Qwen3 235B
Pricing verified 1y ago · source
Benchmarks
preference
Crowdsourced pairwise human preference rankings of LLM responses. Higher Elo means more frequently preferred by users.
math
American Invitational Mathematics Examination 2024 problems. Three-digit integer answers; very hard for non-reasoning models.
coding
164 hand-written Python programming problems scored by passing unit tests. Saturated for frontier models.
Continuously refreshed coding benchmark drawing from LeetCode, AtCoder, and Codeforces; reduces benchmark contamination.
agentic
Real GitHub issues solved end-to-end. Verified subset is a 500-task human-validated slice of SWE-bench.
long context
Long-context retrieval and reasoning suite. We report the 128k token effective-context score.
performance
Median sustained output speed in tokens per second on the model's first-party API for medium-length prompts. Higher is faster.
Median time from request to first output chunk in milliseconds on the model's first-party API for medium-length prompts. Lower is snappier; reasoning models are penalised here because they think before talking.
Providers
| Provider | Input $/M | Output $/M | Context | Quant |
|---|---|---|---|---|
DeepInfra deepinfra/fp8 | $0.07 | $0.10 | 262k | fp8 |
WandB wandb/bf16 | $0.10 | $0.10 | 262k | bf16 |
Novita novita/fp8 | $0.09 | $0.58 | 131k | fp8 |
Alibaba alibaba | $0.15 | $0.60 | 131k | unknown |
SiliconFlow siliconflow/fp8 | $0.09 | $0.60 | 262k | fp8 |
Parasail parasail/fp8 | $0.10 | $0.60 | 131k | fp8 |
Together together | $0.20 | $0.60 | 262k | unknown |
Friendli friendli | $0.20 | $0.80 | 262k | unknown |
AtlasCloud atlas-cloud/fp8 | $0.20 | $0.88 | 131k | fp8 |
Google google-vertex | $0.22 | $0.88 | 262k | unknown |
Google google-vertex | $0.25 | $1.00 | 262k | unknown |
Cerebras cerebras/fp16 | $0.60 | $1.20 | 131k | fp16 |