Writing code
Measured by a third party
Code: 945 · Rank 116 of 122, among scored models · Design Arena, read November 21, 2026
Cost of this job: $0.04
$0.0703
mixed / 1M tokens
Mixed price per 1M tokens: 3 input tokens to 1 output token.
in $0.037 · out $0.17 · Cached input $0.0185
via DeepInfra
Models that think before they answer can use many more output tokens, so your real cost can be higher than the figure shown.
US dollars per million tokens, converted to your currency at the NBP rate.
Each line names the measurement it rests on. A task that is not listed has no measurement or declared feature we can show.
Measured by a third party
Code: 945 · Rank 116 of 122, among scored models · Design Arena, read November 21, 2026
Cost of this job: $0.04
Measured by a third party
Intelligence Index: 3.8 · Rank 65 of 66, among scored models · Artificial Analysis, read November 21, 2026
Cost of this job: $0.01
Models that score at least as high for less in this scenario: 2
Measured by a third party
Websites: 955 · Rank 119 of 127, among scored models · Design Arena, read November 21, 2026
UI components: 911 · Rank 113 of 118, among scored models · Design Arena, read November 21, 2026
Cost of this job: $0.02
Models that score at least as high for less in this scenario: 2
Measured by a third party
Game development: 971 · Rank 109 of 121, among scored models · Design Arena, read November 21, 2026
3D scenes: 869 · Rank 110 of 114, among scored models · Design Arena, read November 21, 2026
Cost of this job: $0.02
Models that score at least as high for less in this scenario: 1
Measured by a third party
Data visualization: 982 · Rank 104 of 112, among scored models · Design Arena, read November 21, 2026
Cost of this job: $0.02
The size of each job is our assumption; the prices are real.
Thinking is billed as output tokens; a model that thinks longer costs more than this estimate. Ranks are among all models we list, including older ones.
The price used in the catalog is the vendor's own; when the vendor has no API of its own, it is the cheapest regular host.
| Provider | Input | Output | Cached input | Mixed | Notes |
|---|---|---|---|---|---|
| Near AI | $0.03 | $0.15 | $0.015 | $0.06 15% cheaper | fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality. |
| Venice | $0.03 | $0.15 | $0.03 | $0.06 15% cheaper | int4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality. |
| AkashML | $0.03 | $0.187 | $0.03 | $0.0693 1% cheaper | fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality. |
| DeepInfra Price used here | $0.037 | $0.17 | $0.0185 | $0.0703 | bf16 |
| Crusoe | $0.05 | $0.25 | $0.05 | $0.10 | bf16 |
| Sail Research | $0.06 | $0.40 | $0.03 | $0.145 | fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality. |
| DigitalOcean | $0.06 | $0.42 | $0.012 | $0.15 | |
| $0.09 | $0.36 | No data | $0.1575 | ||
| Mancer 2 | $0.085 | $0.375 | $0.085 | $0.1575 | fp8 |
| BaseTen | $0.10 | $0.50 | $0.10 | $0.20 | US · fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality. |
| BaseTen | $0.10 | $0.50 | $0.10 | $0.20 | fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality. |
| Amazon Bedrock | $0.15 | $0.60 | No data | $0.2625 | EU |
| Amazon Bedrock | $0.15 | $0.60 | No data | $0.2625 | |
| Groq | $0.15 | $0.60 | $0.075 | $0.2625 | |
| Nebius | $0.15 | $0.60 | $0.10 | $0.2625 | fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality. |
| SiliconFlow | $0.15 | $0.60 | $0.075 | $0.2625 | fp8 |
| Together | $0.15 | $0.60 | No data | $0.2625 | |
| Parasail | $0.10 | $0.75 | $0.055 | $0.2625 | fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality. |
| SambaNova | $0.14 | $0.95 | No data | $0.3425 | |
| Cerebras | $0.35 | $0.75 | $0.35 | $0.45 | fp16 |
| PrimeIntellect | $0.35 | $0.75 | $0.315 | $0.45 | fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality. |
As listed by OpenRouter. "Not listed" means OpenRouter does not list it for this model.
Scores come from third parties and are relayed by OpenRouter. We do not run the tests. Higher is better.
| Source | Score | Rank among scored |
|---|---|---|
| Intelligence Index Artificial Analysis, read November 21, 2026 | 3.8 | Rank 65 of 66, among scored models |
| Websites Design Arena, read November 21, 2026 | 955 | Rank 119 of 127, among scored models |
| UI components Design Arena, read November 21, 2026 | 911 | Rank 113 of 118, among scored models |
| Game development Design Arena, read November 21, 2026 | 971 | Rank 109 of 121, among scored models |
| 3D scenes Design Arena, read November 21, 2026 | 869 | Rank 110 of 114, among scored models |
| Data visualization Design Arena, read November 21, 2026 | 982 | Rank 104 of 112, among scored models |
| Code Design Arena, read November 21, 2026 | 945 | Rank 116 of 122, among scored models |
Intelligence, Coding and Agentic indices: Artificial Analysis (artificialanalysis.ai). Design categories: Design Arena (designarena.ai). Both are relayed by the OpenRouter public model list and were read on November 21, 2026. We compute ranks, tiers and costs from these numbers; the sources have not reviewed them. Scores belong to the model, not to the route it is served on.
Artificial Analysis · Design Arena · Relayed by OpenRouter. opens in a new tab
Prices: OpenRouter routes and a second price table, checked November 21, 2026. Specifications: OpenRouter, November 21, 2026. Exchange rate: NBP, November 20, 2026. Benchmarks: Artificial Analysis and Design Arena via OpenRouter.