Explore the ecosystem of highly capable AI models ready for integration with the GLYNNE autonomous architecture. From lightning-fast production engines to preview systems.
The absolute best-in-class frontier models available via API on the market today. Ideal for complex reasoning, autonomous agent architectures, and high-impact tasks.
| Model ID | Speed (T/s) | Price | Rate Limits | Context | Max Comp. |
|---|---|---|---|---|---|
GPT-4o gpt-4o | High | $5.00 in / $15.00 out | Tier dependent | 128,000 | 4,096 |
Claude 3.5 Sonnet claude-3-5-sonnet-20240620 | Very High | $3.00 in / $15.00 out | Tier dependent | 200,000 | 8,192 |
Claude 3 Opus claude-3-opus-20240229 | Medium | $15.00 in / $75.00 out | Tier dependent | 200,000 | 4,096 |
Gemini 1.5 Pro gemini-1.5-pro | High | $3.50 in / $10.50 out | Tier dependent | 2,000,000 | 8,192 |
Kimi (Moonshot) moonshot-v1-128k | High | $3.30 in / $9.90 out | Tier dependent | 128,000 | 4,096 |
Mistral Large 2 mistral-large-latest | High | $3.00 in / $9.00 out | Tier dependent | 128,000 | 8,192 |
Production models are intended for use in your production environments. They meet or exceed high standards for speed, quality, and reliability.
| Model ID | Speed (T/s) | Price | Rate Limits | Context | Max Comp. |
|---|---|---|---|---|---|
Llama 3.1 8B llama-3.1-8b-instant | 560 | Contact Sales | Contact Sales | 131,072 | 131,072 |
Llama 3.3 70B llama-3.3-70b-versatile | 280 | Contact Sales | Contact Sales | 131,072 | 32,768 |
GPT OSS 120B openai/gpt-oss-120b | 500 | $0.15 in / $0.60 out | 250K TPM / 1K RPM | 131,072 | 65,536 |
GPT OSS 20B openai/gpt-oss-20b | 1000 | $0.075 in / $0.30 out | 250K TPM / 1K RPM | 131,072 | 65,536 |
Whisper Large V3 whisper-large-v3 | - | $0.111 / hour | 200K ASH / 300 RPM | - | - |
Whisper Large V3 Turbo whisper-large-v3-turbo | - | $0.04 / hour | 400K ASH / 400 RPM | - | - |
Systems are a collection of models and tools that work together to answer a user query.
| Model ID | Speed (T/s) | Price | Rate Limits | Context | Max Comp. |
|---|---|---|---|---|---|
Compound groq/compound | 450 | - | 200K TPM / 200 RPM | 131,072 | 8,192 |
Compound Mini groq/compound-mini | 450 | - | 200K TPM / 200 RPM | 131,072 | 8,192 |
Preview models are intended for evaluation purposes only and should not be used in production environments as they may be discontinued at short notice.
| Model ID | Speed (T/s) | Price | Rate Limits | Context | Max Comp. |
|---|---|---|---|---|---|
Canopy Labs Orpheus Arabic canopylabs/orpheus-arabic-saudi | - | $40.00 / 1M chars | 50K TPM / 250 RPM | 4,000 | 50,000 |
Canopy Labs Orpheus V1 En canopylabs/orpheus-v1-english | - | $22.00 / 1M chars | 50K TPM / 250 RPM | 4,000 | 50,000 |
Prompt Guard 2 22M meta-llama/llama-prompt-guard-2-22m | - | $0.03 in / $0.03 out | 30K TPM / 100 RPM | 512 | 512 |
Prompt Guard 2 86M meta-llama/llama-prompt-guard-2-86m | - | $0.04 in / $0.04 out | 30K TPM / 100 RPM | 512 | 512 |
MiniMax M2.7 minimaxai/minimax-m2.7 | 260 | Contact Sales | Contact Sales | 196,608 | 131,072 |
Safety GPT OSS 20B openai/gpt-oss-safeguard-20b | 1000 | $0.075 in / $0.30 out | 150K TPM / 1K RPM | 131,072 | 65,536 |
Qwen 3.6 27B qwen/qwen3.6-27b | 500 | $0.60 in / $3.00 out | 250K TPM / 1K RPM | 131,072 | 16,384 |
Qwen 3.8 27B qwen/qwen3.8-27b | 450 | $0.80 in / $4.00 out | 250K TPM / 1K RPM | 131,042 | 16,384 |
Grab a coffee. Your first step toward innovation begins by talking with AX, the AXGLYNNE artificial intelligence. Together, you will brainstorm your bottlenecks, and AX will map out how our infrastructure and team can transform those blockers into automated systems.