evroc
16 modelsProvider docs
As of Nov 6, 2026, evroc lists 16 supported models in the Sovyron catalog, including Qwen3.8 27B, GLM-5.2, roc, Mistral Medium 3.5 and Kimi K2.6 across the qwen, glm, mistral-medium, kimi-k2, gemma and gpt-oss families. The cheapest rate in the table is Whisper Large v3 Turbo at $0.0023 per 1M output tokens, the priciest roc at $11.516. On a 3:1 input:output blend the metered rates span $0.0023–$5.0352 per 1M tokens, and every price is evroc'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
16 of 16 models
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|---|---|---|---|---|
| Qwen3.8 27B | $0.87 | $3.5 | — | 262k | Aug 14, 2026 |
| GLM-5.2 | $1.4375 | $5.75 | — | 524k | Jun 13, 2026 |
| roc | $2.875 | $11.516 | — | 262k | Jun 6, 2026 |
| Mistral Medium 3.5 | $1.725 | $6.9 | — | 262k | Apr 29, 2026 |
| Kimi K2.6 | $1.4375 | $5.75 | — | 262k | Apr 20, 2026 |
| Qwen3.6 35B-A3B | $0.345 | $1.38 | — | 262k | Apr 17, 2026 |
| Gemma 4 26B A4B IT | $0.144 | $0.575 | — | 262k | Apr 2, 2026 |
| GPT OSS 120B | $0.23 | $0.92 | — | 66k | Aug 5, 2025 |
| Qwen3 Reranker 4B | $0.0575 | free | — | 32k | Jul 30, 2025 |
| Qwen3 Embedding 8B | $0.115 | $0.115 | — | 41k | Jun 5, 2025 |
| Voxtral Small 24B | — | — | — | 32k | Mar 1, 2025 |
| Llama-3.3-70B-Instruct | $1.15 | $1.15 | — | 128k | Dec 6, 2024 |
| KB Whisper | — | — | — | 448 | Oct 1, 2024 |
| Whisper Large v3 Turbo | $0.0023 | $0.0023 | — | 448 | Oct 1, 2024 |
| E5 Multi-Lingual Large Embeddings 0.6B | $0.114 | $0.114 | — | 512 | Jun 1, 2024 |
| Whisper 3 Large | $0.0023 | $0.0023 | — | 448 | Nov 6, 2023 |