AI Rate Card

Qwen3-Coder 480B-A35B Instruct vs Devstral Small 2505: API price and specs

Devstral Small 2505 is 77% cheaper than Qwen3-Coder 480B-A35B Instruct on input price.

Devstral Small 2505 is 85% cheaper than Qwen3-Coder 480B-A35B Instruct on output price.

Devstral Small 2505 is 81% cheaper than Qwen3-Coder 480B-A35B Instruct on a 1M-in / 200k-out workload.

Qwen3-Coder 480B-A35B Instruct has a 104.8% larger context than Devstral Small 2505.

FieldQwen3-Coder 480B-A35B InstructDevstral Small 2505
Lowest input, per 1M$0.22 +340%$0.05
Median input, per 1M$0.36 +502.4%$0.06
Lowest output, per 1M$0.80 +566.7%$0.12
Median output, per 1M$1.58 +615.9%$0.22
Lowest unit price——
Cost of 1M in + 200k out$0.38 +413.5%$0.074
Context262K128K +51.2%
Max output262K4K +98.4%
Providers233 +87%
RegionsEU, US—
Acceptsaudio, image, text, videotext
Returnstexttext
TypeText modelsText models
Free optionnono
Cheapest providergoogle-vertexio-net

Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.

Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.

Providers selling both

deepinfra, io-net, trustedrouter

Frequently asked questions

Which is cheaper, Qwen3-Coder 480B-A35B Instruct or Devstral Small 2505?

Devstral Small 2505 is 77% cheaper than Qwen3-Coder 480B-A35B Instruct on input price. Devstral Small 2505 is 85% cheaper than Qwen3-Coder 480B-A35B Instruct on output price. Devstral Small 2505 is 81% cheaper than Qwen3-Coder 480B-A35B Instruct on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3-Coder 480B-A35B Instruct or Devstral Small 2505?

Qwen3-Coder 480B-A35B Instruct: 262K tokens; Devstral Small 2505: 128K tokens.

Where can I use both Qwen3-Coder 480B-A35B Instruct and Devstral Small 2505?

deepinfra, io-net, trustedrouter