Devstral-2-123B-Instruct-2512-int4-AutoRound
InferXOpen weights
Devstral-2-123B-Instruct-2512-int4-AutoRound by InferX costs $0.00 per 1M input tokens and $0.00 per 1M output tokens, with a 128K-token context window.
Pricing
Input (per 1M tokens)
$0.00
Output (per 1M tokens)
$0.00
Cached input (per 1M)
—
Specifications
- Provider
- InferX
- Context window
- 128K tokens
- Parameters
- —
- Released
- Dec 2025
- Open weights
- Yes
- Frontier model
- No
Compare Devstral-2-123B-Instruct-2512-int4-AutoRound with…
Devstral-2-123B-Instruct-2512-int4-AutoRound vs Gemma 4 31B IT FP8$0.00/1MDevstral-2-123B-Instruct-2512-int4-AutoRound vs Qwen3.6-35B-A3B-fp8-no-thinking$0.00/1MDevstral-2-123B-Instruct-2512-int4-AutoRound vs Qwen3.6 27B FP8$0.00/1MDevstral-2-123B-Instruct-2512-int4-AutoRound vs Qwen3 Coder Next FP8$0.00/1MDevstral-2-123B-Instruct-2512-int4-AutoRound vs Qwen3-Coder-Next-FP8-no-thinking$0.00/1MDevstral-2-123B-Instruct-2512-int4-AutoRound vs mimo-v25$0.00/1M
FAQ
Pricing is per 1M tokens (USD); confirm with the provider before production use.