OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...
No provider description is available for this model yet.
No provider description is available for this model yet.
Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...
No provider description is available for this model yet.
No provider description is available for this model yet.
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....
Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater...
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
This model always redirects to the latest model in the GPT Terra family.
No provider description is available for this model yet.
Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...
o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.
Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...
No provider description is available for this model yet.
Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...
GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...
No provider description is available for this model yet.
No provider description is available for this model yet.
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| OpenAI: o4 Mini High (batch)openai/o4-mini-high:batch | OpenAI |
200K | $0.55 | $2.2 | — | ||
| ByteDance/Seed-2.0-codedeepinfra/bytedance/seed-2.0-code | Deepinfra |
256K | $0.5 | $3 | — | ||
| ByteDance/Seed-2.0-prodeepinfra/bytedance/seed-2.0-pro | Deepinfra |
256K | $0.5 | $3 | — | ||
| moonshotai/Kimi-K2.7-Codedeepinfra/moonshotai/kimi-k2.7-code | Deepinfra |
262.144K | $0.68 | $3.4 | — | ||
| anthropic/claude-sonnet-5deepinfra/anthropic/claude-sonnet-5 | Deepinfra |
1M | $2 | $10 | — | ||
| mistral-vibe-cli-fastmistral/mistral-vibe-cli-fast | Mistral |
262.144K | $0.15 | $0.6 | — | ||
| Anthropic: Claude Opus 4.6 (batch)anthropic/claude-opus-4.6:batch | Anthropic |
1M | $2.5 | $12.5 | — | ||
| Qwen/Qwen3.5-397B-A17Bdeepinfra/qwen/qwen3.5-397b-a17b | Deepinfra |
262.144K | $0.45 | $3 | — | ||
| anthropic/claude-fable-5deepinfra/anthropic/claude-fable-5 | Deepinfra |
1M | $10 | $50 | — | ||
| Anthropic: Claude Fable 5.1 (batch)anthropic/claude-fable-5.1:batch | Anthropic |
1M | $5 | $25 | — | ||
| nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55Bdeepinfra/nvidia/nvidia-nemotron-3-ultra-550b-a55b | Deepinfra |
262.144K | $0.5 | $2.2 | — | ||
| Qwen/Qwen3.5-122B-A10Bdeepinfra/qwen/qwen3.5-122b-a10b | Deepinfra |
262.144K | $0.29 | $2.4 | — | ||
| Qwen: Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instruct | Alibaba Qwen |
131.072K | $0.21 | $1.9 | — | ||
| moonshotai/Kimi-K3deepinfra/moonshotai/kimi-k3 | Deepinfra |
1.04858M | $2.85 | $14.25 | — | ||
| anthropic/claude-opus-4-7deepinfra/anthropic/claude-opus-4-7 | Deepinfra |
1M | $5 | $25 | — | ||
| Qwen/Qwen3.6-27Bdeepinfra/qwen/qwen3.6-27b | Deepinfra |
262.144K | $0.32 | $3.2 | — | ||
| google/gemma-4-26B-A4B-itdeepinfra/google/gemma-4-26b-a4b-it | Deepinfra |
262.144K | $0.07 | $0.34 | — | ||
