MODEL PROOF
Qwen3 VL 235B A22B Instruct
BETTER VALUE OPTION
A stored alternative has an equal-or-higher measured score and an equal-or-lower price.
Serving precision differs between offers.
GLM 5.3 Flash · Δ score 49.5 points · 36% lower measured price · $0.238 / 1M tokens
Gemma 4 31B is a further stored option with these losses: 33K → 16K max output
- Independent LMArena score
- 1,420.1 ± 6.52 · 11,241 votes
- Context window
- 262.14K
- Maximum output
- 32.77K
- Input modalities
- text, image
- Output modalities
- text
- Published input price
- $0.200 / 1M tokens
- Published output price
- $0.880 / 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 and at a declared precision that is not 4-bit (fp8), at its standard rate. The maker’s own precision is not known.
Every price dimension · USD per million tokens
| Input | $0.200/M |
|---|---|
| Output | $0.880/M |
| Cached input | $0.110/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.
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.200/M from DeepInfra.
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 Endpoint terms
| $0.200 | $0.880 | fp8 | 97.86% |
| Venicevenice/fp8 Endpoint terms
| $0.210 | $1.90 | fp8 | 94.57% |
| Parasailparasail/fp8 Endpoint terms
| $0.210 | $1.90 | fp8 | 99.19% |
| Alibabaalibaba Endpoint terms
| $0.260 | $1.04 | undeclared | 99.43% |
| Novitanovita/bf16 Endpoint terms
| $0.300 | $1.50 | bf16 | 93.17% |
Independent scores
| LMArena Elo | 1420.1default |
|---|
LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero.
Capability
| Context window | 262K |
|---|---|
| Max output | 32K |
| Input modes | text, image |
| Tool use | yes |
| Reasoning | no |
| Knowledge cutoff | 2025-03-31 |
| Open weights | Unknown |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-10-06 |
| Quality data | verified |
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...
Questions this page answers
What does Qwen3 VL 235B A22B Instruct cost?
$0.200/M in, $0.880/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.
Does Qwen3 VL 235B A22B Instruct have an independent quality score?
Qwen3 VL 235B A22B Instruct has an LMArena score in this catalogue.
What beats Qwen3 VL 235B A22B Instruct?
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 VL 235B A22B Instruct?
No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated.
Is the cheapest Qwen3 VL 235B A22B Instruct endpoint the same product?
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.200/M from DeepInfra.
MODEL MONUMENT