LeaderBoard

Search models, prices and capabilities across four catalogs. Unreported values stay unknown.

Filter By Any Reported Field
Filter
Second Filter
Columns, Sorting And Cost · 3 Columns

Independent array filters can match different items. Same Array Item requires both array fields to belong to one table; different tables return no matches. Array columns and sorting use the minimum scalar value, not a sum or a complete offer. Numeric sorting accepts numeric strings. Unknown values sort last. Prices retain their source units.

Field ID Directory

3 — /alias_target

4 — /alias_target/name

5 — /alias_target/slug

11 — /architecture

13 — /architecture/input_modalities

14 — /architecture/input_modalities/*

18 — /architecture/instruct_type

12 — /architecture/modality

15 — /architecture/output_modalities

16 — /architecture/output_modalities/*

17 — /architecture/tokenizer

91 — /autoRouting

92 — /autoRouting/models

93 — /autoRouting/models/*

37 — /benchmarks

64 — /benchmarks/artificial_analysis

67 — /benchmarks/artificial_analysis/agentic_index

66 — /benchmarks/artificial_analysis/coding_index

65 — /benchmarks/artificial_analysis/intelligence_index

38 — /benchmarks/design_arena

39 — /benchmarks/design_arena/*/arena

40 — /benchmarks/design_arena/*/category

41 — /benchmarks/design_arena/*/elo

43 — /benchmarks/design_arena/*/rank

42 — /benchmarks/design_arena/*/win_rate

2 — /canonical_slug

10 — /context_length

8 — /created

28 — /default_parameters

52 — /default_parameters/frequency_penalty

53 — /default_parameters/presence_penalty

54 — /default_parameters/repetition_penalty

49 — /default_parameters/temperature

51 — /default_parameters/top_k

50 — /default_parameters/top_p

9 — /description

141 — /enkrypt

146 — /enkrypt/bias_score

147 — /enkrypt/cbrn_score

158 — /enkrypt/evaluatedAt

153 — /enkrypt/evasion_score

161 — /enkrypt/freshness

148 — /enkrypt/harmful_score

157 — /enkrypt/ingestedAt

149 — /enkrypt/insecure_code_score

152 — /enkrypt/jailbreak_score

159 — /enkrypt/lastCheckedAt

142 — /enkrypt/model_name

155 — /enkrypt/nist_score

156 — /enkrypt/owasp_score

143 — /enkrypt/provider

145 — /enkrypt/risk_score

151 — /enkrypt/robustness_score

154 — /enkrypt/safety_score

144 — /enkrypt/source

160 — /enkrypt/staleAfter

150 — /enkrypt/toxicity_score

31 — /expiration_date

6 — /hugging_face_id

1 — /id

89 — /isFree

30 — /knowledge_cutoff

32 — /links

33 — /links/details

90 — /mayTrainOnYourPrompts

7 — /name

84 — /object

87 — /opencode

112 — /opencode/ai_sdk_provider

163 — /opencode/family

162 — /opencode/prompt

94 — /opencode/variants

103 — /opencode/variants/high

104 — /opencode/variants/high/reasoning

106 — /opencode/variants/high/reasoning/effort

105 — /opencode/variants/high/reasoning/enabled

115 — /opencode/variants/high/verbosity

133 — /opencode/variants/instant

134 — /opencode/variants/instant/reasoning

136 — /opencode/variants/instant/reasoning/effort

135 — /opencode/variants/instant/reasoning/enabled

95 — /opencode/variants/low

96 — /opencode/variants/low/reasoning

98 — /opencode/variants/low/reasoning/effort

97 — /opencode/variants/low/reasoning/enabled

113 — /opencode/variants/low/verbosity

117 — /opencode/variants/max

118 — /opencode/variants/max/reasoning

120 — /opencode/variants/max/reasoning/effort

119 — /opencode/variants/max/reasoning/enabled

121 — /opencode/variants/max/verbosity

99 — /opencode/variants/medium

100 — /opencode/variants/medium/reasoning

