Infer by Flow7
As of Nov 22, 2026, Infer by Flow7 lists 10 supported models in the Sovyron catalog, including GPT-6.1 Sol (Low cost), Claude Sonnet 5.5 (Low cost), Claude Opus 5.5 (Low cost), Grok 4.7 (Low cost) and GPT-6 Astra (Low cost) across the gpt-sol, claude-sonnet, claude-opus, grok, gpt-astra and gemini-flash families. The cheapest rate in the table is GPT-6.1 Sol (Low cost) at $0.89 per 1M output tokens, the priciest GPT-6 Astra (Official API) at $62.5. On a 3:1 input:output blend the metered rates span $0.4025–$25 per 1M tokens, and every price is Infer by Flow7's own, normalized to USD. Offer mix: metered per-token rates only, with no free-tier or subscription offers in the catalog. Open a model to compare it with the cheapest offer across all providers.
Supported models and pricing
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|---|---|---|---|---|
| GPT-6.1 Sol (Low cost) | $0.24 | $0.89 | $0.02 | 272k | Sep 29, 2026 |
| Claude Sonnet 5.5 (Low cost) | $0.99 | $4.91 | $0.1 | 1.0M | Sep 28, 2026 |
| Claude Opus 5.5 (Low cost) | $1.97 | $9.81 | $0.1 | 1.0M | Sep 22, 2026 |
| Grok 4.7 (Low cost) | $0.44 | $1.3 | $0.11 | 200k | Sep 21, 2026 |
| GPT-6 Astra (Low cost) | $1.18 | $4.42 | $0.12 | 272k | Sep 4, 2026 |
| GPT-6 Astra (Official API) | $12.5 | $62.5 | $1.25 | 272k | Sep 4, 2026 |
| Gemini 3.8 Flash (Low cost) | $0.45 | $2.21 | $0.05 | 1.0M | Sep 2, 2026 |
| Claude Fable 5.1 (Low cost) | $4.91 | $24.53 | $0.13 | 1.0M | Sep 1, 2026 |
| GPT-5.6 Sol (Official API) | $2.5 | $12.5 | $0.25 | 272k | Jul 9, 2026 |
| Gemini 3.1 Pro Preview (Low cost) | $1.18 | $5.3 | $0.12 | 200k | Feb 19, 2026 |