gpt-5.6-solReasoning model for tool-driven agents and multi-step technical work.
- Published input cap
- —
- Endpoint
- Chat
- Base input / output per 1M
- Managed price not published
OpenAI
gpt-5.515 model pages across 5 providers
Compare configured models from OpenAI, Anthropic, DeepSeek, Google, and TypeSafe AI. Published rates come from billing; actual availability depends on your project and endpoint.
Switch providers without changing your application code, with routing and fallbacks handled by Gruvo.
15 models
gpt-5.6-solReasoning model for tool-driven agents and multi-step technical work.
gpt-5.6-terraModel for large repositories, documents, and enterprise knowledge work.
gpt-5.5General-purpose reasoning model for text, code, and tool-based workflows.
anthropic/claude-opus-4-6Deep reasoning model for nuanced analysis, research synthesis, and long-form writing.
anthropic/claude-opus-4-7Long-context coding model for repository analysis and multi-step engineering work.
anthropic/claude-opus-4-8High-capability reasoning model for complex technical work.
anthropic/claude-sonnet-4-5Balanced coding model for developer tools, agents, and production automation.
anthropic/claude-sonnet-4-6Long-context coding model for tool use, repository work, and extended agent sessions.
deepseek/deepseek-v4.1-flashCost-efficient model for high-volume classification, summarization, and extraction.
deepseek/deepseek-v4-proReasoning model for mathematics, programming, and cost-sensitive technical analysis.
deepseek/deepseek-v4.1-flashFast, low-cost model for routing, moderation, and structured transformations.
google/gemini-2.5-proModel for document, code, and research workloads.
google/gemini-3.6-flashInteractive model for text and tool-based workloads.
jev-latestA fast decision model that returns typed choices instead of generated prose.