This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.
Upstage has launched a newer release, Solar Pro 4. We suggest considering it instead.
Solar Pro 3: Intelligence, Performance & Price Analysis
Available providers
Model summary
Verbosity
Solar Pro 3 supports text input, outputs text, and has a 128k tokens context window.
Pricing for Solar Pro 3 is $0.15 per 1M input tokens (competitively priced, median: $0.24) and $0.60 per 1M output tokens (moderately priced, median: $0.83).
| Reasoning | Yes |
|---|---|
| Input modality | Supports: text |
| Output modality | Supports: text |
| Context window | 128k ~192 A4 pages of size 12 Arial font |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Index vs. Cost per Task
Capability Indexes
Incorporates 4 evaluations: AutomationBench-AA, AA-Briefcase v1.1, AA-Omniscience v1.1, GDP.pdf · Higher is better
Evaluations
Agentic knowledge work, Elo
Knowledge
1 - hallucination rate
Agentic SaaS workflows
Professional document reasoning, All-pass
Agentic coding & terminal use
Agentic real-world work tasks, Elo
Medical long context reasoning
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Performance
Measured by time per task (minutes), output speed (tokens per second), time to first answer token and time to first token (seconds)
Time per Intelligence Index Task
Output Speed
Time to First Answer Token
Context Window
Context Window
Further details
Weights | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| Solar Pro 3 | - | 102B 12B active at inference time | 128k | $0.10 | - | 117 | Not available |
Frequently Asked Questions
Common questions about Solar Pro 3
Solar Pro 3 was released on April 6, 2026.
Solar Pro 3 was created by Upstage.
Solar Pro 3 has a time to first answer token of 11.16s (based on Upstage's API), which is somewhat higher than average compared to other models in a similar price tier (median: 8.10s).
Solar Pro 3 costs $0.15 per 1M input tokens (very competitive, median: $0.24) and $0.60 per 1M output tokens (better than average, median: $0.83), based on Upstage's API.
Solar Pro 3 costs $0.15 per 1M input tokens and $0.60 per 1M output tokens (based on Upstage's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.10 per 1M tokens. Pricing may vary by provider. Compare provider pricing
Yes, Solar Pro 3 is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Solar Pro 3 supports text input.
Solar Pro 3 supports text output.
No, Solar Pro 3 does not support image input. It can only process text.
No, Solar Pro 3 is not multimodal. It only supports text input.
Solar Pro 3 has a context window of 128k tokens. This determines how much text and conversation history the model can process in a single request.
No, Solar Pro 3 is proprietary. The model weights are not publicly available.
Solar Pro 3 has 102B parameters.
Yes, Solar Pro 3 is available via API through 1 provider. Compare API providers
Solar Pro 3 is available through 1 API provider. Compare providers