102 — /opencode/variants/medium/reasoning/effort

101 — /opencode/variants/medium/reasoning/enabled

114 — /opencode/variants/medium/verbosity

129 — /opencode/variants/minimal

130 — /opencode/variants/minimal/reasoning

132 — /opencode/variants/minimal/reasoning/effort

131 — /opencode/variants/minimal/reasoning/enabled

125 — /opencode/variants/none

126 — /opencode/variants/none/reasoning

128 — /opencode/variants/none/reasoning/effort

127 — /opencode/variants/none/reasoning/enabled

137 — /opencode/variants/thinking

138 — /opencode/variants/thinking/reasoning

140 — /opencode/variants/thinking/reasoning/effort

139 — /opencode/variants/thinking/reasoning/enabled

107 — /opencode/variants/xhigh

108 — /opencode/variants/xhigh/reasoning

110 — /opencode/variants/xhigh/reasoning/effort

109 — /opencode/variants/xhigh/reasoning/enabled

116 — /opencode/variants/xhigh/verbosity

85 — /owned_by

26 — /per_request_limits

88 — /preferredIndex

19 — /pricing

78 — /pricing/audio

83 — /pricing/audio_output

21 — /pricing/completion

111 — /pricing/discount

72 — /pricing/image

69 — /pricing/image_output

71 — /pricing/image_token

79 — /pricing/input_audio_cache

35 — /pricing/input_cache_read

55 — /pricing/input_cache_write

56 — /pricing/input_cache_write_1h

80 — /pricing/internal_reasoning

57 — /pricing/overrides

81 — /pricing/overrides/*/audio

60 — /pricing/overrides/*/completion

82 — /pricing/overrides/*/input_audio_cache

61 — /pricing/overrides/*/input_cache_read

62 — /pricing/overrides/*/input_cache_write

63 — /pricing/overrides/*/input_cache_write_1h

58 — /pricing/overrides/*/min_prompt_tokens

59 — /pricing/overrides/*/prompt

74 — /pricing/overrides/*/utc_days

75 — /pricing/overrides/*/utc_days/*

77 — /pricing/overrides/*/utc_end

76 — /pricing/overrides/*/utc_start

20 — /pricing/prompt

86 — /pricing/request

34 — /pricing/web_search

164 — /providers

167 — /providers/*/context_length

174 — /providers/*/first_token_latency_ms

171 — /providers/*/is_free

176 — /providers/*/is_model_author

168 — /providers/*/pricing

169 — /providers/*/pricing/input

170 — /providers/*/pricing/output

165 — /providers/*/provider

166 — /providers/*/status

173 — /providers/*/supports_structured_output

172 — /providers/*/supports_tools

175 — /providers/*/throughput

44 — /reasoning

48 — /reasoning/default_effort

70 — /reasoning/default_enabled

45 — /reasoning/mandatory

46 — /reasoning/supported_efforts

47 — /reasoning/supported_efforts/*

73 — /reasoning/supports_max_tokens

27 — /supported_parameters

36 — /supported_parameters/*

29 — /supported_voices

68 — /supported_voices/*

122 — /terminalBench

124 — /terminalBench/avgAttemptCostUsd

123 — /terminalBench/overallScore

22 — /top_provider

23 — /top_provider/context_length

25 — /top_provider/is_moderated

24 — /top_provider/max_completion_tokens

Reset Catalog
Explore More Catalog Views

Explore Collections

  • Long Context

    Models reporting at least 131,072 context tokens, sorted numerically.

    725 Matching Listings

  • Tool Controls

    Listings that explicitly include tools in their supported parameters.

    718 Matching Listings

  • Image Input

    Listings that report image as an input modality.

    677 Matching Listings

  • Response Format Controls

    Listings that report the response_format parameter. This alone does not guarantee JSON Schema support.

    734 Matching Listings

  • Tool-Capable Hosting Offers

    Hugging Face listings with at least one offer explicitly reporting tool support.

