GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost and shares Astra's clearer, more concise communication style in technical and coding conversations.
Providers
Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).
| $1.00 | $5.00 | $0.10 | -- | -- |
Input $1.00 / Output $5.00-- tok/s-- uptime
Pricing
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
Weighted average
GPT-6 Sol (batch) — Price history
| $0.00 | $0.00 | 0.8% | 100.0% |
- Effective in $0.00 / Effective out $0.00Token share100.0%
Performance
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
Uptime
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Not enough uptime data to display yet.
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.
Benchmarks
Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.
| Source | Benchmark | Score |
|---|---|---|
| Artificial Analysis | GPT-6 Sol (Max) Intelligence Index | 44.2 |
| Artificial Analysis | GPT-6 Sol (Max) HLE | 47.9% |
| Artificial Analysis | GPT-6 Sol (Max) AA-LCR | 83.7% |
| Artificial Analysis | GPT-6 Sol (Max) GDPval-AA | 50.8% |
| Artificial Analysis | GPT-6 Sol (Max) CritPt | 30.9% |
| Artificial Analysis | GPT-6 Sol (Max) SciCode | 57.6% |
| Artificial Analysis | GPT-6 Sol (Max) Terminal-Bench 4.0 | 43.9% |
| Artificial Analysis | GPT-6 Sol (Max) AA-Omniscience Accuracy | 51.1% |
| Artificial Analysis | GPT-6 Sol (Max) AA-Omniscience Non-Hallucination Rate | 39.2% |
| Artificial Analysis | GPT-6 Sol (Low) HLE | 34.9% |
| Artificial Analysis | GPT-6 Sol (Low) AA-LCR | 79.3% |
| Artificial Analysis | GPT-6 Sol (Low) GDPval-AA | 35.1% |
| Artificial Analysis | GPT-6 Sol (Low) CritPt | 16.3% |
| Artificial Analysis | GPT-6 Sol (Low) SciCode | 50.2% |
| Artificial Analysis | GPT-6 Sol (Low) Terminal-Bench 4.0 | 9.1% |
| Artificial Analysis | GPT-6 Sol (Medium) HLE | 41.0% |
| Artificial Analysis | GPT-6 Sol (Medium) AA-LCR | 82.3% |
| Artificial Analysis | GPT-6 Sol (Medium) GDPval-AA | 42.6% |
| Artificial Analysis | GPT-6 Sol (Medium) CritPt | 24.6% |
| Artificial Analysis | GPT-6 Sol (Medium) SciCode | 53.8% |
| Artificial Analysis | GPT-6 Sol (Medium) Terminal-Bench 4.0 | 18.7% |
| Artificial Analysis | GPT-6 Sol (Non-reasoning) HLE | 18.4% |
| Artificial Analysis | GPT-6 Sol (Non-reasoning) AA-LCR | 64.0% |
| Artificial Analysis | GPT-6 Sol (Non-reasoning) GDPval-AA | 37.7% |
| Artificial Analysis | GPT-6 Sol (Non-reasoning) CritPt | 4.0% |
| Artificial Analysis | GPT-6 Sol (Non-reasoning) SciCode | 47.3% |
| Artificial Analysis | GPT-6 Sol (Non-reasoning) Terminal-Bench 4.0 | 13.1% |
| Artificial Analysis | GPT-6 Sol (High) HLE | 44.1% |
| Artificial Analysis | GPT-6 Sol (High) AA-LCR | 83.7% |
| Artificial Analysis | GPT-6 Sol (High) GDPval-AA | 45.2% |
| Artificial Analysis | GPT-6 Sol (High) CritPt | 25.4% |
| Artificial Analysis | GPT-6 Sol (High) SciCode | 54.9% |
| Artificial Analysis | GPT-6 Sol (High) Terminal-Bench 4.0 | 26.3% |
| Artificial Analysis | GPT-6 Sol (Xhigh) HLE | 46.3% |
| Artificial Analysis | GPT-6 Sol (Xhigh) AA-LCR | 81.3% |
| Artificial Analysis | GPT-6 Sol (Xhigh) GDPval-AA | 48.3% |
| Artificial Analysis | GPT-6 Sol (Xhigh) CritPt | 28.0% |
