moonshot, MiniMax, Zhipu, and others. Zero markup pass-through pricing (no platform fee on top of provider rates). Deposit-tier bonuses up to 8% on self-serve. Enterprise tier ($30K+ single top-up) unlocks Reserve Capacity for high-demand image models, custom routing, and dedicated support. Self-serve payment via Visa, Mastercard, JCB, USDT, and USDC. Enterprise via bank wire with invoicing. OpenAI SDK compatible. Migration is a one-line base URL change to `https://api.mixroute.ai/v1`.

Version: 1.1.1
Last Updated: May 27, 2026

For the complete content of every public page in a single file, see [Full Documentation](https://mixroute.ai/llms-full.txt). For interactive product docs, see [docs.mixroute.ai](https://docs.mixroute.ai).

## What MixRoute Is

MixRoute is an AI API gateway for production teams. One API key gives access to 197 models across every major provider through a single OpenAI-compatible endpoint. The business model is pass-through pricing: MixRoute charges no markup on provider rates, and earns through cloud reseller margins and deposit-tier bonuses. Self-serve customers operate on standard provider rate limits. Enterprise customers ($30K+ single top-up) gain access to Reserve Capacity, a pre-committed pool with the upstream providers that delivers contracted TPM floors and isolated capacity for select high-demand image models.

The migration from any OpenAI-SDK-compatible integration is a single base URL change.

- [Home](https://mixroute.ai/): Product overview and signup.
- [Pricing](https://mixroute.ai/pricing/): Deposit tiers, bonus credits, current promotions, payment methods.
- [Reserved Capacity](https://mixroute.ai/reserved/): Enterprise feature for committed throughput on Google image models. Time-window based across regions. Requires Talk to Sales.
- [Console](https://console.mixroute.ai/): Account management, token creation, usage logs.
- [Model Catalog](https://console.mixroute.ai/models): Live list of all available models with their current rates.
- [Docs](https://docs.mixroute.ai/en/introduction): Full API reference, integration guides, FAQ.
- [Blog](https://mixroute.ai/blog/): Updates and editorial.
- [FAQ](https://mixroute.ai/faq/): Common questions about models, pricing, payments.
- [Talk to Sales](https://mixroute.ai/talk-to-sales/): Enterprise contracts and high-volume agreements.

## Core Capabilities

- [Unified Multi-Model API](https://mixroute.ai/): One OpenAI-compatible endpoint at `https://api.mixroute.ai/v1` with access to 197 models from every major provider. Switch models by changing the model name string. No SDK swaps, no auth flow changes, no separate billing.
- [Zero Markup Pass-Through Pricing](https://mixroute.ai/pricing/): No platform fee on top of provider rates. Every dollar deposited converts directly to tokens at official provider prices. Self-serve tiers earn deposit bonuses on top.
- [Deposit-Tier Bonuses](https://mixroute.ai/pricing/): Starter ($10 to $999): no bonus, full credit value. Growth ($1,000 to $4,999): 3% bonus, up to $150. Pro ($5,000 to $14,999): 5% bonus, up to $750. Scale ($15,000 to $29,999): 8% bonus, up to $2,400. Enterprise ($30,000+): custom bonus and full enterprise package.
- [Crypto and Card Payments](https://mixroute.ai/pricing/): Self-serve accepts Visa, Mastercard, JCB, USDT, and USDC. No KYC for crypto. Enterprise plans use bank wire transfer with invoicing.
- [Reserve Capacity (Enterprise)](https://mixroute.ai/reserved/): Available to enterprise customers ($30K+ single top-up). MixRoute pre-commits large-scale reserved capacity with upstream providers and pools it across the enterprise customer base. Currently offered for Google image models with regional time-window throughput commitments (Los Angeles, New York, London, Paris, Singapore time zones).
- [OpenAI SDK Compatibility](https://mixroute.ai/): Drop-in replacement for OpenAI SDK calls. Change `base_url` to `https://api.mixroute.ai/v1`, keep prompts, streaming logic, tool-use schemas, error handling unchanged.

