💰 Model Pricing Reference
Detailed breakdown of OpenRouter pricing for every model available on Eidolon. Prices are updated regularly based on current API rates.
💡 Scroll the tables horizontally to view all details.
🤖 User-Selectable Models
| Model | Tier | Est. $/Turn | Est. $/Month* | Context |
|---|---|---|---|---|
| Alibaba Qwen 3.5 Flash (Qwen 3.5 Flash) | Free | $0.0022 | ~$1.32 | 1M |
| Alibaba Qwen 3.5 35B (Qwen 3.5 35B) | Free | $0.0049 | ~$2.90 | 262K |
| xAI Grok 4 Fast (Grok 4 Fast) | Free | $0.0038 | ~$2.28 | 2M |
| xAI Grok 4.1 Fast (Grok 4.1 Fast) | Free | $0.0038 | ~$2.28 | 2M |
| Alibaba Qwen 3 VL (Qwen 3 VL) | Free | $0.0046 | ~$2.74 | 262K |
| OpenAI GPT-5 Mini (GPT-5 Mini) | Free | $0.0075 | ~$4.50 | 400K |
| Google Gemini 2.5 Flash (Gemini 2.5 Flash) | Free | $0.0092 | ~$5.52 | 1M |
| Mistral AI Mistral Medium 3.1 (Mistral Medium 3.1) | Free | $0.0096 | ~$5.76 | 131K |
| Mistral AI Mistral Large (Mistral Large) | Free | $0.0100 | ~$6.00 | 262K |
| Anthropic Claude Haiku 4.5 (Claude Haiku 4.5) | Free | $0.0240 | ~$14.40 | 200K |
| OpenAI GPT-5 (GPT-5) | Premium | $0.0375 | ~$22.50 | 400K |
| OpenAI GPT-5.1 (GPT-5.1) | Premium | $0.0375 | ~$22.50 | 400K |
| Google Gemini 2.5 Pro (Gemini 2.5 Pro) | Premium | $0.0375 | ~$22.50 | 1M |
| OpenAI GPT-4o (GPT-4o) | Free | $0.0550 | ~$33.00 | 128K |
| Anthropic Claude Sonnet 4.5 (Claude Sonnet 4.5) | Premium | $0.0720 | ~$43.20 | 1M |
| Anthropic Claude Sonnet 4.6 (Claude Sonnet 4.6) | Premium | $0.0720 | ~$43.20 | 1M |
| xAI Grok 4 (Grok 4) | Premium | $0.0720 | ~$43.20 | 256K |
| Anthropic Claude Opus 4.5 (Claude Opus 4.5) | Premium | $0.1200 | ~$72.00 | 200K |
| Anthropic Claude Opus 4.6 (Claude Opus 4.6) | Premium | $0.1200 | ~$72.00 | 1M |
* These estimates are based on an average of 20 messages per day, with each turn consuming approximately 14k input tokens and 2k output tokens.
⚙️ Technical Details
AdvancedFor power users who want the exact input and output rates per million tokens as reported by OpenRouter.
| Model ID | Input ($/M) | Output ($/M) |
|---|---|---|
| qwen/qwen3.5-flash-02-23 | $0.10 | $0.40 |
| qwen/qwen3.5-35b-a3b | $0.16 | $1.30 |
| x-ai/grok-4-fast | $0.20 | $0.50 |
| x-ai/grok-4.1-fast | $0.20 | $0.50 |
| qwen/qwen3-vl-235b-a22b-instruct | $0.20 | $0.88 |
| openai/gpt-5-mini | $0.25 | $2.00 |
| google/gemini-2.5-flash | $0.30 | $2.50 |
| mistralai/mistral-medium-3.1 | $0.40 | $2.00 |
| mistralai/mistral-large-2512 | $0.50 | $1.50 |
| anthropic/claude-haiku-4.5 | $1.00 | $5.00 |
| openai/gpt-5 | $1.25 | $10.00 |
| openai/gpt-5.1 | $1.25 | $10.00 |
| google/gemini-2.5-pro | $1.25 | $10.00 |
| openai/gpt-4o | $2.50 | $10.00 |
| anthropic/claude-sonnet-4.5 | $3.00 | $15.00 |
| anthropic/claude-sonnet-4.6 | $3.00 | $15.00 |
| x-ai/grok-4 | $3.00 | $15.00 |
| anthropic/claude-opus-4.5 | $5.00 | $25.00 |
| anthropic/claude-opus-4.6 | $5.00 | $25.00 |
🏷️ Tier Definitions
-
Free Tier:
Usage is fully covered by the platform using our system key. No cost to you.
-
Premium Tier:
Requires your own OpenRouter API Key. You pay OpenRouter directly for what you use.
📝 Cost Management
- Default Model: Mistral Medium 3.1 is our current balanced default.
- Premium gate: High-cost models ($15-$25/M output) are gated to Premium only.
- BYOK Usage: Your key is only used for chat turns. Platform tasks (diaries, dreams) always use the platform key.
- Transparency: We add zero markup to OpenRouter rates.
These rates are accurate as of March 13, 2026. Model providers change pricing frequently; for the absolute latest rates, always check the OpenRouter dashboard.