← Back to Guides
Model Pricing Reference
Detailed breakdown of OpenRouter pricing for every model available on Eidolon. Prices are sourced from OpenRouter’s live model catalog and updated regularly. Provider pricing can change without notice.
Model access policy: The current Included catalog is available without a key. New models added in the future will be Premium and require a BYOK OpenRouter key. Without BYOK, users can send 75 messages per day on Included models; BYOK removes that platform message cap.
Scroll the tables horizontally to view all details.
User-Selectable Models
| Model | Tier | Est. $/Turn | Est. $/Month* | Context | 🧠† |
|---|---|---|---|---|---|
| Claude Haiku 4.5 (Claude Haiku 4.5)
| Premium | $0.0240 | ~$14.40 | 200K | — |
| Claude Sonnet 4.5 (Claude Sonnet 4.5)
| Premium | $0.0720 | ~$43.20 | 1000K | — |
| Claude Sonnet 4.6 (Claude Sonnet 4.6)
| Premium | $0.0720 | ~$43.20 | 1000K | — |
| Claude Opus 4.5 (Claude Opus 4.5)
| Premium | $0.1200 | ~$72.00 | 200K | — |
| Claude Opus 4.6 (Claude Opus 4.6)
| Premium | $0.1200 | ~$72.00 | 1000K | — |
| Claude Opus 4.8 (Claude Opus 4.8)
| Premium | $0.1200 | ~$72.00 | 1000K | — |
| Claude Sonnet 5 (Claude Sonnet 5)
| Premium | $0.0480 | ~$28.80 | 1000K | — |
| Claude Fable 5 (Claude Fable 5)
| Premium | $0.2400 | ~$144.00 | 1000K | — |
| Gemini 2.5 Flash (Gemini 2.5 Flash)
| Free | $0.0092 | ~$5.52 | 1048K | — |
| Gemini 2.5 Pro (Gemini 2.5 Pro)
| Premium | $0.0375 | ~$22.50 | 1048K | 🧠 |
| Gemma 4 26B (MoE) (Gemma 4 26B (MoE))
| Free | $0.0017 | ~$1.00 | 262K | — |
| Gemma 4 31B (Gemma 4 31B)
| Free | $0.0021 | ~$1.25 | 262K | — |
| Mistral Large (Mistral Large)
| Free | $0.0100 | ~$6.00 | 262K | — |
| Mistral Medium 3.1 (Mistral Medium 3.1)
| Free | $0.0096 | ~$5.76 | 131K | — |
| Mistral Medium 3.5 (Mistral Medium 3.5)
| Premium | $0.0360 | ~$21.60 | 262K | — |
| Mistral Small 4 (Mistral Small 4)
| Free | $0.0033 | ~$1.98 | 262K | — |
| GPT-4o (GPT-4o)
| Premium | $0.0550 | ~$33.00 | 128K | — |
| GPT-4.1 (GPT-4.1)
| Premium | $0.0440 | ~$26.40 | 1047K | — |
| GPT-4.1 Mini (GPT-4.1 Mini)
| Free | $0.0088 | ~$5.28 | 1047K | — |
| GPT-5 (GPT-5)
| Premium | $0.0375 | ~$22.50 | 400K | 🧠 |
| GPT-5 Mini (GPT-5 Mini)
| Free | $0.0075 | ~$4.50 | 400K | 🧠 |
| GPT-5.1 (GPT-5.1)
| Premium | $0.0375 | ~$22.50 | 400K | 🧠 |
| GPT-5.4 (GPT-5.4)
| Premium | $0.0650 | ~$39.00 | 1050K | 🧠 |
| GPT-5.4 Mini (GPT-5.4 Mini)
| Premium | $0.0195 | ~$11.70 | 400K | 🧠 |
| GPT-5.6 Luna (GPT-5.6 Luna)
| Premium | $0.0026 | ~$1.56 | 1050K | 🧠 |
| GPT-5.6 Luna Pro (GPT-5.6 Luna Pro)