    103 Matching Listings

  • Free Token Models

    Both reported prompt and completion rates are numerically zero. Other charges and access limits may apply.

    118 Matching Listings

  • Newly Discovered

    Listings first observed by this catalog in the past seven days; this is discovery time, not model release time.

    0 Matching Listings

Model Listings

  • OpenRouter

    Nace.AI: Drex v2.0

    nace-ai/drex-v2.0

    Drex v2.0 is a 35B mixture-of-experts decision model (3B active) from Nace.AI, the larger successor to [Drex v1.5](https://openrouter.ai/nace-ai/drex-v1.5). Given a state (text or…

    Context Tokens
    131,072
    Input Price · USD / 1M Tokens
    0.06
    Output Price · USD / 1M Tokens
    0
  • OpenRouter

    Meta: Muse Wonder

    meta/muse-wonder

    Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and…

    Context Tokens
    1,048,576
    Input Price · USD / 1M Tokens
    4
    Output Price · USD / 1M Tokens
    20
  • OpenRouter

    Microsoft: Microsoft-Decision-1

    microsoft/microsoft-decision-1

    Microsoft-Decision-1 is a small model built for fast decision-making. Instead of generating text, it reads the provided content and returns a calibrated probability for each fixed…

    Context Tokens
    32,768
    Input Price · USD / 1M Tokens
    0.042
    Output Price · USD / 1M Tokens
    0
  • OpenRouter

    Nace.AI: Drex v1.5

    nace-ai/drex-v1.5

    Drex v1.5 is a 9B decision model from Nace.AI. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal score), it returns a calibrated probability…

    Context Tokens
    131,072
    Input Price · USD / 1M Tokens
    0.04
    Output Price · USD / 1M Tokens
    0
  • OpenRouter

    Cloudflare: Clef Omni

    cloudflare/clef-omni

    Clef Omni is the mixture-of-experts member of Cloudflare's open-source Clef decision model family, a fine-tune of Qwen3-Omni-30B-A3B (30B total, 3B active parameters) served on…

    Context Tokens
    65,536
    Input Price · USD / 1M Tokens
    0.15
    Output Price · USD / 1M Tokens
    0
  • OpenRouter

    StepFun: Step 5 Preview

    stepfun/step-5-preview

    Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in…

    Context Tokens
    1,048,576
    Input Price · USD / 1M Tokens
    1
    Output Price · USD / 1M Tokens
    2.7
  • OpenRouter

    Upstage: Solar Decide Flash

    upstage/solar-decide-flash

    Solar Decide Flash is Upstage's low-latency structured decision model, a faster variant of [Solar Decide](/upstage/solar-decide) built on Solar Mini 4 and served through the…

    Context Tokens
    524,288
    Input Price · USD / 1M Tokens
    0.05
    Output Price · USD / 1M Tokens
    0
  • OpenRouter

    Anthropic: Claude Haiku 5.5

    anthropic/claude-haiku-5.5

    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…

    Context Tokens
    1,000,000
    Input Price · USD / 1M Tokens
    0.1
    Output Price · USD / 1M Tokens
    0.5
  • OpenRouter

    Anthropic: Claude Haiku 5.5 (batch)

    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…

    Context Tokens
    1,000,000
    Input Price · USD / 1M Tokens
    0.05
    Output Price · USD / 1M Tokens
    0.25
  • OpenRouter

    Perplexity: Decider V1.1 27B

    perplexity/pplx-decider-v1.1-27b

    Decider V1.1 27B is a new checkpoint of Perplexity's decision model, succeeding [Decider V1 27B](/perplexity/pplx-decider-v1-27b) with the same API contract. Instead of generating…

    Context Tokens
    262,144
    Input Price · USD / 1M Tokens
    0.02
    Output Price · USD / 1M Tokens
    0
  • OpenRouter

    ElevenLabs: Eleven v4

    elevenlabs/eleven-v4

    Eleven v4 is a text-to-speech model from ElevenLabs. It is ElevenLabs' most expressive model, with inline audio tags for emotional and delivery control, support for 90+ languages,…

