Is Devstral 2 123B Instruct (2512) or Qwen3 Embedding 8B cheaper?

Qwen3 Embedding 8B is cheaper on output tokens ($0.00 vs $2.00 per 1M).

Which has the larger context window, Devstral 2 123B Instruct (2512) or Qwen3 Embedding 8B?

Devstral 2 123B Instruct (2512) has the larger context window (256K tokens).

Devstral 2 123B Instruct (2512) vs Qwen3 Embedding 8B

Qwen3 Embedding 8B is cheaper on output tokens, while Devstral 2 123B Instruct (2512) offers a larger context window. Choose Devstral 2 123B Instruct (2512) or Qwen3 Embedding 8B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Devstral 2 123B Instruct (2512)	Qwen3 Embedding 8B
Provider	Scaleway	Scaleway
Input / 1M tokens	$0.40	$0.10
Output / 1M tokens	$2.00	$0.00
Context window	256K	33K
Parameters	—	—
Open weights	Yes	No
Released	Jan 2026	—

Devstral 2 123B Instruct (2512) details →Qwen3 Embedding 8B details →

FAQ

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.