Text models
388 models. Compare AI chat and text models by context window size, function/tool calling, JSON mode, and whether they accept image input alongside text.
Price ranks a model against others of the same modality — a second of video generation and a second of image generation aren't the same unit of work, so thirds are computed within each modality, not across all of them.
388 of 388 models
Aion-2.0
AionLabs · Chat & Text
Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling.
100 cr / 1M tokens · 200 cr / 1M tokens
Aion-3.0
AionLabs · Chat & Text
Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.
375 cr / 1M tokens · 750 cr / 1M tokens
Aion-3.0-Mini
AionLabs · Chat & Text
Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models.
87.5 cr / 1M tokens · 175 cr / 1M tokens
Aion-RP 1.0 (8B)
AionLabs · Chat & Text
Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of…
100 cr / 1M tokens · 200 cr / 1M tokens
Anthropic Claude Haiku Latest
Anthropic · Chat & Text
This model always redirects to the latest model in the Anthropic Claude Haiku family.
125 cr / 1M tokens · 625 cr / 1M tokens
Anthropic Claude Sonnet Latest
Anthropic · Chat & Text
This model always redirects to the latest model in the Anthropic Claude Sonnet family.
250 cr / 1M tokens · 1250 cr / 1M tokens
Arize AI Qwen 2 1.5B Instruct
Arize AI · Chat & Text
12.5 cr / 1M tokens · 12.5 cr / 1M tokens
Claude 3.5 Haiku
Anthropic · Chat & Text
100 cr / 1M tokens · 500 cr / 1M tokens
Claude 3 Haiku
Anthropic · Chat & Text
Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance.
31.25 cr / 1M tokens · 156 cr / 1M tokens
Claude Fable 5
Anthropic · Chat & Text
Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding.
1250 cr / 1M tokens · 6250 cr / 1M tokens
Claude Fable Latest
Anthropic · Chat & Text
This model always redirects to the latest model in the Claude Fable family.
1250 cr / 1M tokens · 6250 cr / 1M tokens
Claude Haiku 4.5
Anthropic · Chat & Text
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and…
125 cr / 1M tokens · 625 cr / 1M tokens
Claude Opus 4.1
Anthropic · Chat & Text
Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks.
1875 cr / 1M tokens · 9375 cr / 1M tokens
Claude Opus 4.5
Anthropic · Chat & Text
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon…
625 cr / 1M tokens · 3125 cr / 1M tokens
Claude Opus 4.6
Anthropic · Chat & Text
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks.
625 cr / 1M tokens · 3125 cr / 1M tokens
Claude Opus 4.7
Anthropic · Chat & Text
Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents.
625 cr / 1M tokens · 3125 cr / 1M tokens
Claude Opus 4.7 (Fast)
Anthropic · Chat & Text
Fast-mode variant of Opus 4.7 - identical capabilities with higher output speed at premium 6x pricing.
3750 cr / 1M tokens · 18750 cr / 1M tokens
Claude Opus 4.8
Anthropic · Chat & Text
Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family.
625 cr / 1M tokens · 3125 cr / 1M tokens
Claude Opus 4.8 (Fast)
Anthropic · Chat & Text
Fast-mode variant of Opus 4.8 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8.
1250 cr / 1M tokens · 6250 cr / 1M tokens
Claude Opus 5
Anthropic · Chat & Text
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.
625 cr / 1M tokens · 3125 cr / 1M tokens
Claude Opus 5 (Fast)
Anthropic · Chat & Text
Fast-mode variant of Opus 5 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5.
1250 cr / 1M tokens · 6250 cr / 1M tokens
Claude Opus Latest
Anthropic · Chat & Text
This model always redirects to the latest model in the Claude Opus family. 1,000,000 token context window, maximum output of 128,000 tokens.
625 cr / 1M tokens · 3125 cr / 1M tokens
Claude Sonnet 4.5
Anthropic · Chat & Text
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows.
375 cr / 1M tokens · 1875 cr / 1M tokens
Claude Sonnet 4.6
Anthropic · Chat & Text
Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.
375 cr / 1M tokens · 1875 cr / 1M tokens
Claude Sonnet 5
Anthropic · Chat & Text
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.
250 cr / 1M tokens · 1250 cr / 1M tokens
Codestral 2508
Mistral · Chat & Text
Mistral's cutting-edge language model for coding released end of July 2025. 256,000 token context window.
37.5 cr / 1M tokens · 113 cr / 1M tokens
Codex Mini Latest
OpenAI · Chat & Text
188 cr / 1M tokens · 750 cr / 1M tokens
Command A
Cohere · Chat & Text
Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic…
313 cr / 1M tokens · 1250 cr / 1M tokens
Command R (08-2024)
Cohere · Chat & Text
command-r-08-2024 is an update of the Command R with improved performance for multilingual retrieval-augmented generation (RAG) and tool…
18.75 cr / 1M tokens · 75 cr / 1M tokens
Command R+ (08-2024)
Cohere · Chat & Text
command-r-plus-08-2024 is an update of the Command R+ with roughly 50% higher throughput and 25% lower latencies as compared to the…
313 cr / 1M tokens · 1250 cr / 1M tokens
Command R7B (12-2024)
Cohere · Chat & Text
Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024.
