MODEL PROOF
Qwen3 235B A22B Instruct 2507
BETTER VALUE OPTION
A stored alternative has an equal-or-higher measured score and an equal-or-lower price.
GLM 5.3 Flash · Δ score 52.2 points · 28% lower measured price · $0.148 / 1M tokens
Gemma 4 31B is a further stored option with these losses: 118K → 16K max output
- Independent LMArena score
- 1,419.2 ± 2.54 · 97,527 votes
- Context window
- 262.14K
- Maximum output
- 117.96K
- Input modalities
- text
- Output modalities
- text
- Published input price
- $0.090 / 1M tokens
- Published output price
- $0.550 / 1M tokens
- Pricing kind
- fixed
Inspect complete billing conditions and endpoint terms below.
Price from DeepInfra: the cheapest offer that is serving, at standard delivery, with at least 90% of the reference context and at a declared precision that is not 4-bit (fp8), at its standard rate. The maker’s own precision is not known.
Cheaper right now: $0.164/M at DeepInfra — delivery tier (flex) It does not pass the like-for-like test, so it never sets a rank.
Every price dimension · USD per million tokens
| Input | $0.090/M |
|---|---|
| Output | $0.550/M |
| Cached input | Unknown/M |
| Cache write | Unknown/M |
| Cache write 1h | Unknown/M |
| Reasoning | Unknown/M |
Who sells it
The same weights, different shops. Cheapest is not like-for-like when serving precision differs.
5 provider offers · rates, limits and conditions
Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test.
| Seller | Input | Output | Precision | Uptime (1d) |
|---|---|---|---|---|
| DeepInfradeepinfra/fp8/flex Endpoint terms
| $0.072 | $0.440 | fp8 | 100.00% |
| DeepInfradeepinfra/fp8 Endpoint terms
| $0.090 | $0.550 | fp8 | 95.82% |
| DeepInfradeepinfra/fp8/priority Endpoint terms
| $0.135 | $0.825 | fp8 | 95.22% |
| Parasailparasail/fp8 Endpoint terms
| $0.140 | $0.800 | fp8 | 100.00% |
| Venicevenice/fp8 Endpoint terms
| $0.150 | $0.750 | fp8 | 99.01% |
Independent scores
| LMArena Elo | 1419.2default |
|---|---|
| LMArena row | qwen3-235b-a22b-instruct-2507 |
LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero.
Best rankings by task
- Data visualisation #114 1065
- 3D #125 961
- Websites #128 1045
- Code categories #128 1020
- UI components #130 949
- Game development #140 924
Per-task Elo and rank from Design Arena, via OpenRouter’s model feed. The rank is the feed’s, and it counts models OpenRouter does not list.
Capability
| Context window | 262K |
|---|---|
| Max output | 117K |
| Input modes | text |
| Tool use | yes |
| Reasoning | no |
| Knowledge cutoff | 2025-06-30 |
| Open weights | Unknown |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-11-22 |
| Quality data | verified |
Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...
Questions this page answers
What does Qwen3 235B A22B Instruct 2507 cost?
$0.090/M in, $0.550/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.
Does Qwen3 235B A22B Instruct 2507 have an independent quality score?
Qwen3 235B A22B Instruct 2507 has an LMArena score in this catalogue.
What beats Qwen3 235B A22B Instruct 2507?
GLM 5.3 Flash has an equal-or-higher measured score and an equal-or-lower price.
Does this page use Artificial Analysis scores for Qwen3 235B A22B Instruct 2507?
No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated.
MODEL MONUMENT