Synrouter Docs
Models
Synrouter exposes a configured model catalog through the OpenAI-compatible models endpoint. Use this endpoint as the source of truth for available model IDs.
List available models
Call GET /v1/models to fetch the current model list. The response is OpenAI-compatible — drop it into any OpenAI SDK.
bash
1curl https://synrouter.ai/api/v1/models \
2 -H "Authorization: Bearer sk-sr-..."
json
1{
2 "object": "list",
3 "data": [
4 {
5 "id": "deepseek/deepseek-v4-flash",
6 "object": "model",
7 "owned_by": "deepseek"
8 },
9 {
10 "id": "anthropic/claude-sonnet-4.6",
11 "object": "model",
12 "owned_by": "anthropic"
13 }
14 ]
15}
Model ID format
Synrouter model IDs use the provider/model-name format. This makes it easy to identify the provider and select the right model for your compatibility mode:
- OpenAI-compatible requests accept any model ID — use
deepseek/deepseek-v4-flash,openai/gpt-5.5, etc. - Anthropic-compatible requests should use Anthropic model IDs like
anthropic/claude-sonnet-4.6.
Configured models
The following models are currently available through Synrouter. For live pricing and weekly usage data, visit the Models dashboard.
| Model ID | Provider | Description |
|---|---|---|
| anthropic/claude-opus-4.8 | Anthropic | Anthropic’s next-generation frontier model — the most capable Opus ever with breakthrough reasoning,… |
| anthropic/claude-opus-4.8-fast | Anthropic | A faster variant of Claude Opus 4.8, delivering next-gen reasoning quality with reduced latency for … |
| anthropic/claude-opus-4.7 | Anthropic | Anthropic’s latest frontier model with state-of-the-art reasoning, extended thinking, and superior i… |
| anthropic/claude-opus-4.7-fast | Anthropic | A faster variant of Claude Opus 4.7, delivering frontier-quality responses with reduced latency for … |
| anthropic/claude-sonnet-4.6 | Anthropic | Anthropic’s best-balanced model for coding agents — fast, cost-effective, and capable of handling co… |
| anthropic/claude-opus-4.6 | Anthropic | Anthropic’s deep-reasoning flagship with exceptional performance on hard architectural problems, mat… |
| anthropic/claude-opus-4.6-fast | Anthropic | A faster variant of Claude Opus 4.6 optimized for lower latency while retaining strong reasoning cap… |
| anthropic/claude-haiku-4.5 | Anthropic | Anthropic’s fastest and most affordable model, ideal for simple queries, classification, and high-th… |
| deepseek/deepseek-v4-pro | DeepSeek | DeepSeek’s flagship model with exceptional reasoning and coding ability at a fraction of the cost of… |
| deepseek/deepseek-v4-flash | DeepSeek | DeepSeek’s fast and affordable model — the default recommendation for most agent workloads with exce… |
| deepseek/deepseek-v4-flash-free | DeepSeek | Free-tier access to DeepSeek V4 Flash with slightly reduced throughput. Great for testing and low-pr… |
| google/gemini-3.5-flash | Google’s latest fast multimodal model with strong performance across text, code, and vision tasks at… | |
| google/gemini-3.1-flash-lite-preview | Google’s cost-optimized flash model delivering solid performance for simpler tasks at the lowest pri… | |
| google/gemini-3.1-pro-preview | Google’s most capable Gemini model with advanced reasoning, long-context understanding, and superior… | |
| google/gemini-3.1-flash-image-preview | A Gemini Flash variant optimized for image generation and vision tasks, combining text and image cap… | |
| minimax/minimax-m3 | MiniMax | MiniMax’s latest multimodal foundation model with native image and video understanding, 1M-token con… |
| minimax/minimax-m2.7 | MiniMax | MiniMax’s latest model with strong general capabilities, competitive pricing, and solid performance … |
| moonshotai/kimi-k2.6 | Moonshot AI | Moonshot AI’s Kimi K2.6 with extremely long context handling and strong Chinese-English bilingual pe… |
| openai/gpt-5.5-pro | OpenAI | OpenAI’s most advanced model with exceptional depth across all domains — coding, reasoning, math, an… |
| openai/gpt-5.5 | OpenAI | OpenAI’s latest generation model with strong general performance and improved efficiency over previo… |
| openai/gpt-5.4-image-2 | OpenAI | OpenAI’s image-capable model combining GPT-5.4 text intelligence with native image generation and ed… |
| qwen/qwen3.7-max | Qwen | Alibaba's flagship Qwen3.7 model with 256K context, native Dashscope support, and strong multilingua… |
| qwen/qwen3.6-max-preview | Qwen | Alibaba’s most capable Qwen model with strong coding, reasoning, and multilingual support, especiall… |
| qwen/qwen3.6-flash | Qwen | Qwen’s fast and efficient model delivering solid performance for everyday tasks at a competitive pri… |
| x-ai/grok-4.3 | xAI | xAI’s latest Grok model with strong reasoning, real-time knowledge integration, and a distinctive pe… |
| z-ai/glm-5.2 | Z.ai | Z.ai’s latest GLM-5.2 with improved reasoning, stronger multilingual performance, and efficient infe… |
| z-ai/glm-5.1 | Z.ai | Z.ai’s GLM-5.1 with competitive general capabilities, strong Chinese performance, and efficient infe… |