30Models
1,000,000Max context
$0.05Lowest listed input
- file
- image
- structured
- text
- tools
Fast answer
Choose the provider route that fits the workload, not a generic brand ranking
Choose based on the model behavior and provider ecosystem your workflow needs, not a generic provider ranking
Data source and freshness
Catalog-backed, not a static price sheet
TVP refreshes this page from the live OpenRouter model catalog. This render used 685 public model records and was synchronized Oct 26, 2026, 7:31 AM UTC. Pricing, availability, and context values can change.
Verify the exact route before sending production traffic, then use the linked model and provider pages as the source for current values. Read the TVP data methodology.
Live coverage
Current provider inventory at a glance
53Models
1,048,576Max context
$0.04Lowest listed input
- audio
- embeddings
- file
- image
- speech
- structured
- text
- tools
Start testing
High-context listed models to evaluate next
- Anthropic: Claude Haiku 5.5Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...
- Anthropic: Claude Haiku 5.5 (batch)Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...
- Anthropic: Claude Sonnet 5.5Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...
- Anthropic: Claude Sonnet 5.5 (batch)Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...
- Google: Gemini 4 ArgonGemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...
- Google: Gemini 4 Argon (batch)Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...
- Google: Gemini 3.8 FlashGemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
- Google: Gemini 3.8 Flash (batch)Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
Provider FAQ
How to make the provider decision
Is Anthropic or Google better for research?
Research workloads need enough context, strong analytical behavior, and a price point that fits the volume of source processing. Compare those live signals here before choosing.
How should I evaluate Claude and Gemini candidates?
Start with the specific models, then compare their context, capability support, and route cost. This provider page is a starting point rather than a substitute for a model-level test.