| Artificial Analysis | GPT-6 Sol (Xhigh) SciCode | 55.1% |
| Artificial Analysis | GPT-6 Sol (Xhigh) Terminal-Bench 4.0 | 30.3% |
| Vals AI | GPT-6 Sol BioMysteryBench | 74.8% |
| Vals AI | GPT-6 Sol Code Migration | 57.2% |
| Vals AI | GPT-6 Sol CyberBench v1.1 | 78.0% |
| Vals AI | GPT-6 Sol EMB | 71.5% |
| Vals AI | GPT-6 Sol Finance Agent (v2) | 49.0% |
| Vals AI | GPT-6 Sol Financial Coaching Bench | 62.6% |
| Vals AI | GPT-6 Sol Harvey's Legal Agent Benchmark v1 | 1.7% |
| Vals AI | GPT-6 Sol IOI | 82.6% |
| Vals AI | GPT-6 Sol Legal Research Bench | 28.8% |
| Vals AI | GPT-6 Sol MedCode | 47.1% |
| Vals AI | GPT-6 Sol MedScribe | 82.0% |
| Vals AI | GPT-6 Sol MysteryMechanism | 30.2% |
| Vals AI | GPT-6 Sol ProgramBench | 2.0% |
| Vals AI | GPT-6 Sol ProofBench v1.1 | 83.0% |
| Vals AI | GPT-6 Sol Public Benefits Bench v1.1 | 56.6% |
| Vals AI | GPT-6 Sol Vals RSI Index | 28.1% |
| Vals AI | GPT-6 Sol SAGE v1 | 44.8% |
| Vals AI | GPT-6 Sol Vals Science Index | 45.0% |
| Vals AI | GPT-6 Sol SRE Bench | 30.5% |
| Vals AI | GPT-6 Sol Tax Agent Bench | 15.0% |
| Vals AI | GPT-6 Sol Terminal-Bench 4.0 | 44.4% |
| Vals AI | GPT-6 Sol Terminal-Bench-Science | 30.0% |
| Vals AI | GPT-6 Sol Vals Index | 57.5% |
| Vals AI | GPT-6 Sol Vibe Code Bench v1.1 | 87.8% |
Apps
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
Not enough data for apps using this model yet.
Activity
Token volume and request traffic to this model over time.
API
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
Not currently available through EU in-region routing. In-region routing docs
Documentation
Guides, cookbooks, blog posts, and tools for building with OpenAI: GPT-6 Sol (batch) on OpenRouter.
Frequently asked questions
GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases.
The GPT-6 Sol (batch) documentation on OpenRouter includes the GPT-6 Migration Guide cookbook. The quickstart covers API keys and your first request, and the API reference lists every parameter.
GPT-6 Sol (batch) costs $1.00/M input tokens and $5.00/M output tokens, with separate rates for Cache Read at $0.10/M tokens, Cache Write at $1.25/M tokens, and Web Search at $10.00/1K calls.
GPT-6 Sol (batch) has a 1,050,000 token context window. It supports up to 128,000 completion tokens.
Yes. GPT-6 Sol (batch) accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
Yes. OpenAI caches prompts of 1024 tokens or more automatically, and GPT-6 Sol (batch) bills a cache write on each cached prompt whether or not the cached prefix is read again. To turn caching off for a request, set prompt_cache_options.mode to "explicit" at the request root and do not mark any content block with prompt_cache_breakpoint. Explicit mode disables OpenAI-managed breakpoints, so a request with none of your own has no cacheable prefix and is billed at the plain input rate. See the prompt caching guide.
GPT-6 Sol (batch) accepts files such as PDFs, images, and text as input and returns text.
GPT-6 Sol (batch) is served by 1 provider on OpenRouter: OpenAI.
GPT-6.1 Terra Pro, GPT-6.1 Terra, GPT-6 Luna Decisions and 58 more are other text models from OpenAI.
GPT-6 Sol (batch) was released on September 22, 2026.