| google/gemini-3.1-prodeepinfra/google/gemini-3.1-pro | Deepinfra |
1M | $2 | $12 | — | ||
| anthropic/claude-haiku-4-5deepinfra/anthropic/claude-haiku-4-5 | Deepinfra |
200K | $1 | $5 | — | ||
| Qwen/Qwen3.5-9Bdeepinfra/qwen/qwen3.5-9b | Deepinfra |
262.144K | $0.1 | $0.15 | — | ||
| google/gemma-4-31B-itdeepinfra/google/gemma-4-31b-it | Deepinfra |
262.144K | $0.13 | $0.38 | — | ||
| Qwen: Qwen3 VL 235B A22B Thinkingqwen/qwen3-vl-235b-a22b-thinking | Alibaba Qwen |
131.072K | $0.4 | $4 | — | ||
| Google: Gemini 2.5 Flash (batch)google/gemini-2.5-flash:batch | Google |
1.04858M | $0.15 | $1.25 | — | ||
| anthropic.claude-fable-5-1bedrock_converse/anthropic.claude-fable-5-1 | 1M | $10 | $50 | — | |||
| global.anthropic.claude-fable-5-1bedrock_converse/global.anthropic.claude-fable-5-1 | 1M | $10 | $50 | — | |||
| us.anthropic.claude-fable-5-1bedrock_converse/us.anthropic.claude-fable-5-1 | 1M | $11 | $55 | — | |||
| eu.anthropic.claude-fable-5-1bedrock_converse/eu.anthropic.claude-fable-5-1 | 1M | $11 | $55 | — | |||
| claude-fable-5-1azure_ai/claude-fable-5-1 | 1M | $10 | $50 | — | |||
| kimi-k3moonshot/kimi-k3 | 1.04858M | $3 | $15 | — | |||
| OpenAI: GPT Terra Latest~openai/gpt-terra-latest | OpenAI |
1.05M | $2 | $12 | — | ||
| kimi-k2.7-codeqwencloud/kimi-k2.7-code | 229.376K | $0.95 | $4 | — | |||
| Meta: Muse Spark 1.3 Contributormeta/muse-spark-1.3-contributor | Meta |
1.04858M | $0.1 | $0.2 | — | ||
| OpenAI: o3 (batch)openai/o3:batch | OpenAI |
200K | $1 | $4 | — | ||
| MoonshotAI: Kimi K3 (batch)moonshotai/kimi-k3:batch | Moonshot AI |
1.04858M | $3 | $15 | — | ||
| OpenAI: o3 Pro (batch)openai/o3-pro:batch | OpenAI |
200K | $10 | $40 | — | ||
| qwen3-vl-235b-a22b-instructqwencloud/qwen3-vl-235b-a22b-instruct | 131.072K | $0.4 | $1.6 | — | |||
| qwen3-vl-235b-a22b-thinkingqwencloud/qwen3-vl-235b-a22b-thinking | 131.072K | $0.4 | $4 | — | |||
| qwen3-vl-32b-instructqwencloud/qwen3-vl-32b-instruct | 131.072K | $0.16 | $0.64 | — | |||
| qwen3-vl-32b-thinkingqwencloud/qwen3-vl-32b-thinking | 131.072K | $0.16 | $2.87 | — | |||
| qwen3-vl-plusqwencloud/qwen3-vl-plus | 260.096K | — | — | — | |||
| qwen3.5-plusqwencloud/qwen3.5-plus | 991.808K | — | — | — | |||
| qwen3.7-plusqwencloud/qwen3.7-plus | 991.808K | — | — | — | |||
| qwen3.8-maxqwencloud/qwen3.8-max | 991.808K | $2 | $6 | — | |||
| Qwen: Qwen3.8 Flashqwen/qwen3.8-flash | Alibaba Qwen |
1M | $0.15 | $0.47 | — | ||
| Sakana: Fugu Ultra v2sakana/fugu-ultra-v2 | Sakana |
1M | $5 | $30 | — | ||
| kimi-k2.7-codeqwen_ai_platform/kimi-k2.7-code | 229.376K | $0.95 | $4 | — | |||
| SpaceXAI: Grok 4.20 Multi-Agentx-ai/grok-4.20-multi-agent | xAI |
2M | $1.25 | $2.5 | — | ||
| OpenAI: GPT-6 Astra (batch)openai/gpt-6-astra:batch | OpenAI |
1.05M | $5 | $25 | — | ||
| qwen3-vl-235b-a22b-instructqwen_ai_platform/qwen3-vl-235b-a22b-instruct | 131.072K | $0.4 | $1.6 | — | |||
| qwen3-vl-235b-a22b-thinkingqwen_ai_platform/qwen3-vl-235b-a22b-thinking | 131.072K | $0.4 | $4 | — |