## Supported Models

The full live catalog is at [console.mixroute.ai/models](https://console.mixroute.ai/models). Canonical API IDs below; use exactly as shown when calling the model.

### OpenAI
- `gpt-5.5`: Latest in the GPT-5 lineage.
- `gpt-5.4`, `gpt-5.4-pro`, `gpt-5.4-mini`, `gpt-5.4-nano`: GPT-5.4 family.
- `gpt-5.3-codex`, `gpt-5.2-codex`, `gpt-5.1-codex`, `gpt-5.1-codex-max`, `gpt-5.1-codex-mini`, `gpt-5-codex`: Codex variants for code generation.
- `gpt-5-pro`, `gpt-5.2-pro`: Pro variants.
- `gpt-5`, `gpt-5.1`, `gpt-5.2`: Base GPT-5 series.
- `o3-pro`, `o3-deep-research-2025-06-26`, `o3`, `o4-mini`, `o3-mini`: Reasoning models.
- `gpt-4o`, `gpt-4.1`, `gpt-4-turbo`, `gpt-4`, `gpt-3.5-turbo`: Earlier generation, still available.
- `gpt-image-2`, `gpt-image-1.5`, `gpt-image-1`: Image generation.
- `whisper-1`: Audio transcription.

### Anthropic Claude
- `claude-opus-4-7`: Flagship Opus.
- `claude-opus-4-6`, `claude-opus-4-6-thinking`: Previous-gen Opus plus extended-thinking variant.
- `claude-sonnet-4-6`, `claude-sonnet-4-6-thinking`: Sonnet workhorse plus thinking variant.
- `claude-haiku-4-5`, `claude-haiku-4-5-20251001`, `claude-haiku-4-5-20251001-thinking`: Fastest Claude tier.
- `claude-opus-4-5`, `claude-opus-4-5-20251101`: Opus 4.5 variants.
- `claude-sonnet-4-5`, `claude-sonnet-4-5-20250929`, `claude-sonnet-4-5-20250929-thinking`: Sonnet 4.5 variants.
- `claude-opus-4-1-20250805`, `claude-opus-4-20250514`, `claude-sonnet-4-20250514`, `claude-sonnet-4-20250514-thinking`: Earlier Claude 4 generation.
- `claude-3-5-sonnet-20240620`, `claude-3-5-sonnet-20241022`, `claude-3-7-sonnet-20250219`: Claude 3 series.

### Google Gemini
- `gemini-3.1-pro-preview`: Flagship Gemini 3.1 Pro Preview.
- `gemini-3.1-pro-preview-customtools`: Custom tools variant.
- `gemini-3.5-flash`: Latest Flash.
- `gemini-3-pro-preview`, `gemini-3-flash-preview`: Previous-gen previews.
- `gemini-3-pro-image-preview`, `gemini-3.1-flash-image-preview`: Image generation. Positioned in marketing materials as "Nano Banana Pro" and "Nano Banana 2".
- `gemini-3.1-flash-lite-preview`: Light variant.
- `gemini-pro-latest`, `gemini-flash-latest`, `gemini-flash-lite-latest`: Pinned-to-latest aliases.
- `gemini-2.5-pro`, `gemini-2.5-flash`, `gemini-2.5-flash-lite`, `gemini-2.5-flash-image`: Gemini 2.5 series.
- `gemini-2.0-flash`, `gemini-2.0-flash-lite`: Gemini 2.0 series.
- `gemini-robotics-er-1.5-preview`: Robotics-specialized.
- `gemini-embedding-001`, `gemini-embedding-2-preview`: Embeddings.