    Context Tokens
    0
    Input Price · USD / 1M Tokens
    40
    Output Price · USD / 1M Tokens
    0
  • OpenRouter

    ElevenLabs: Eleven v4 Turbo

    elevenlabs/eleven-v4-turbo

    Eleven v4 Turbo is a low-latency text-to-speech model from ElevenLabs. It keeps Eleven v4's expressive delivery and audio tags while being tuned for faster generation, with…

    Context Tokens
    0
    Input Price · USD / 1M Tokens
    20
    Output Price · USD / 1M Tokens
    0
  • OpenRouter

    ElevenLabs: Eleven v3

    elevenlabs/eleven-v3

    Eleven v3 is a text-to-speech model from ElevenLabs. It produces emotionally rich, highly expressive speech with inline audio tags, supports 70+ languages, and has a…

    Context Tokens
    0
    Input Price · USD / 1M Tokens
    40
    Output Price · USD / 1M Tokens
    0
  • OpenRouter

    ElevenLabs: Eleven v3 Conversational

    elevenlabs/eleven-v3-conversational

    Eleven v3 Conversational is a text-to-speech model from ElevenLabs, a variant of Eleven v3 optimized for natural dialogue in conversational agents. It supports 70+ languages and…

    Context Tokens
    0
    Input Price · USD / 1M Tokens
    20
    Output Price · USD / 1M Tokens
    0
  • OpenRouter

    ElevenLabs: Eleven Flash v2.5

    elevenlabs/eleven-flash-v2.5

    Eleven Flash v2.5 is an ultra-low-latency text-to-speech model from ElevenLabs. It is suited for conversational and real-time use cases, supports 32 languages, and has a…

    Context Tokens
    0
    Input Price · USD / 1M Tokens
    20
    Output Price · USD / 1M Tokens
    0
  • OpenRouter

    ElevenLabs: Eleven Turbo v2

    elevenlabs/eleven-turbo-v2

    Eleven Turbo v2 is an English-only, low-latency text-to-speech model from ElevenLabs. It is suited for developer use cases where speed matters and only English is needed, and has…

    Context Tokens
    0
    Input Price · USD / 1M Tokens
    20
    Output Price · USD / 1M Tokens
    0
  • OpenRouter

    ElevenLabs: Eleven Multilingual v2

    elevenlabs/eleven-multilingual-v2

    Eleven Multilingual v2 is a text-to-speech model from ElevenLabs. It is suited for lifelike, consistent long-form narration such as voice-overs and audiobooks, supports 29…

    Context Tokens
    0
    Input Price · USD / 1M Tokens
    40
    Output Price · USD / 1M Tokens
    0
  • OpenRouter

    ElevenLabs: Eleven Turbo v2.5

    elevenlabs/eleven-turbo-v2.5

    Eleven Turbo v2.5 is a low-latency text-to-speech model from ElevenLabs. It balances quality and speed for developer use cases that need non-English languages, supports 32…

    Context Tokens
    0
    Input Price · USD / 1M Tokens
    20
    Output Price · USD / 1M Tokens
    0
  • OpenRouter

    ElevenLabs: Eleven Flash v2

    elevenlabs/eleven-flash-v2

    Eleven Flash v2 is an English-only, ultra-low-latency text-to-speech model from ElevenLabs. It is suited for conversational and real-time English use cases, and has a…

    Context Tokens
    0
    Input Price · USD / 1M Tokens
    20
    Output Price · USD / 1M Tokens
    0
  • OpenRouter

    ElevenLabs: Scribe v2

    elevenlabs/scribe-v2

    ElevenLabs Scribe v2 is a speech-to-text model that transcribes audio in 90+ languages with word-level timestamps, optional speaker diarization, and audio-event tagging.

    Context Tokens
    0
    Input Price · USD / 1M Tokens
    30.55555556
    Output Price · USD / 1M Tokens
    0
  • Next 20 Models →