AI Rate CardDevstral 2 123B vs GLM-5.3: API price and specs
Devstral 2 123B is 26% cheaper than GLM-5.3 on input price.
GLM-5.3 is 11% cheaper than Devstral 2 123B on output price.
Devstral 2 123B is 11% cheaper than GLM-5.3 on a 1M-in / 200k-out workload.
GLM-5.3 has a 309.6% larger context than Devstral 2 123B.
| Field | Devstral 2 123B | GLM-5.3 |
|---|---|---|
| Lowest input, per 1M | $0.14 | $0.19 +35.6% |
| Median input, per 1M | $0.40 | $1.40 +250% |
| Lowest output, per 1M | $0.72 +12.5% | $0.64 |
| Median output, per 1M | $2.00 | $4.40 +120% |
| Lowest unit price | — | $0.033 / request |
| Cost of 1M in + 200k out | $0.28 | $0.32 +11.9% |
| Context | 256K +75.6% | 1M |
| Max output | 8K +99.2% | 1M |
| Providers | 4 +93.9% | 66 |
| Regions | EU, US | APAC, EU, FI, GLOBAL, US |
| Accepts | text | file, image, text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | yes |
| Cheapest provider | inferx | trustedrouter |
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
amazon-bedrock, edenai, inferx, trustedrouter
Frequently asked questions
Which is cheaper, Devstral 2 123B or GLM-5.3?
Devstral 2 123B is 26% cheaper than GLM-5.3 on input price. GLM-5.3 is 11% cheaper than Devstral 2 123B on output price. Devstral 2 123B is 11% cheaper than GLM-5.3 on a 1M-in / 200k-out workload.
Which has the larger context, Devstral 2 123B or GLM-5.3?
Devstral 2 123B: 256K tokens; GLM-5.3: 1M tokens.
Where can I use both Devstral 2 123B and GLM-5.3?
amazon-bedrock, edenai, inferx, trustedrouter