4.69 cr / 1M tokens · 18.75 cr / 1M tokens
Computer Use Preview
OpenAI · Chat & Text
Specialized model for computer use tool
375 cr / 1M tokens · 1500 cr / 1M tokens
Cydonia 24B V4.1
Thedrummer · Chat & Text
Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.
37.5 cr / 1M tokens · 62.5 cr / 1M tokens
Deepseek Coder 33B Instruct
Deepseek AI · Chat & Text
100 cr / 1M tokens · 100 cr / 1M tokens
DeepSeek R1 Distill Qwen 14B
Deepseek AI · Chat & Text
200 cr / 1M tokens · 200 cr / 1M tokens
DeepSeek R1 Distill Qwen 1.5B
Deepseek AI · Chat & Text
22.5 cr / 1M tokens · 22.5 cr / 1M tokens
DeepSeek V3 0324
DeepSeek · Chat & Text
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.
31.25 cr / 1M tokens · 125 cr / 1M tokens
DeepSeek V3.1
DeepSeek · Chat & Text
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt…
68.75 cr / 1M tokens · 206 cr / 1M tokens
Deepseek V3.1 NVFP4
Deepseek AI · Chat & Text
75 cr / 1M tokens · 213 cr / 1M tokens
DeepSeek V3.1 Terminus
DeepSeek · Chat & Text
DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by…
33.75 cr / 1M tokens · 125 cr / 1M tokens
DeepSeek V3.2
DeepSeek · Chat & Text
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous…
18.2 cr / 1M tokens · 36.4 cr / 1M tokens
DeepSeek V3.2 Exp
DeepSeek · Chat & Text
DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future…
33.75 cr / 1M tokens · 51.25 cr / 1M tokens
DeepSeek V3.2 Reasoner
DeepSeek · Chat & Text
18.2 cr / 1M tokens · 36.4 cr / 1M tokens
DeepSeek V4 Flash
DeepSeek · Chat & Text
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated…
18.2 cr / 1M tokens · 36.4 cr / 1M tokens
DeepSeek V4 Flash 0731
DeepSeek · Chat & Text
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.
10 cr / 1M tokens · 22.5 cr / 1M tokens
DeepSeek V4 Flash Latest
DeepSeek · Chat & Text
This model always redirects to the latest model in the DeepSeek V4 Flash family.
6.88 cr / 1M tokens · 22.5 cr / 1M tokens
DeepSeek V4 Flash Vision Exp
DeepSeek · Chat & Text
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding…
27.5 cr / 1M tokens · 82.5 cr / 1M tokens
DeepSeek V4 Pro
DeepSeek · Chat & Text
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting…
56.55 cr / 1M tokens · 113 cr / 1M tokens
DeepSeek V4 Pro 0813
DeepSeek · Chat & Text
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.
140 cr / 1M tokens · 421 cr / 1M tokens
ERNIE 4.5 VL 424B A47B
Baidu · Chat & Text
ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with…
52.5 cr / 1M tokens · 156 cr / 1M tokens
Fugu Ultra
Sakana · Chat & Text
Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. 1,000,000 token context window, maximum output of 128,000 tokens.
625 cr / 1M tokens · 3750 cr / 1M tokens
Gemini 2.5 Computer Use
Google · Chat & Text
156 cr / 1M tokens · 1250 cr / 1M tokens
Gemini 2.5 Flash
Google · Chat & Text
Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and…
37.5 cr / 1M tokens · 313 cr / 1M tokens
Gemini 2.5 Flash-Lite
Google · Chat & Text
Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency.
13 cr / 1M tokens · 52 cr / 1M tokens
Gemini 2.5 Flash Lite Preview 09-2025
Google · Chat & Text
13 cr / 1M tokens · 52 cr / 1M tokens
Gemini 2.5 Flash Native Audio
Google · Chat & Text
37.5 cr / 1M tokens · 313 cr / 1M tokens
Text, on Infery.ai
Text models cover chat completions, instruction-following and reasoning. Every one consumes a text prompt and returns text; a subset also accepts images as an additional input without moving to a different category — that is an optional input on a text model, not a separate output kind.
It is a catalogue, not one model
Three properties separate them: context window (from well under 32K tokens for small models to over 1M for the largest), tool/function calling for agent-style workflows, and JSON mode for structured output. Pricing is per token, billed separately for input and output — a model cheap on input and dear on output suits a short-prompt, long-answer workload differently than the reverse.
Open the Studio with a text model already picked
Free trial credits, no card. Filter above, or start from a blank chat and pick as you go.