| Premium | $0.0026 | ~$1.56 | 1050K | 🧠 |
| GPT-5.6 Terra (GPT-5.6 Terra)
| Premium | $0.0260 | ~$15.60 | 1050K | 🧠 |
| GPT-5.6 Terra Pro (GPT-5.6 Terra Pro)
| Premium | $0.0260 | ~$15.60 | 1050K | 🧠 |
| GPT-5.6 Sol (GPT-5.6 Sol)
| Premium | $0.1300 | ~$78.00 | 1050K | 🧠 |
| GPT-5.6 Sol Pro (GPT-5.6 Sol Pro)
| Premium | $0.1300 | ~$78.00 | 1050K | 🧠 |
| Qwen 3 VL (Qwen 3 VL)
| Free | $0.0067 | ~$4.04 | 262K | — |
| Qwen 3.5 Flash (Qwen 3.5 Flash)
| Free | $0.0014 | ~$0.86 | 1000K | — |
| Qwen 3.5 35B (Qwen 3.5 35B)
| Free | $0.0067 | ~$4.05 | 262K | — |
| Grok 4.3 (Grok 4.3)
| Premium | $0.0225 | ~$13.50 | 1000K | 🧠 |
| Grok 4.5 (Grok 4.5)
| Premium | $0.0400 | ~$24.00 | 500K | 🧠 |
| DeepSeek V3.2 (DeepSeek V3.2)
| Free | $0.0046 | ~$2.74 | 163K | — |
| DeepSeek Chat V3.1 (DeepSeek Chat V3.1)
| Free | $0.0054 | ~$3.24 | 163K | — |
| DeepSeek Chat V3 0324 (DeepSeek Chat V3 0324)
| Free | $0.0060 | ~$3.61 | 163K | — |
| Kimi K2 (Kimi K2)
| Free | $0.0134 | ~$8.04 | 262K | — |
| Kimi K2.5 (Kimi K2.5)
| Premium | $0.0137 | ~$8.21 | 262K | — |
| Gemini 3.1 Pro Preview (Gemini 3.1 Pro Preview)
| Premium | $0.0520 | ~$31.20 | 1048K | 🧠 |
| Gemini 3.6 Flash (Gemini 3.6 Flash)
| Premium | $0.0180 | ~$10.80 | 1048K | — |
| Gemini 3.7 Flash (Gemini 3.7 Flash)
| Premium | $0.0090 | ~$5.40 | 1048K | — |
| DeepSeek V4 Flash (DeepSeek V4 Flash)
| Free | $0.0015 | ~$0.91 | 1048K | — |
| DeepSeek V4 Flash (0731 snapshot) (DeepSeek V4 Flash (0731 snapshot))
| Free | $0.0025 | ~$1.51 | 1048K | — |
| DeepSeek V4 Pro (DeepSeek V4 Pro)
| Free | $0.0132 | ~$7.92 | 1048K | — |
| Qwen 3.6 Flash (Qwen 3.6 Flash)
| Free | $0.0049 | ~$2.93 | 1000K | — |
| Qwen 3.6 35B (Qwen 3.6 35B)
| Free | $0.0040 | ~$2.38 | 262K | — |
| Qwen 3.8 27B (Qwen 3.8 27B)
| Premium | $0.0127 | ~$7.62 | 262K | 🧠 |
| Qwen 3.8 2.4T (MoE) (Qwen 3.8 2.4T (MoE))
| Premium | $0.0400 | ~$24.00 | 1048K | 🧠 |
| Gemini Pro Latest (Gemini Pro Latest)
| Premium | $0.0520 | ~$31.20 | 1048K | — |
| Gemini Flash Latest (Gemini Flash Latest)
| Premium | $0.0090 | ~$5.40 | 1048K | — |
| GLM 4.7 (GLM 4.7)
| Premium | $0.0091 | ~$5.46 | 204K | — |
| GLM 4.7 Flash (GLM 4.7 Flash)
| Premium | $0.0016 | ~$0.98 | 202K | — |
| GLM 5.1 (GLM 5.1)
| Premium | $0.0196 | ~$11.76 | 204K | 🧠 |
| GLM 5.2 (GLM 5.2)
| Premium | $0.0155 | ~$9.29 | 1048K | 🧠 |
* Estimates based on 20 messages/day, ~14k input + 2k output tokens per turn. 🧠 models include mandatory internal reasoning tokens (billed at the output rate, effort=low) which add ~500–1,500 tokens per turn to the effective billed output.
