Verified 2026-11-18 · rates follow the live catalog
Openference is one OpenAI- and Anthropic-compatible endpoint in front of 55 models from 15 providers (Openference (1), DeepSeek (6), Baidu (1), Z.ai (7), Google (4), OpenAI (9), Tencent (2), Moonshot AI (月之暗面) (2), Xaoimi MiMo (3), Mistral AI (1), Minimax (1), Meta (1), Qwen (3), StepFun (1), Anthropic (13)). Instead of holding accounts, keys and billing relationships with each of them, you configure one base URL and one key.
Published input rates start at $0.06 per million tokens and reach $10 per million — a 167× spread, which makes model choice a far bigger cost lever than plan tier.
Both API formats are served from one host and one key, so a tool that speaks either works without a translation layer:
https://api.openference.com/v1/chat/completionshttps://api.openference.com/v1/messagesSet OPENAI_BASE_URL or ANTHROPIC_BASE_URL to that host and keep the client library you already use.
| Model | Provider | Context | Input / 1M | Output / 1M | Cached input / 1M |
|---|---|---|---|---|---|
| Auto | Openference | 1.0M | $0.37 | $1 | — |
| DeepSeek-V4-Flash-0731 | DeepSeek | 1.0M | $0.44 | $1.32 | $0.01 |
| DeepSeek V4.1 Flash | DeepSeek | 1.0M | $0.30 | $1.20 | $0.01 |
| DeepSeek V4.1 Flash 1017 | DeepSeek | 1.0M | $0.30 | $1.20 | $0.01 |
| DeepSeek V4.1 Flash 1017 Free | DeepSeek | 1.0M | $0 | $0 | $0 |
| DeepSeek V4 Pro | DeepSeek | 1.0M | $1.32 | $3.96 | $0.13 |
| ERNIE 5.5 Flash Preview | Baidu | 1.0M | $0.28 | $1.13 | $0.03 |
| GLM-4.7-Flash | Z.ai | 128K | $0.06 | $0.40 | — |
| Gemma 4 26B | 250K | $0.10 | $0.30 | — | |
| GPT-OSS 120B | OpenAI | 128K | $0.35 | $0.75 | — |
| GLM-5.1 | Z.ai | 256K | $1.40 | $4.40 | $0.26 |
| GLM-5.2 | Z.ai | 256K | $1.40 | $4.40 | $0.26 |
| GLM-5.3 | Z.ai | 1.0M | $1.40 | $4.40 | $0.26 |
| Hy4 | Tencent | 1.0M | $0.83 | $2.50 | $0.04 |
| Hy4 Flash | Tencent | 1.0M | $0.07 | $0.28 | $0.00 |
| Kimi K2.7 Code | Moonshot AI (月之暗面) | 256K | $0.95 | $4 | — |
| Kimi K3 | Moonshot AI (月之暗面) | 1.0M | $3 | $15 | $0.30 |
| MiMo-V2.5 | Xaoimi MiMo | 1.0M | $0.14 | $0.28 | — |
| MiMo-V2.6-Flash | Xaoimi MiMo | 1.0M | $0.14 | $0.28 | $0.00 |
| MiMo-V2.6-Pro | Xaoimi MiMo | 1.0M | $0.43 | $0.87 | $0.00 |
| MiniMax M2.7 | Mistral AI | 200K | $0.30 | $1.20 | — |
| MiniMax M3 | Minimax | 1.0M | $0.30 | $1.20 | $0.06 |
| GPT-OSS 20B | OpenAI | 128K | $0.20 | $0.30 | — |
| Llama 4 Scout | Meta | 128K | $0.27 | $0.85 | — |
| GLM-5.3-Flash | Z.ai | 1.0M | $0.15 | $0.50 | $0.03 |
| GLM-5.3-Flash-Free | Z.ai | 1.0M | $0 | $0 | $0 |
| GLM-5.3-Flash-Uncensored | Z.ai | 1.0M | $0.25 | $0.75 | $0.10 |
| Qwen3.5 | Qwen | 256K | $0.30 | $1.20 | — |
| Qwen3.8 27b | Qwen | 256K | $0.45 | $3.20 | — |
| Step-5 Preview | StepFun | 1.0M | $1 | $2.70 | $0.10 |
| Claude Fable 5.2 | Anthropic | 1.0M | $8 | $40 | $0.20 |
| Claude Fable 5.1 | Anthropic | 1.0M | $10 | $50 | $0.25 |
| Claude Fable 5 | Anthropic | 1.0M | $10 | $50 | $1 |
| Claude Opus 5.5 | Anthropic | 1.0M | $4 | $20 | $0.20 |
| Claude Opus 5 | Anthropic | 1.0M | $5 | $25 | $0.50 |
| Claude Opus 4.8 | Anthropic | 1.0M | $5 | $25 | $0.50 |
| Claude Opus 4.7 | Anthropic | 1.0M | $5 | $25 | $0.50 |
| Claude Opus 4.6 | Anthropic | 1.0M | $5 | $25 | $0.50 |
| Claude Sonnet 5.5 | Anthropic | 1.0M | $2 | $10 | $0.10 |
| Claude Sonnet 5 | Anthropic | 1.0M | $2 | $10 | $0.20 |
| Claude Sonnet 4.6 | Anthropic | 1.0M | $3 | $15 | $0.30 |
| Claude Haiku 5.5 | Anthropic | 1.0M | $0.10 | $0.50 | $0.01 |
| Claude Haiku 4.5 | Anthropic | 195K | $1 | $5 | $0.10 |
| Gemini 3.8 Flash | 1.0M | $0.75 | $3.75 | $0.07 | |
| Gemini 3 Pro Image | 128K | $0 | $134 | — | |
| Gemini 3.1 Flash Image | 128K | $0 | $67 | — | |
| GPT-6 Luna | OpenAI | 1.1M | $0.10 | $0.50 | $0.01 |
| GPT-6.1 Terra | OpenAI | 1.1M | $1 | $5 | $0.05 |
| GPT-6.1 Sol | OpenAI | 1.1M | $2 | $10 | $0.10 |
| GPT-6 Astra | OpenAI | 1.1M | $10 | $50 | $1 |
| GPT-6 Sol | OpenAI | 1.1M | $0.50 | $2.50 | $0.05 |
| GPT-6.2 Sol | OpenAI | 1.1M | $0.75 | $3.50 | $0.07 |
| GPT-6.2 Astra | OpenAI | 1.1M | $3.50 | $17.50 | $0.35 |
| Qwen3.8 Flash | Qwen | 1M | $0.15 | $0.47 | $0.02 |
| DeepSeek V4.1 Flash 1017 Uncensored | DeepSeek | 1.0M | $0.30 | $1.20 | $0.03 |
| Plan | Price |
|---|---|
| Minion | $20 / month |
| Boss | $80 / month |
Every plan draws from the same catalog at the rates above. Usage beyond a plan's allowance bills as on-demand credits at those same catalog rates — there is no separate overage price list.
A gateway earns its place only by removing work you would otherwise do yourself. Three things are genuinely awkward to build in an application:
openai client do not need separate integrations.What a gateway does not fix: it does not make a model better than it is, and it adds a network hop. If you use one provider and one model, calling that provider directly is simpler and faster.
Model catalog · Pricing · Comparisons · Cost guides · Integration guides · FAQ
Guides: GLM coding plan alternative · Free AI API · LLM gateway · LLM proxy · Cheap AI API · OpenAI-compatible API
Model APIs: GLM API · DeepSeek API · Kimi API · Qwen API · MiniMax API