Writing code
Measured by a third party
Coding Index: 39.3 · Rank 51 of 86, among scored models · Artificial Analysis, read November 18, 2026
$0.2625
mixed / 1M tokens
Mixed price per 1M tokens: 3 input tokens to 1 output token.
in $0.15 · out $0.60
Price disputed
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.
It is a separate listing and differs in: Max output: 33k (other version: 236k); Structured output: Not listed (other version: Yes).
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
Coding Index: 39.3 · Rank 51 of 86, among scored models · Artificial Analysis, read November 18, 2026
Measured by a third party
Agentic Index: 2.9 · Rank 44 of 64, among scored models · Artificial Analysis, read November 18, 2026
Declared, not measured
Accepts: images and video. Declared by the provider through OpenRouter; we did not test it.
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 |
|---|---|---|---|---|---|
| Darkbloom | $0.05 | $0.19 | $0.0125 | $0.085 68% cheaper | |
| Io Net | $0.055 | $0.24 | $0.032 | $0.1013 61% cheaper | bf16 |
| NextBit | $0.0675 | $0.225 | $0.0375 | $0.1069 59% cheaper | bf16 · promo −25% |
| AkashML | $0.07 | $0.24 | $0.046 | $0.1125 57% cheaper | fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality. |
| DekaLLM | $0.06 | $0.33 | $0.04 | $0.1275 51% cheaper | bf16 |
| DeepInfra | $0.07 | $0.34 | No data | $0.1375 48% cheaper | fp8 |
| Makora | $0.09 | $0.28 | $0.049 | $0.1375 48% cheaper | |
| Cloudflare | $0.10 | $0.30 | $0.05 | $0.15 43% cheaper | |
| CoreWeave | $0.10 | $0.30 | $0.05 | $0.15 43% cheaper | bf16 |
| PrimeIntellect | $0.10 | $0.30 | $0.05 | $0.15 43% cheaper | bf16 |
| Novita | $0.13 | $0.40 | No data | $0.1975 25% cheaper | bf16 |
| Parasail | $0.13 | $0.40 | $0.05 | $0.1975 25% cheaper | bf16 |
| Venice | $0.13 | $0.40 | $0.05 | $0.1975 25% cheaper | bf16 |
| SiliconFlow | $0.14 | $0.40 | $0.05 | $0.205 22% cheaper | fp8 |
| Google Vendor Price used here | $0.15 | $0.60 | No data | $0.2625 |
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 |
|---|---|---|
| Coding Index Artificial Analysis, read November 18, 2026 | 39.3 | Rank 51 of 86, among scored models |
| Agentic Index Artificial Analysis, read November 18, 2026 | 2.9 | Rank 44 of 64, 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.