CheapestToken
19 modelsProvider docs
As of Nov 22, 2026, CheapestToken lists 19 supported models in the Sovyron catalog, including GPT-6.1 Terra, MiniMax-M3.1-Flash, DeepSeek V4.1 Flash 1017, Nemotron 3.5 Super VL and GPT-6.1 Sol across the gpt-terra, minimax-m-flash, deepseek-flash, nemotron-super, gpt-sol and gpt-luna families. The cheapest rate in the table is GPT-6 Luna at $0.5 per 1M output tokens, the priciest GPT-6 Astra at $35. On a 3:1 input:output blend the metered rates span $0.2–$16.25 per 1M tokens, and every price is CheapestToken'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
19 of 19 models
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|---|---|---|---|---|
| GPT-6.1 Terra | $1 | $4 | $0.05 | 1.1M | Oct 26, 2026 |
| MiniMax-M3.1-Flash | $0.15 | $0.6 | $0.01 | 1.0M | Oct 19, 2026 |
| DeepSeek V4.1 Flash 1017 | $0.3 | $1.2 | $0.006 | 1.0M | Oct 17, 2026 |
| Nemotron 3.5 Super VL | $0.3 | $0.65 | $0.06 | 1.0M | Oct 15, 2026 |
| GPT-6.1 Sol | $2 | $8 | $0.1 | 1.1M | Sep 29, 2026 |
| GPT-6 Luna | $0.1 | $0.5 | $0.01 | 1.1M | Sep 22, 2026 |
| GPT-6 Sol | $2 | $8 | $0.2 | 1.1M | Sep 22, 2026 |
| Grok 4.7 | $2 | $4.5 | $0.5 | 500k | Sep 21, 2026 |
| GPT-6 Astra | $10 | $35 | $1 | 1.1M | Sep 4, 2026 |
| GLM5.3 Flash | $0.15 | $0.5 | $0.03 | 1.0M | Aug 26, 2026 |
| GLM5.3 | $1.4 | $3.96 | $0.26 | 1.0M | Aug 14, 2026 |
| DeepSeek V4 Pro 0813 | $1.32 | $3.56 | $0.04 | 1.0M | Aug 13, 2026 |
| Grok 4.6 | $2 | $4.5 | $0.5 | 200k | Aug 12, 2026 |
| Qwen3.8 Max | $2 | $4.5 | $0.2 | 1.0M | Aug 3, 2026 |
| Kimi K3 | $4 | $12 | $1 | 1.0M | Jul 16, 2026 |
| GPT-5.6 Luna | $0.2 | $1.2 | $0.02 | 1.1M | Jul 9, 2026 |
| GPT-5.6 Sol | $4 | $16 | $0.4 | 1.1M | Jul 9, 2026 |
| GPT-5.6 Terra | $2 | $10.2 | $0.2 | 1.1M | Jul 9, 2026 |
| GPT-5.5 | $5 | $24 | $0.5 | 1.1M | Apr 23, 2026 |