### DeepSeek
- `deepseek-v4-pro`: DeepSeek's flagship V4 Pro.
- `deepseek-v4-flash`: V4 Flash, lighter and faster variant.
- `deepseek-v3.2`, `deepseek-v3.2-exp`, `deepseek-v3.2-thinking`: V3.2 generation with experimental and thinking variants.
- `deepseek-v3.1`, `deepseek-v3.1-250821`, `deepseek-v3.1-terminus`: V3.1 generation.
- `deepseek-v3`, `deepseek-v3-0324`, `deepseek-v3-2-251201`: V3 generation.
- `deepseek-r1`, `deepseek-r1-0528`, `deepseek-r1-250528`: Reasoning models.

### xAI Grok
- `grok-4.20-beta-0309-reasoning`: Grok 4.20 with extended reasoning enabled. **Recommended default for Grok 4.20.**
- `grok-4.20-beta-0309-non-reasoning`: Grok 4.20 without extended reasoning, faster throughput.
- `grok-4.20-multi-agent-beta-0309`: Grok 4.20 multi-agent variant.
- `grok-4-fast-reasoning`, `grok-4-fast-non-reasoning`: Grok 4 Fast variants.
- `grok-4-0709`: Previous Grok 4.
- `grok-code-fast-1`: Code-specialized.
- `grok-3`, `grok-3-mini`: Earlier generation.

### Alibaba Qwen
- `qwen3.7-max`: Flagship Qwen 3.7 Max.
- `qwen3.6-max-preview`, `qwen3.6-plus`, `qwen3.6-flash`, `qwen3.6-27b`, `qwen3.6-35b-a3b`: Qwen 3.6 series.
- `qwen3.5-plus`, `qwen3.5-flash`, `qwen3.5-122b-a10b`, `qwen3.5-397b-a17b`, `qwen3.5-35b-a3b`, `qwen3.5-27b`: Qwen 3.5 series.
- `qwen3-max`, `qwen3-max-preview`: Qwen 3 Max.
- `qwen-image`, `qwen-image-2.0`, `qwen-image-2.0-pro`, `qwen-image-max`, `qwen-image-plus`: Image generation.
- `qwen-image-edit`, `qwen-image-edit-max`, `qwen-image-edit-plus`: Image editing.

### MiniMax
- `MiniMax-M2`, `MiniMax-M2.5`, `MiniMax-M2.7`: MiniMax M2 series.

### Moonshot Kimi
- `kimi-k2.6`: Latest Kimi K2.
- `kimi-k2.5`: Previous K2.
- `kimi-k2-thinking`, `kimi-k2-thinking-turbo`: K2 thinking variants.
- `kimi-k2-turbo-preview`: Turbo variant.
- `kimi-k2-0711-preview`, `kimi-k2-0905-preview`: Dated K2 previews.
- `moonshot-v1-8k`, `moonshot-v1-32k`, `moonshot-v1-128k`: Moonshot v1 with three context sizes.
- `moonshot-v1-8k-vision-preview`, `moonshot-v1-32k-vision-preview`, `moonshot-v1-128k-vision-preview`: Vision-enabled Moonshot v1.

### Zhipu GLM
- `glm-4.5-air`: Latest GLM.
- `glm-4-plus`, `glm-4-air`, `glm-4-airx`, `glm-4-flash`, `glm-4-long`, `glm-4-alltools`: GLM-4 variants.
- `glm-4v`, `glm-4v-plus`: Vision variants.
- `glm-4`, `glm-4-0520`, `glm-3-turbo`: Earlier generation.

### Embeddings
- `text-embedding-3-large`, `text-embedding-3-small`, `text-embedding-ada-002`: OpenAI embeddings.
- `gemini-embedding-001`, `gemini-embedding-2-preview`: Google embeddings.