Technical Details
AdvancedFor power users who want the exact input and output rates per million tokens as reported by OpenRouter.
| Model ID | Input ($/M) | Output ($/M) |
|---|---|---|
| anthropic/claude-haiku-4.5 | $1 | $5 |
| anthropic/claude-sonnet-4.5 | $3 | $15 |
| anthropic/claude-sonnet-4.6 | $3 | $15 |
| anthropic/claude-opus-4.5 | $5 | $25 |
| anthropic/claude-opus-4.6 | $5 | $25 |
| anthropic/claude-opus-4.8 | $5 | $25 |
| anthropic/claude-sonnet-5 | $2 | $10 |
| anthropic/claude-fable-5 | $10 | $50 |
| google/gemini-2.5-flash | $0.3 | $2.5 |
| google/gemini-2.5-pro | $1.25 | $10 |
| google/gemma-4-26b-a4b-it | $0.07 | $0.34 |
| google/gemma-4-31b-it | $0.1 | $0.34 |
| mistralai/mistral-large-2512 | $0.5 | $1.5 |
| mistralai/mistral-medium-3.1 | $0.4 | $2 |
| mistralai/mistral-medium-3-5 | $1.5 | $7.5 |
| mistralai/mistral-small-2603 | $0.15 | $0.6 |
| openai/gpt-4o | $2.5 | $10 |
| openai/gpt-4.1 | $2 | $8 |
| openai/gpt-4.1-mini | $0.4 | $1.6 |
| openai/gpt-5 | $1.25 | $10 |
| openai/gpt-5-mini | $0.25 | $2 |
| openai/gpt-5.1 | $1.25 | $10 |
| openai/gpt-5.4 | $2.5 | $15 |
| openai/gpt-5.4-mini | $0.75 | $4.5 |
| openai/gpt-5.6-luna | $0.1 | $0.6 |
| openai/gpt-5.6-luna-pro | $0.1 | $0.6 |
| openai/gpt-5.6-terra | $1 | $6 |
| openai/gpt-5.6-terra-pro | $1 | $6 |
| openai/gpt-5.6-sol | $5 | $30 |
| openai/gpt-5.6-sol-pro | $5 | $30 |
| qwen/qwen3-vl-235b-a22b-instruct | $0.21 | $1.9 |
| qwen/qwen3.5-flash-02-23 | $0.065 | $0.26 |
| qwen/qwen3.5-35b-a3b | $0.225 | $1.8 |
| x-ai/grok-4.3 | $1.25 | $2.5 |
| x-ai/grok-4.5 | $2 | $6 |
| deepseek/deepseek-v3.2 | $0.269 | $0.4 |
| deepseek/deepseek-chat-v3.1 | $0.25 | $0.95 |
| deepseek/deepseek-chat-v3-0324 | $0.27 | $1.12 |
| moonshotai/kimi-k2-0905 | $0.6 | $2.5 |
| moonshotai/kimi-k2.5 | $0.57 | $2.85 |
| google/gemini-3.1-pro-preview | $2 | $12 |
| google/gemini-3.6-flash | $0.75 | $3.75 |
| google/gemini-3.7-flash | $0.375 | $1.875 |
| deepseek/deepseek-v4-flash | $0.08386 | $0.1677 |
| deepseek/deepseek-v4-flash-0731 | $0.14 | $0.28 |
| deepseek/deepseek-v4-pro | $1.32 | $3.96 |
| qwen/qwen3.6-flash | $0.1875 | $1.125 |
| qwen/qwen3.6-35b-a3b | $0.14 | $1 |
| qwen/qwen3.8-27b | $0.45 | $3.2 |
| qwen/qwen3.8-2.4t-a95b | $2 | $6 |
| ~google/gemini-pro-latest | $2 | $12 |
| ~google/gemini-flash-latest | $0.375 | $1.875 |
| z-ai/glm-4.7 | $0.4 | $1.75 |
| z-ai/glm-4.7-flash | $0.06 | $0.4 |
| z-ai/glm-5.1 | $0.966 | $3.036 |
| z-ai/glm-5.2 | $0.76 | $2.42 |
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: DeepSeek V4 Flash is our current default for new companions.
- Future additions: New models enter the Premium tier and require BYOK.
- Premium gate: High-cost models ($15-$25/M output) are gated to Premium only.
- BYOK Usage: Your key is only used for real-time chat turns. Diaries, dreams, musings, reflections, and other background companion-life workflows use Eidolon's platform key and are not charged to your BYOK.
- Transparency: We add zero markup to OpenRouter rates.
These rates were verified against OpenRouter’s /api/v1/models catalog on August 16, 2026. Model providers change pricing frequently; for the absolute latest rates, always check the OpenRouter dashboard.