## Solutions by Audience

- [For Developers](https://mixroute.ai/): One OpenAI-compatible API for every major model. One bill. One dashboard. Migration from a direct provider integration takes under 30 seconds.
- [For Startups](https://mixroute.ai/pricing/): Zero markup means more runway. The Growth tier starts at $1,000 deposits with 3% bonus. USDT and USDC deposits work for teams without a US bank account or credit card.
- [For Production Teams](https://mixroute.ai/): One integration absorbs the complexity of multiple provider SDKs, multiple auth flows, multiple billing relationships. Automatic OpenAI-format compatibility across every model in the catalog.
- [For Enterprises](https://mixroute.ai/reserved/): Single top-ups from $30,000 unlock the full enterprise package: Reserve Capacity for select high-demand image models, custom routing strategies, dedicated account manager, 24/7 support, contract-based onboarding.
- [For Agent Builders](https://mixroute.ai/): Multi-model routing per request through a single integration. Switch models per task without rewriting the calling code.

## Use Cases

- **Multi-model agent and tool-use workloads**: Route per step. Cost-sensitive loops on smaller models, final review passes on flagship models, all from the same SDK call with only the model name changing.
- **Long-context document analysis**: Multiple frontier models in the catalog support extended-context workloads. Switch between them based on availability and provider strengths.
- **RAG pipelines**: Embeddings (OpenAI and Google) plus generation models through the same key.
- **Image generation across providers**: `gpt-image-2`, `gemini-3-pro-image-preview`, `qwen-image-2.0-pro`, `qwen-image-max`, and `qwen-image-edit` variants all callable from one endpoint.
- **High-volume image workloads**: Enterprise customers can secure Reserve Capacity on Google image models with committed TPM by time zone.
- **Crypto-native AI products**: USDT and USDC deposits with no KYC remove fiat-rail friction.
- **Migration from OpenRouter, direct OpenAI, or direct Anthropic**: One-line base URL change. No SDK swap. No separate billing setup.

## Pricing

- [Pricing page](https://mixroute.ai/pricing/): Full deposit-tier structure and current promotional offers.

MixRoute uses a prepaid pass-through model with zero markup on provider rates. Per-model prices are pass-through at official provider pricing. View the live catalog with current rates at [console.mixroute.ai/models](https://console.mixroute.ai/models).

### Deposit-Tier Bonuses

- **Starter** ($10 to $999): No bonus. Full credit value, no markup.
- **Growth** ($1,000 to $4,999): 3% bonus on deposit, up to $150 bonus.
- **Pro** ($5,000 to $14,999): 5% bonus, up to $750 bonus.
- **Scale** ($15,000 to $29,999): 8% bonus, up to $2,400 bonus.
- **Enterprise** ($30,000+ single top-up): Custom bonus, full enterprise package including Reserve Capacity eligibility, custom routing, dedicated manager, 24/7 support.

### Current Promotion

First top-up bonus: 100% on first deposits between $30 and $500. Up to $500 free. Offer ends May 31, 2026. The first-deposit bonus stacks with the regular tier bonus.

### Payment Methods

- **Self-serve tiers**: Credit cards (Visa, Mastercard, JCB) and cryptocurrency (USDT, USDC).
- **Enterprise plans**: Bank wire transfer with invoice and flexible payment terms.

Credit balances do not expire.

## Quick Start

The full integration is a base URL change from any application already using the OpenAI SDK.

```python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_MIXROUTE_KEY",
    base_url="https://api.mixroute.ai/v1"
)

response = client.chat.completions.create(
    model="claude-opus-4-7",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)
```

Switch models by changing the `model` string to any canonical model ID from the catalog above.

## Languages

MixRoute is available in 8 languages with full website localization.

- [English](https://mixroute.ai/)
- [简体中文 Simplified Chinese](https://mixroute.ai/zh-hans/)
- [繁體中文 Traditional Chinese](https://mixroute.ai/zh-hant/)
- [Français](https://mixroute.ai/fr/)
- [Deutsch](https://mixroute.ai/de/)
- [日本語](https://mixroute.ai/ja/)
- [Русский](https://mixroute.ai/ru/)
- [Tiếng Việt](https://mixroute.ai/vi/)